Speed of processing

OCR-IT Cloud OCR API provides access to high-quality OCR from devices and environments where OCR does not reside locally due technical limitations and other constraints.  This enables such environments to perform OCR-related tasks without use of local resources or maintenance and upkeep.  In some cases, cloud-based OCR is the only option to enable image processing and text recognition.  As the result, since images are processed off-device, developers should consider several optimization techniques at every stage of their submission process. In general, the Web OCR process is represented here: The entire conversion workflow can be separated into these logical steps: Image capture, creation, optimization Transmission to cloud Processing Transmission back to source Text/data processing There are multiple actions developers can take at each process stage to achieve fastest possible processing.  Let’s explore each stage separately. 1. Image capture, creation, optimization – preparation of the image for submission to processing.  This is one of the most important steps in successful workflow, since all consecutive stages will depend on the result of this stage.  Image should be as clear as possible to achieve higher level of OCR.  This means using various techniques such as user guidance and training to achieve better images, on-device quality check, resolution check, shake detection, image cleanup to prepare clean and small image for transmission, as well as other techniques.  An average 3G connection upload speed on iPhone or Android device is about 0.85 Mbps (0.11MBps) per PCWorld field tests here.  The average photo size is about 2.5 MB.  This means the upload of the original photo alone will take about 23 seconds.  However, if the image is binarized prior to transmission, the resulting black & white image filesize can be about 30 KB,...

OCR-IT Team attended Apps World 2013 tradeshow in San Francisco – post visit summary

If your have attended Apps World 2013 last week, you could not have missed OCR-IT corner booth right in front of ‘Media & Speakers Lounge”.  OCR-IT Team members were wearing bright yellow sweaters and gave away environmentally-friendly carry bags, cell phone stands, and other items to booth visitors.  We had many great conversations, suggestions about future cloud-based OCR products, questions about API and valuable feedback about our existing services.   It was interesting to see people look at our diagrams for a few seconds, and then exclaim “That’s a good idea!” or “I did not know that was possible!” or “I could definitely use it in my apps!“.   On the first day over 7,000 attendees walked the show floor learning about new and emerging technologies, major service providers, and big-name players in Apps and Mobile markets.  OCR-IT shared two major offerings: OCR-IT Cloud 2.0 API and Managed OCR Services. Visitors attended seminars, visited vendor booths, and overall enjoyed modern high-tech environment between sessions. OCR-IT Team members demonstrated OCR capabilities on the spot via Web browser and mobile apps created by other third-party developers using OCR-IT API on iPhone, iPad, Android devices.  Visitors asked to take pictures of signs, their badges, business cards, receipts, books they were carrying and other text-based documents just to see how OCR-IT could process them.  Within a few seconds of processing and after seeing processing results in digital text, they were impressed with high accuracy of OCR from OCR-IT Web service.  It was great to see their reaction, smiles, and sparkles in their eyes as numerous ideas how to use OCR-IT services jumped into their minds. The second day was slower, and OCR-IT Team had more time...

Guide to better mobile images (from cell phone camera) for higher quality OCR

Mobile images make up large volume of traffic going through OCR-IT OCR Cloud 2.0 API.  Compared to conventional office documents, which are typically black on white at 200 to 400 dpi resolution images, and for which OCR technology has been fine-tuned for over a decade, mobile images vary greatly in resolution, quality, and image content, and present new and interesting challenges for technology and beyond.  With mobile image capture, technology is not the only important factor anymore, since behavior and simple actions performed by users can easily make or break any and all available technology.  So user behavior became much more important for ‘distributed capture’ of mobile images across very wide network of users with different skills and hardware.  Industry has not seen that dependency on user actions before cell phones, because using scanners, faxes, MFPs and copiers for image capture provided predictable image quality expectations controlled by mature technology and without much user intervention. In the following post I will describe most common situations encountered by OCR-IT Cloud OCR processing of pictures from mobile devices.  However, this text should apply to any OCR in general. I will use specific examples to describe and document common issues with mobile images. Document type: business card (which is in the top 5 of most frequently requested document types through OCR-IT Cloud API, receipt images being the most frequent document type) Mobile device: iPhone 4 (which is equivalent to average mobile camera, not top end camera by today’s standards) Environment: office desk, 8 PM (winter night), one fluorescent desk lamp for lighting For simplicity of explanation, and to further explain how some OCR engines operate internally,...

