Resources and suggestions for iOS developers

OCR-IT Cloud-based OCR API was one of the first high-quality online OCR Optical Character Recognition) services on the market. It launched in 2009 and started to appear in various implementations by 2010. On of the first apps on Apple Store was FotoNote app, which to this day gets 5-star rating due to high OCR quality. Many other apps followed with unique and creative uses of OCR. OCR-IT offers a number of plans and resources to enable iOS developers to use the OCR-IT API in their own apps. Pricing Plans All currently available pricing plans are listed here: Pricing Plans Development Account – developers receive Free account and full access to API for entire development and testing lifecycle.  Full access to resources is provided along with live testing environment.  Sign up to Development & Testing plan to start the development. Production Account – once the app is ready to go live, a different subscription from Development & Testing plan is needed.  Developer can choose any other plan available from OCR-IT plan selection page, depending on the estimated volume of images to be processed.  Alternatively, a custom plan can be discussed and created if Developer finds that a different licensing model will be more beneficial. API Technical Resources There are three major sources of technical information for iOS developers: API Documentation – detailed technical documentation explaining every part of OCR service and its usage. OCR-IT Blog – a number of articles containing tips, tricks and best approaches to creating powerful and effective OCR-based apps. OCR-IT Support Team – technical experts with many years of OCR and image processing experience.  OCR-IT staff can help answer theoretic and practical questions regarding image and text quality, use...

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,...

Standard Process for Managed Document Conversion and Outsourcing

OCR-IT Document Conversion Services Team uses the following methodology and project progress tracking for every Document Conversion task. Party Stage Task Client INITIATION Issue the Order for Service, complete Service Agreement, discuss project progression. Client PREPARATION Prepare documents for processing.  Documents should be in PDF (without password protection or content extraction limitations), TIF, JPEG, BMP, PNG file format.  Documents may be in sub-folder structure, or in a single folder.  This original structure will be preserved for Delivery. Client SEND Documents should be provided to OCR-IT for processing. Media options are: – FTP (OCR-IT will provide secure FTP location) – HDD (Recommended for large volumes over several GB) – Any other standard storage media, such as USB drive, flash card, DVD, etc. Sending options are: – FedEx – FTP – Local pickup (for urgent projects) OCR-IT SETUP Documents are received and checked for transmission errors.  Processing profile is created.  Processing settings are confirmed to client. OCR-IT PROOF RUN A small sample set is processed using created settings.  Processed set is delivered to client for review. Client PROOF CHECK Sample is reviewed and settings confirmed.  Upon confirmation, OCR-IT locks down settings to be used for the entire volume. OCR-IT PRODUCTION Entire volume goes into production with confirmed settings.  Progress updates are provided every 48 hours to completion. OCR-IT QA Upon completion, results are checked using following techniques: – Total count IN = total count OUT – File name IN = file name OUT – Random spot check to verify successful processing (searchability) and desired file format output (per settings) NOTE: Some projects may or may not include manual verification of text. OCR-IT DELIVERY...