Technical FAQs

Question

What quality should my images be for processing form data and recognition using FormSuite?

Answer

In all cases, you want to have your images as clear and as clean as possible. For any particular procedure, please consider the following:

OCR and ICR: Capture images in at least 300 DPI resolution. Ideally, working in black and white allows the objects of interest on your image to be better defined and recognized. Free the image form all noise as much as possible. As if a human were reading it, you want the text objects on the image to be as legible as possible. For ICR, ensure that the characters are printed (no cursive text, etc).

Barcode recognition: As with OCR and ICR, capture images in at least 300 DPI and working with black and white content can provide excellent results. Ensure that the bars in the barcodes are clearly defined on the image and are not malformed (for example, the barcodes should have the proper start and stop sequence, etc). Clear as much noise from the image as possible.

Forms matching and registration: As with the prior 2 items above, capture your documents in at least 300 DPI. Ensure that your resolution is consistent between your form templates and incoming batch images. Form templates should only contain data that is common to every image that is being processed (i.e. Form fields, the text that appears on the blank form itself, etc). The template should not have filled-in field information as this will affect the forms matching process.

View Detail >
Question

What are the best quality images to use when processing form data and recognition?

Answer

In all cases, you’ll want to have your images as clear and as clean as possible. For any particular procedure, please consider the following: OCR and ICR: Capture images in at least 300 DPI resolution. Ideally, working in black and white will allow the objects of interest on your image to be better defined and recognized. Free the image form all noise as much as possible. As if a human was reading it, you’ll want the text objects on the image to be as legible as possible. For ICR, make sure that the characters are printed (no cursive text, etc). Barcode recognition: As with OCR and ICR, capture images in at least 300 DPI and working with black and white content can provide excellent results. You’ll also want to make sure that the bars in the barcodes are clearly defined on the image and are not mal-formed (for example, the barcodes should have the proper start and stop sequence, etc). As always, clear as much noise from the image as possible. Forms matching and registration: As with the prior 2 items above, capture your documents in at least 300 DPI. Make sure that your resolution is consistent between your form templates and incoming batch images as well. Form templates should only contain data that is common to every image that is being processed (i.e. – Form fields, the text that appears on the blank form itself, etc). The template should not have filled-in field information as this will affect the forms matching process.

View Detail >

PDFs HTML embed

As digital processes become more commonplace, it’s more important than ever for organizations to have the tools in place to manage electronic documents effectively. The evolution of PDF viewing technology continues to provide new levels of flexibility for software applications. Now that HTML5 is capable of rendering PDF data within a conventional browser, developers are looking for new ways to make the viewing experience even more seamless. By embedding PDFs in HTML, they can continue to streamline document viewing and reduce the need for external software.

Why Embed a PDF in HTML?

Sharing a PDF online is far easier to do today than it was just a decade ago. For many years, the two most commonly used options were providing a link to download the file directly from a server or sending it as an attachment in an email. Once the file was downloaded, it could be opened and viewed with PDF reader software installed on a computer. This, of course, introduced numerous security risks that are associated with downloadable files and email attachments.

The widespread adoption of cloud storage has made it very convenient to share a PDF file and even manage who has access to it. And since most modern browsers can view PDFs without needing to download the file, providing a link is typically all that’s necessary to pass the file along.

While this solution is usually sufficient for the personal needs of an individual user, it’s not a practical option for even a small-scale business when it comes to public-facing document management. Organizations want to retain control over their files with respect to how they’re accessed and displayed. By embedding PDFs in HTML, they can keep their documents within their secure application environment where they have full control over how they’re managed, shared, and viewed. For developers looking to provide a seamless user experience, building options for embedded PDFs into their software is critically important.

The Value of an Integrated PDF Viewer

Since most modern browsers can utilize HTML5 to render PDF files, developers could lean on those capabilities without building a dedicated PDF viewer for their application. That decision will very quickly lead to some unpleasant complications, however. In the first place, they are leaving a lot to chance in terms of the viewing experience. Not every browser renders PDF files the same way, so it’s very possible that two different users could have two very different experiences when viewing a document. In some cases, that could mean nothing more than a missing font that’s replaced with an alternative. But in other cases, it could mean that the document doesn’t open at all or is missing important graphical elements.

This approach also forces users to make do with whatever PDF functionality is incorporated into their browser’s viewer. In most cases, that will mean subpar search performance, a lack of responsive mobile controls, and no annotation features. The browser may also have trouble with some of the less common PDF specifications, making it impossible for some users to even view a document.

By embedding a JavaScript-based PDF viewer into their application, developers can ensure that documents will display the correct way every time. Since the viewing is handled through a viewer embedded into the web application by default, it will be the same no matter what kind of browser or operating system is being used. A customizable viewer also allows developers to adjust the interface to permit or hide certain features, such as downloading or markup tools.