User Scenario: Process digital camera pictures and OCR to extract specific numbers

In this specific project asked by one of our users, we would like to provide analysis and suggestions how to process photos of marathon runners and OCR and extract text data from these pictures. This article will describe the fully automated OCR Cloud 2.0 API approach and automated tools for developers to be used without human intervention in processing of these images. If you are interested in semi-automated process including human verification options, please contact us separately. In this project, there are several parts we will discuss separately, but overall we believe it is possible to achieve good recognition result on most good images. This project can be considered medium-to-hard complexity project, due to multiple factors, technology limitations, and multiple decision steps in approach. We will test several images from the same category to illustrate how OCR works internally, what limitations exist in these specific images, and what we can do to optimize output quality. First, we will test one random image and describe every step happening to that specific image in background processes.  These same processes will happen on each image processed. The original color photograph looks like this: NOTE : It should be noted that original photographs have high resolution, and are large files around 3 MB in file size. Only for this visual explanation and illustration purposes images (above and below) were decreased in size. For simplicity of explanation, and to further explain how OCR engines operate internally, let’s review the binarized image next. Binarization – the process of converting every pixel in the photo to either black or white, which effectively converts the photo into...

Newsletter: New Releases and Upcoming Events (2012-10-03)

OCR Cloud 2.0 News New Releases and Upcoming Events Announcements Over the past many months OCR-IT Development Team has been working hard to create a new and exciting set of features and capabilities.  This is our biggest revision and addition of features since the launch of the OCR Cloud several years ago. Did you know? This high-quality OCR platform has been one of the first APIs available on the market for wide development use, delivering OCR without any startup costs.  Easy, inexpensive, good. Did you know? Early versions of this OCR system were in production even before the world new of Amazon Elastic Cloud (EC2) or what cloud architecture could do.  This is one of most mature platforms on the market today. Over the period of next several weeks we will be releasing and announcing new features, some of which will include: New News & Updates system (you are reading the first letter – this letter) New security and management protocols New subscription and management portal Improvements in speed of text recognition Profiles – fine-tuned processing scenarios OCR-IT Cloud Data Capture (TM) – revolutionary methods for extracting standardized data Addition of handwriting support Addition of new languages …many more… If you have experienced some slowdown in recent weeks, we apologize for any inconveniences.  It was necessary to update parts of our system.  Please be assured that reliability and responsiveness are among our top priorities. We are eager to announce some new features as soon as with next few days. Your OCR-IT Team About OCR-IT LLC OCR-IT LLC is an expert in OCR, document recognition, forms processing and data capture...

OCR-IT Demonstrates Power of Mobile OCR with Free Demo Android App with Full Source Code for Developers to Add OCR Capabilities

OCR-IT Demo Android App and Source Code for Android OS by the host of OCR Cloud 2.0 API lets developers add the capability to process mobile images and create usable text documents to their Android apps.  This sample app demonstrates how easily optical character recognition (OCR) can be implemented for Android OS applications and spur developers to make the leap to adding OCR to newly created applications for that platform. Download the App, full source code for this app, and view screenshots here: Android App and Source Code “The new OCR-IT Demo Android App, for the lack of better name, and its source code are designed to help app developers bring the power of OCR to their Android apps easily and seamlessly,” said company officials at OCR-IT. “In the onslaught of new apps for Android smart phones, we believe that those that integrate OCR will stand out for users. These capabilities add significant values since it lets users do more in less time by transforming paper-based documents into usable formats. We want to help more developers bring these capabilities to end users.” The OCR-IT Demo Android App allows users to capture images of documents taken with a smart phone camera and to create a document library to house document images. The solution provides single-button access that extracts text in several predefined hard-coded languages in seconds. Results can be viewed in two hard-coded formats: Searchable PDF and Plain Text TXT.  In addition, the OCR-IT Demo Android App offers links to external pages that provide additional information about OCR in the Cloud, as well as transparent details that allow developers to see...