The open-source PDF.js library is a popular choice for many web applications, but it comes with a number of well-documented shortcomings. In addition to lacking key features like annotation, it also doesn’t support the entire PDF standard and does not provide a responsive UI for mobile devices. For developers looking to add more robust features, working with PDF.js often entails quite a bit of additional coding and engineering to build those capabilities from the ground up.

Embed PDFs in HTML with Accusoft PDF Viewer

Accusoft PDF Viewer takes the foundation of PDF.js and provides robust enhancements to meet the viewing needs of today’s applications. In addition to incredibly fast text search, expanded PDF standard support, and optimization for high-resolution displays, this lightweight SDK is also equipped with a responsive UI that adapts automatically to mobile screens. Developers can integrate essential mobile features like pinch to zoom quickly and easy, with no additional integrations or engineering required.

With no external dependencies or complicated server configurations, Accusoft PDF Viewer integrates into a web-based application with less than 10 lines of code. Once the viewer is in place, developers can embed PDFs in HTML and easily render them to provide a state-of-the-art PDF viewing experience regardless of the browser or device users have at their disposal. And since the UI can be customized to your application’s needs, there’s no reason to sacrifice control for the sake of viewing convenience.

Accusoft PDF Viewer is a JavaScript SDK that you can incorporate into your application environment quickly and easily to provide much greater viewing control and functionality than is possible with a standard browser viewer or base PDF.js library. If you’re planning to embed PDFs in HTML as part of your software solution, taking just a few moments to integrate versatile and responsive viewing tools can ensure a high-quality viewing experience. Download Accusoft PDF Viewer Standard Version today at no cost to see how easily it can transform your application’s HTML5 viewing potential.

For additional features like annotation, eSignature, and UI customization, contact one of our solutions experts to upgrade to Professional Version.

View Detail >
Question

When doing a text search in a document in PrizmDoc, the highlight color for the search results is a light blue background. Is there a way to change the highlight color for search results in the PrizmDoc Viewer?

Answer

You can change the highlight color specifically in the PrizmDoc Viewer file viewer.js file located in the viewer-assets\js folder of your project/application.

You will need to locate 2 instances of the search term “highlightColor: undefined” in the code block below located close to line 4400. The actual line number will vary depending on the version of viewer.js you are using. You can replace “undefined” with a hexadecimal color value which you can look up from the following site: https://htmlcolorcodes.com/

// This is a request for a new searchQuery triggered by the search input field.
// Generate new search terms, and save them globally.
prevMatchingOptions = _.clone(matchingOptions);

if (matchingOptions.exactPhrase) {
    // We need to match the exact string, as is
    if (queryString.length) {
        searchTerms.push({
            searchTerm: queryString,
            highlightColor: undefined,
            searchTermIsRegex: false,
            contextPadding: 25,
            matchingOptions: matchingOptions
        });
    }
} else {
    // Split up multiple words in the string into separate search term objects
    var queryArr = queryString.split(' ');
    queryArr = _.unique(queryArr);
    _.forEach(queryArr, function(query){
        if (query.length) {
            searchTerms.push({
                searchTerm: query,
                highlightColor: undefined,
                searchTermIsRegex: false,
                contextPadding: 25,
                matchingOptions: matchingOptions
            });
        }
    });
}
View Detail >
Question

How can I change the PrizmDoc Viewer so that the TextSelection tool is selected by default instead of the Pan tool?

Answer

In order to select the TextSelection tool by default in PrizmDoc Viewer there are a few things you need to take into account. First, you have to click the button inside the embedViewer() function found in the index page of the sample. Second, the button for the text selection tool is actually disabled initially, so in order to be able to click it, the button has to be enabled first by removing the pcc-disabled class.

Use the following code to do this:

function embedViewer(options) {
    var viewer = $('#viewer1').pccViewer(options);
    viewer.viewerControl.on(PCCViewer.EventType.ViewerReady, function(viewer) {
        $("[data-pcc-mouse-tool=\"AccusoftSelectText\"]").removeClass('pcc-disabled');
        $("[data-pcc-mouse-tool=\"AccusoftSelectText\"]").click();            
    });
}
View Detail >
Question

In some cases, when the Server Licensing Utility (SLU) is run, it may return an error similar to the following:

"Server License Utility – Auto register failed

Failed to auto-register. Extra code
#0100-20(RCN=Accusoft.ULF.LicenseService.GenerateLicenseKey,
RC=-56, REC=428). Contact Accusoft support. Error #1"

If, on the other hand, you manually register, you might see a message such as this:

An error has occurred: object (Accusoft.ULF.LicenseService.GenerateLicenseKey), value1 (-56), value2 (429)

What could be the cause?

Answer

A possible cause for this error is if you have a license with an expiration date and you have not specified the Access Key in the field on the SLU main window. Since these particular keys expire, our licensing needs to know which specific Access Key to use to differentiate it from any other licenses you may have with different expiration dates or OEM licenses. So, supplying the Access Key will point the license utility to the specific license in the license pool, and should resolve this error.

View Detail >

Although it might feel as though time has been standing still for several months, 2020 is finally coming to an end. It’s been a year of unprecedented disruption for many industries, and insurance companies often found themselves struggling to adapt to change. Firms that had the foresight to invest in digital transformation backed by InsurTech solutions, however, proved more capable of meeting the moment and are now poised to thrive in 2021 and beyond.

As the new year approaches, it’s helpful to take a look back at some of the key trends that defined 2020 and created opportunities for innovative InsurTech applications. Understanding the pressures facing the insurance industry will also identify InsurTech projections to watch in the future.

5 Insurance Trends and InsurTech Projections

1. Remote Collaboration

No discussion of 2020 insurance industry trends would be complete without exploring how the COVID-19 pandemic has affected organizations. According to a survey conducted by Deloitte, 48 percent of insurance executives agreed that the pandemic revealed how unprepared their business was for such a disruptive crisis. From the sudden transition to a remote workforce to a shift in risk adjustment factors across the market, insurers have had to scramble to adapt their operations and continue delivering quality services to clients.

With so many employees going remote and customers unable to meet with representatives in-person, organizations that made early investments in digital collaboration tools and automation software were better equipped to meet the challenges of 2020. The industry is expected to make tremendous investments in digital transformation in the upcoming year, whether it’s in powerful document editing and management software, file conversion tools, or secure communication channels that better facilitate true collaboration.

2. Customer Demographic Shifts

Prior to 2020, insurance customers tended to be older, with millennials purchasing life insurance policies at lower rates and often delaying home ownership until later in life. This trend seems to have reversed itself in the wake of the COVID-19 pandemic, however, with life insurance application activity growing twice as fast for people under 45 than those aged 45-49. Since many of these younger buyers are first-time applicants, it’s important for insurance agents and firms to make the process as streamlined and easy to navigate as possible.

According to a nationwide industry survey, just over 75 percent of independent insurance agents are age 50 or older and nearly 68 percent have more than 20 years of experience. Having such a long-tenured workforce poses challenges when it comes to implementing new processes and reaching out to potential customers with different needs and preferences than those of earlier decades. In order to remain competitive, however, firms must invest in the right InsurTech solutions to gather data that will give them a better picture of what insurance products and services younger customers will find attractive.

3. Robotic Process Automation

The shift to a remote workplace greatly disrupted traditional workflows. Without centralized offices, key insurance tasks like claims processing and document verification are much more difficult to perform manually. Organizations that had already invested in robotic process automation (RPA) to handle repetitive tasks were in a much better position to thrive in a remote landscape. 

Insurance companies must be able to process a variety of forms during an application or a claim. Having automated InsurTech tools in place to quickly extract data from a variety of sources and carry information over from one form to another not only saves time, but also greatly reduces the risk of human error. For a remote workforce, automation software helps to consolidate complex workflows to eliminate version confusion and enhance collaboration.

4. Artificial Intelligence

Risk assessment and data analysis are crucial to the underwriting process. In a volatile economic environment, insurance firms are under more pressure than ever before to set the right premiums. Although the data is now readily available to make more accurate assessments, sorting through that information manually is difficult and time consuming. 

As the COVID-19 pandemic demonstrated, the scope of risk can change dramatically in a very short period of time. By deploying artificial intelligence (AI) to analyze risk factors and review potential fraud claims quickly and accurately, insurers can create customized policies and provide more responsive service to their customers.

Implementing AI-driven algorithms as part of the underwriting and fraud analysis process will only be one part of the challenge facing firms in 2021. These powerful tools must have sufficient data in order to make informed predictions. By improving the data collection process with form processing tools, file conversion, and programmatic searches, insurers can provide their analytics platforms the best possible information for analysis.

5. Customer Experience

One of the few positive impacts of the COVID-19 pandemic was that it forced organizations across every industry to find new ways of connecting with their customers. The insurance industry has traditionally lagged behind other sectors, tending to lean upon a combination of tradition and legacy infrastructure to engage with customers. But the events of 2020 have underscored the need for a true digital transformation that fundamentally reorients the way firms market, sell, and deliver insurance products. The need has become so evident, in fact, that a recent PWC survey found that 70 percent of insurance CEOs are prioritizing customer experience and user interfaces as their top investment opportunity.

In the coming year, firms will likely continue to invest in technology that makes it easier for customers to research and manage their policies. Whether it’s applications that allow them to submit claims information in a variety of file formats or forms and contracts that automatically fill in commonly used form fields, the core focus will be on making the customer experience as frictionless as possible with a variety of InsurTech benefits.

The Role of InsurTech

Many insurance companies will be looking to upgrade their technology stack and client-facing applications in response to these trends. That creates a tremendous opportunity for InsurTech developers who are creating the next generation of software tools to streamline core processes common to the insurance industry.

Delivering those digital products on a short timeline with limited resources, however, can be quite a challenge for even the most innovative InsurTech startup. That’s why many of them turn to third-party solutions to provide proven functionality that lies outside the scope of their development expertise. 

Features like forms processing, document conversion, and image viewing can be easily integrated into an application using an SDK or API, saving the team weeks or even months of work. This helps InsurTech companies get their products to market faster to meet the digital transformation needs of their customers and keep them a step ahead of their competitors.

InsurTech SDKs and APIs

Accusoft’s family of processing and automation SDKs and APIs provide InsurTech developers with the tools they need to easily plug essential functionality into their applications so they can get back to focusing on their most innovative features. With a variety of deployment options and a diverse set of code-based solutions, we have the flexibility to meet your software’s unique use case and substantially reduce your time to market.

Whether you’re looking to integrate document viewing, collaboration, or processing to your InsurTech platform, our SDK and API-based products can help you deliver the InsurTech benefits your customers are looking for. Learn more about our insurance solutions or contact us today to demo one of our products.

View Detail >

Although often considered a bit old fashioned, the insurance industry has made great strides in recent years to adapt to the changing needs of its customers. The latest generation of insurance customers expects faster service, better support, and more options from providers. Given these pressures, it’s no surprise that InsurTech developers have found ample opportunities to deliver solutions that help insurance firms better manage their workflows and create better customer experiences.

Despite the successes of this digital transformation, however, there are still a number of challenges that InsurTech developers face when building new applications. Investing heavily in creating powerful AI and big data tools might help those platforms stand out from the crowd, but they won’t find much success with firms if they don’t also provide the core functionality organizations need to service their customers. 

That’s why many InsurTech developers are turning to versatile SDK and API integrations to expand their feature sets without compromising their development timelines.

4 Major Challenges of InsurTech Applications

1. Security and Privacy

As the insurance industry continues to shift toward digital processes and platforms, it’s become more important than ever for InsurTech applications to keep sensitive data secure. While most organizations do invest in cybersecurity protections, they often don’t realize how their own practices could potentially pose a risk to customer information. This is especially true of insurers that rely on third-party programs for various tasks like document viewing and editing. Take, for instance, the case of Folksam Group, which inadvertently shared client data from as many as one million customers with Google, Facebook, LinkedIn, Microsoft, and Adobe in late 2020. 

2. File Management

Today’s insurers are receiving all kinds of documents, files, and images from their customers, which creates something of a document dilemma. A single auto accident claim, for instance, might have valuable information spread across multiple PDFs, Word documents, spreadsheet files, scanned images of hand-written forms, and image files. In order to process claims quickly and effectively, firms need InsurTech solutions that provide an all-in-one solution that can handle a broad array of file formats. Without these file management tools, insurers will be forced to use multiple programs to meet their needs, which creates inefficient dependencies and increases security risks.

3. Data Collection

Insurance companies gather quite a bit of information from form applications, both in physical and digital formats. Unfortunately, transferring that information from a form document into an InsurTech system is often a laborious manual process. Not only is manual data collection time consuming, it also increases the likelihood of human error. Even when firms do implement an InsurTech solution with forms processing capabilities, however, they often lack the capability to read certain types of form fields, especially those completed by hand. The ability to adapt to new form templates is also critical for organizations that want to invest in automation. 

4. Remote Collaboration

The COVID-19 pandemic may have forced insurance offices to rapidly embrace a remote work strategy, but many firms had already been investing in some form of hybrid work model for years. Nationwide was able to transition 98 percent of its workforce to remote status precisely because the company already had the technology solutions in place to allow insurance agents to work from home. Without some way of facilitating remote collaboration directly through InsurTech applications, organizations end up relying on email, which poses serious security concerns. Furthermore, with multiple copies of a document being distributed and downloaded, it quickly becomes difficult to know which version incorporates the most up-to-date changes.

SDK and API InsurTech Solutions

Building new functionality into an application always involves a tradeoff. When developers choose to code something from scratch, that means pulling team members away from another project or extending the product’s release timeline. In a fast-moving industry where InsurTech developers are racing competitors to be the first to market, it doesn’t make sense to design and build every aspect of an application in-house. 

Rather than pulling valuable development resources away from their innovative InsurTech features, developers can solve common insurance challenges much faster with SDK toolkits and API integrations. 

Secure File Viewing

The easiest way for InsurTech solutions to keep documents secure is to integrate HTML5 viewing capabilities directly into the application. Rather than being forced to download or open a file for viewing in a third-party application, employees can view multiple document formats natively. This is critical because it means no data will be shared with third-party programs.  Since the files remain safely within the secure InsurTech environment, firms can also control the level of access to any document, which prevents unauthorized individuals from downloading or viewing the contents. Thanks to API-based integrations like Accusoft’s PrizmDoc Viewer, InsurTech developers can help their applications safely view more than 100 unique file types without any third-party dependencies.

Data Capture

By integrating forms processing capabilities into their applications, InsurTech developers can provide their clients with powerful tools that allow them to gather essential data quickly and accurately. As the essential connective tissue between customers and insurance databases, form field recognition integrations use OCR technology to intelligently identify form data and extract it for processing. They can also be set up to identify a wide range of insurance forms to quickly identify and scan documents to streamline processing workflows. Accusoft’s FormSuite for Structured Forms even goes a step further by incorporating powerful image cleanup functionality to ensure that data will be extracted as accurately as possible.

File Conversion

In order to meet the file management challenges of today’s insurance providers, InsurTech developers need document and image processing integrations that can read and write multiple file formats. Information spread across multiple documents, emails, or even texts can be processed using OCR technology, and then consolidated and converted into a variety of formats for easy reference and collaboration. Rather than juggling several files with different dependencies, an SDK integration like Accusoft’s ImageGear can easily output processed files in PDF, RTF, XML, or DOCX format for viewing and editing within a single application.

Editing and Annotation

Providing secure document viewing capabilities solves only one half of the insurance collaboration challenge. InsurTech applications also need to provide both internal and external stakeholders with the ability to edit and markup documents throughout the application and claims process. Content processing integrations can allow authorized users to make changes to documents completely within their InsurTech solution and review markups and comments from other collaborators. 

Since all editing occurs within the application itself, there’s no need to worry about anyone downloading a document to make changes locally and creating confusion over which version is the most up-to-date. Redactions may also be necessary to hide private or confidential information from unauthorized viewers. As an added benefit, PrizmDoc Viewer’s editing features allow users to make a variety of markups and redactions while preserving the integrity of the original file.

Accelerate Your InsurTech Application Development with Accusoft

Accusoft’s collection of powerful SDK toolkits and API integrations provide innovative InsurTech developers with the resources they need to solve core insurance industry challenges. By implementing proven functionality into their applications, project managers can streamline the development process and dedicate more resources to the innovative features that will set their platform apart from the competition.

Whether you’re looking to incorporate versatile document viewing and editing or need a more accurate forms processing solution, Accusoft’s family of InsurTech SDKs and APIs can help your development team get to market faster. Learn more about what our products can do for your application in our InsurTech fact sheet.

 

View Detail >

Today’s organizations gather information from a variety of sources. Structured forms remain one of the most popular tools for collecting and processing data, and anyone who has filled out such a form recently has likely encountered the familiar bubbles or squares used to indicate some form of information. Whether these marks are used to identify marital status, health conditions, education level, or some other parameter, optical mark recognition plays an important role in streamlining forms processing and data capture.

What is Optical Mark Recognition?

Optical mark recognition (OMR) reads and captures data marked on a special type of document form. In most instances, this form consists of a bubble or a square that is filled in as part of a test or survey. After the form is marked, it can either be read by dedicated OMR software or fed into a physical scanner device that shines a beam of light onto the paper and then detects answers based on how much light is reflected back to an optical sensor. Older OMR scanners detected answers by measuring how much light passed through the paper itself using phototubes on the other side. Since the phototubes were very sensitive, #2 pencils often had to be used when filling out forms to ensure an accurate reading.

Today’s OMR scanners are much more accurate and versatile, capable of reading marks regardless of how they’re filled out (although they struggle if the mark is made with the same color as the printed form). More importantly, OMR software has made it possible to capture data from OMR forms without the need for any special equipment. This is especially helpful for processing forms information that exists in digital format, such as PDF files or JPEG images. 

The History of Optical Mark Recognition

One of the oldest versions of forms processing technology, OMR dates back to the use of punch cards, which were first developed in the late 1800s for use with crude “tabulating” machines. The cards typically provided simple “yes/no” information based on whether or not a hole was punched out. When fed through the tabulating machine, a hole would be registered and counted. This same basic principle would allow more complex machines to perform basic arithmetic in the early 1900s before serving as the foundation for early computer programming by mid-century. Entire computer programs were stored on stacks of punch cards, which would remain in use until well into the 1970s when more powerful machines made them obsolete.

Although OMR operates on the same principle as a punch card, it instead uses scanning technology to detect the presence of a mark made by a pencil or a pen. This form of identification was first popularized by IBM’s electrographic “mark sense” technology in the 1930s and 1940s. The concept itself was first developed by a schoolteacher named Reynold Johnson, who wanted to streamline test grading. He designed a machine that could read pencil marks on a special test paper and then tabulate the marks to generate a final score. After joining IBM in 1934, Johnson spearheaded the development of the Type 805 Test Scoring Machine, which debuted in 1938 and revolutionized test scoring in the education sector. In production until 1963, the 805 could score 800 sheets per hour when run by an experienced operator.

The 805 registered marks by using metal brushes to sense the electrical conductivity of graphite from the pencil lead. While effective, it had limitations in terms of reading speed and flexibility. When Everett Franklin Lindquist, best known as the creator of the ACT, needed a machine that could keep up with Iowa’s widespread adoption of standardized testing in the 1950s, he developed the first true optical mark reader. Patented in 1962, Lindquist’s machine detected marks by measuring how much light passed through a scoring sheet and was capable of scoring 4,000 tests per hour.

Throughout the 1960s, OMR scanning technology continued to improve and spread to a variety of industries looking for ways to rapidly process data. In education, however, the OMR market would soon be dominated by the Scantron Corporation, which was founded in 1972 to market smaller, less expensive scanners to K-12 schools and universities. After placing the scanners in educational institutions, Scantron then sold large quantities of proprietary test sheets that could be used for a variety of testing purposes. Scantron was so successful that their distinctive green and white sheets have become synonymous with OMR scanning for generations of US college students.

The next major innovation in OMR technology arrived in the early 1990s with dedicated OMR software that could replicate the drop-out capabilities of commercial scanners. Part of the reason why scanners used proprietary, pre-printed forms was so they could use colors and watermarks that would not register during scanning for more accurate reading. Thanks to OMR software, it became possible to create templated forms and then remove the form image during the reading process to ensure that only marked information remained.

Take Control of OMR Forms with Accusoft SDKs

Accusoft’s FormFix forms processing SDK features powerful production-level OMR capabilities. It not only detects the presence of check or bubble marks, but can also detect markings in form fields, which is particularly useful for determining whether or not a signature is present on a document. Capable of reading single or multiple marks at 0, 90, 180, and 270 degree orientations, FormFix can also recognize checkboxes and be programmed to accommodate a variety of bubble shapes. Its form drop-out and image cleanup features also help to ensure the highest level of accuracy during OMR reading.

For expanded forms functionality, including optical character recognition (OCR) and intelligent character recognition (ICR), developers can also turn to FormSuite for Structured Forms. Featuring a comprehensive set of forms template creation tools and data capture capabilities, FormSuite can streamline forms processing workflows and significantly reduce the costs and errors associated with manual data entry and extraction.

Find out what flexible OMR functionality can do for your application with a fully-featured trial of the FormSuite SDK. Get started with some functional sample code and explore FormFix’s features to start planning your integration.

View Detail >

Seventy-six percent of companies surveyed plan to prioritize machine learning (ML) and artificial intelligence (AI) deployments in 2021. Despite increased uptake, however, there is still a great deal of confusion surrounding these advanced concepts. In order to understand how organizations hope to leverage ML and AI in their technology initiatives, it’s helpful to take a step back and examine how they work and how they differ from each other.

What Is Machine Learning?

Machine learning uses statistics-driven algorithms to find patterns in massive amounts of data. These algorithms are designed to improve over time as they process more data to enable more accurate outputs. Machine learning is widely used to produce predictive recommendations — companies such as Google, Netflix, and Facebook collect data about user behaviors and feed it into machine learning algorithms which then produce targeted search results, movie recommendations, or advertisements. 

The key to machine learning success is data. The more data available to ML algorithms — and the higher-quality this data — the better they’ll be able to identify patterns in current datasets and apply them to new data sources.

Most machine learning methodologies fall under one of two broad categories:

  • Supervised Learning: Developers classify and label data to guide the algorithm’s inputs and outputs to ensure specific patterns are recognized. This method is time and resource intensive because it requires data scientists to capture, control, and curate data sources.
  • Unsupervised Learning: This approach provides ML algorithms with unlabeled and unclassified data and allows them to identify patterns based on unique data characteristics. Developers don’t interfere with the learning and pattern recognition process, instead evaluating the outputs for accuracy and modifying code as needed.

Why Does Machine Learning Matter?

Machine learning helps organizations leverage the massive amounts of data they’ve accumulated. This information is drawn from a variety of sources, including disparate forms and documents, data produced through customer transactions and service calls, and the ongoing operational data produced by staff as they interact with IT resources.

Thanks to both the rapid uptake of cloud computing and availability of large-scale data collection and analysis tools, these data volumes are increasing exponentially. As a result, aggregate assessment is now critical — companies need a way to rapidly and reliably derive patterns from available data, and apply these patterns to predictive action.

This is the evolving role of machine learning. By creating, testing, and deploying ML algorithms capable of rapid pattern analysis and application it’s possible for companies to benefit from this continual data influx rather than being constrained by the bounds of traditional data evaluation. To facilitate this process, many next-generation software tools and services are either equipped with built-in ML frameworks or are capable of interfacing with them.

Key Machine Learning Applications

The applications of machine learning are vast, but they tend to produce the best results when paired with existing processes that supplement human efforts or automate low-value, but labor-intensive, functions in the workplace. In effect, it has the potential to do almost anything a human mind can do, given enough time. 

Improved Data Capture

Capturing data from internal documents and customer-submitted forms can be cumbersome and time-consuming. It can also lead to wasted time and effort if data is incorrectly entered, duplicated, or accidentally deleted. By pairing machine learning tools with forms processing solutions like Accusoft’s FormSuite for Structured Forms, developers can build applications that identify, collect, and capture key data more efficiently and accurately. For example, a robot process automation (RPA) bot can be set up to receive extracted form data from FormSuite and then populate that information into the appropriate fields within an application. This not only accelerates forms processing workflows, but also greatly reduces the risk of data entry error. Properly implemented, automated data capture can act as a springboard for improved data insight and decision-making thanks to improved accuracy and consistency. 

Streamlined Content Creation

By combining machine learning algorithms and data sources with document editing tools, it’s possible to streamline key processes such as the creation of complex, compliance-bound content. One in-practice example is the use of Accusoft’s PrizmDoc Editor within the LegalSifter contract review and creation platform. By pairing its AI technology with PrizmDoc Editor’s document assembly capabilities, LegalSifter was able to quickly locate repetitive clauses and suggest replacements to create an automated contract creation experience for end users. 

What Is AI, and How Does It Relate to Machine Learning?

The terms artificial intelligence and machine learning are closely related and often used interchangeably, but they’re not identical.

Artificial intelligence refers to technologies that are capable of performing tasks like photo recognition or data pattern analysis with similar (or better) outcomes than human beings. Machine learning refers to the creation, testing, and refinement of the algorithms needed to support AI tools. In many ways, then, ML functions as a distinct process that helps make AI possible.

As noted by Toward Data Science, it often helps to think of AI, machine learning, and deep learning like a set of concentric rings. The smallest, inner ring is deep learning, which helps inform the middle ring of machine learning by providing layered neural network structures that improve the process of pattern recognition. The final, outside ring is AI, which depends on both deep and machine learning to deliver real-world results. 

Artificial intelligence tools can be broken down into two basic types:

  • Generalized AI: These tools are capable of solving problems bounded by a clear set of rules. Using the ML algorithms that underpin the larger AI structure, general AI applications can act on stimuli — such as a security alert from an IT network — and respond appropriately by creating and logging reports or looping in human agents. 
  • Narrow AI: These solutions are designed to solve specific, small-scale tasks. Building on the security example from above, a narrow AI application might see tools responding to specific threat events such as DDoS or ransomware attacks by deploying targeted, defensive responses that close active sessions, capture attack data, and prevent future connections from the same IP address. 

In practice, narrow AI tools can outperform their human counterparts in completing specific tasks, but are unable to translate this expertise into applicable action at scale. General tools come closer to mimicking human intelligence but are still a long way from replicating the depth and breadth of human thinking.

Limitations of AI

Much has been made about the potential of AI technologies to take the place of human staff, leading to a generalized sense of worry about the future of these tools at scale. Recent research, however, found that substantial confusion remains around not only the deployment of AI but the definition itself. In fact, one study found that 40 percent of AI startups in Europe were not actually using AI. In some cases, increasing market interest in AI tools encouraged the use of this term to help startups capture attention, in much the same way that rapid cloud adoption spurred the creation of a host of “cloud” companies that offered nothing of the sort.

Uncertainty around AI itself, however, also plays a role in this disconnect. Given the massive potential of AI to help companies solve both specific and generalized problems, the term can be applied in almost any context and made to fit almost any description.

Unlocking the Future

After spending many years confined to research projects and future-focused technology articles, both machine learning and artificial intelligence are making their way into the applications and software companies are deploying every day. As developers look ahead to building the next generation of technology solutions, they must not only think about how they can better leverage ML and AI principles, but also how to implement features that take advantage of them.

Accusoft’s collection of versatile SDK and API integrations deliver powerful viewing and image processing capabilities that help applications streamline workflows and enhance productivity. To learn more about how Accusoft can help you enhance the workflow in your machine learning or artificial intelligence projects, contact us today.

View Detail >

For today’s healthcare organizations, having a versatile electronic health records (EHR) system is essential for running an efficient practice and connecting to other medical providers. Thanks to EHRs, practices can ensure that they’re getting a complete picture of a patient’s health and treatment history, which allows them to deliver much better care outcomes. As developers continue to refine the usability of these systems, they need to consider how they can improve core features like healthcare electronic document management and medical imaging support.

Managing Medical Documents

A typical EHR system has to be able to handle quite a lot of document types. Anyone who has visited a healthcare provider is quite familiar with the myriad forms used to gather patient information. Many of those forms end up being converted into digital formats that need to be managed within the EHR system. Then there are digital versions of lab reports, physician notes, invoices, and financial documents. 

While EHR systems may utilize databases to store much of the information they need, healthcare providers still need to be able to produce physical documents and view digital files in many situations. This could include communicating information to patients, complying with regulatory requests, or filing a financial claim of some kind. More importantly, they also rely on digital documents to enter data into the EHR system. The push toward interoperability between EHR systems has improved information sharing, but there are still many instances where medical records are delivered in the form of a document that needs to be managed securely.

Document Conversion

If an EHR application lacks the right file conversion capabilities, viewing and extracting data from those documents could prove difficult. The last thing a practice wants to do is actually remove them from the secure EHR system to open and convert the files using separate software that may not be compliant when it comes to handling healthcare information. Even if the external application is secure, transferring files over, converting them, and then transferring them back is both inefficient and creates unnecessary risk (especially if someone forgets to delete the original file or move it back into the EHR environment).

ImageGear Medical has a document conversion feature that supports a wide range of file types, allowing developers to build EHR applications capable of quickly converting incoming documents. They can even set up their solution to perform conversion tasks programmatically to help streamline workflows and minimize human error. This helps practices to get a better handle on document management, ensuring that they will be able to do everything they need with files completely within the EHR application.

Other Essential Document Features

But ImageGear Medical’s document capabilities go far beyond just conversion. With full annotation support, developers can provide markup tools within the EHR system that allow physicians to make notes and comments on various documents. This allows them to share information much more easily. If a physician has a question about a diagnosis or a prescription, for instance, they can simply leave an annotation note directly on the document rather than referring to it in a separate message.

ImageGear Medical also allows applications to perform full-page optical character recognition (OCR), which can quickly read and extract text from document and image files. This feature is especially useful for capturing text from scanned images of documents, which can then be used to create a searchable PDF or fill form fields within the EHR system. The OCR engine not only reads most Western languages, but also detects and reads several Eastern language characters.

Managing DICOM Files

One of the biggest challenges healthcare organizations face is with managing medical imaging files. When providers need to send X-Rays, MRIs, or CT Scans, they use a standardized file format known as Digital Imaging and Communications in Medicine (DICOM) files. These files are more than just image files, however. They contain extensive datasets that provide a patient’s information along with image pixel data for multi-dimensional medical scans. A DICOM file can be quite large due to the high-resolution image data used by most medical imaging equipment.

Although most EHR systems are capable of transmitting DICOM files (via a DICOM out or DICOM send feature), they usually can’t actually view them in their native format. Since Windows doesn’t recognize them as image files, additional viewing software is typically needed to open and view them. This is why physical storage, like discs and flash drives, are often used to transfer DICOM files along with the necessary viewing software.

ImageGear Medical helps to solve the DICOM dilemma thanks to its extensive conversion and compression capabilities. By decoding the complex data contained within the file, ImageGear Medical can convert DICOM files into image formats that are much easier to view and manage. This is especially useful for smaller practices that don’t have a picture archiving and communication system (PACS) capable of storing, retrieving, distributing, and viewing high-quality medical images. 

Converting DICOM files makes it possible for healthcare professionals to view them on any device connected with their EHR system. That could include tablets or other IoT devices that healthcare technology companies are rolling out to put critical medical data on the front lines of everyday care. Developers can also use ImageGear Medical’s conversion tools to allow their EHR system to share viewable versions of diagnostic scans with patients, allowing practices to make good on the promise of providing patients access to their essential health data at all times. 

The sheer size of DICOM files makes them difficult for many practices to manage. Simply compressing them tends to degrade the image data, which can create significant problems when files are unpacked and opened for viewing. Losing even a small degree of image quality can make it much harder to render an accurate diagnosis. In some cases, poorly designed compression can even make it nearly impossible to uncompress again at all. Thanks to powerful lossless compression technology, ImageGear Medical makes it easier to share medical images between providers without damaging the integrity of the original data.

Expand EHR Capabilities with ImageGear Medical

Accusoft’s imaging, conversion, and compression technology has been supporting the needs of the healthcare industry for decades. As developers work to expand the capabilities of their EHR applications, our engineers are busy improving the medical SDKs that will provide them with the features they need to stand out in a competitive market. 

ImageGear Medical utilizes a combination of efficient code and elegant APIs to deliver the document and image processing tools EHR systems require. For a closer look at this dynamic SDKs capabilities, check out our extensive developer resources today or download a free trial to get started.

View Detail >