OCR-IT Web OCR API Free Account Setup & Testing in Fiddler Video

OCR-IT, provider on high-accuracy Web-based OCR API for platform-independent development of text recognition from images, presents… How to integrate and test OCR API in two minutes (video) [su_youtube_advanced url=”http://youtu.be/pLblxSgg4yU” rel=”no” theme=”light”] OCR-IT API will provide you with powerful capabilities to convert images to highly accurate text data.  It is currently used in numerous mobile applications, desktop software, and enterprise solutions.  Now you can use it, too. First, open a free OCR API development account by visiting http://www.ocr-it.com/free-ocr-cloud-2-0-api-trial. Click on a big red “SIGN UP NOW” button to open a new account, or LOGIN link to access your existing account.  Once the account is open, you are ready to start you development and testing. Next, write your code or use your testing environment to create an OCR-IT API request via a Web call.  For this testing, we will use Fiddler, a free Web monitoring utility. Your request will consist of only three easy parts: Request URL  This is a special URL to which you will submit your OCR requests.  It contains your Secret Key.  Both the submit URL and you Secret key can be found in your OCR-IT account. Header Make sure you are creating a POST request, and your header contains the appropriate header information. Request Body  The body should contain XML with your request specifics.  It can be very minimal as only the image URL being submitted for OCR is required.  All other settings will be used as default.  Or it may contain other settings in case you prefer to overwrite any default values, such as OCR language or other parameters. This XML is provided in the API...

Recognizing 7-segment LCD display characters using OCR-IT API

This question has been asked by a developer on Stackoverflow (source link).  OCR-IT API came to the rescue. “I’m trying to develop a Windows Phone 8.1 App but I need to recognize some numbers from different Displays.” I wish the answer to your question would be “Sure, here it is” with a link to a black-box process-anything OCR tool, but there are several stages and steps to the success are involved, which are best considered separately. First, there is some work on image pre-processing BEFORE you even consider any OCR. These image samples are very drastically different, and include full range of issues. SAMPLE 1 has low contrast, so when it is binarized to black and white layer, which most OCR will perform internally at some stage, there are no characters to process. It looks like this after binarization: See this OCR Blog post for additional details on image pre-processing: http://www.ocr-it.com/guide-to-better-mobile-images-from-cell-phone-camera-for-higher-quality-ocr. Secondly, the image has no dpi information in the header, which some OCR technologies use to determine appropriate scaling of the image. Without header information, some OCR programs may set some default dpi, which may or may not match your image, thus affecting the OCR result. This is NOT critical, but preferred if this can be implemented at the time of picture creation. SAMPLE 2 has sufficient contrast and adaptive notarization returns a clear image. It is also missing dpi resolution value in the header. SAMPLE 3 has very clear contrast, but it also has no resolution dpi in the header. Once you have images that are optimized for OCR processing, the next step is to look at OCR technologies. In...

Helping in research to extract OCR data from WWII records

Someone asked: “I am working on a research project that deals with American military casualties during WWII. Specifically, I am attempting to construct a count of casualties for each service at the county level. There are two sources of data here, each presenting their own challenges. 1. Army and Air Force data.  2. Navy and Marine Core data.” Full question is here: http://datascience.stackexchange.com/questions/5047/ocr-text-recognition-and-recovery-problem/5078#5078 Source 1 Sample Image | Source 2 Sample Image The answer to both data sets is an OCR application with some post-processing, but a more specialized program than a generic low-quality or an open source OCR. Essentially the harder the problem, the more capable and advanced tools need to be used to solve it. There will be two major stages in this task: generating the data (image to text, i.e. OCR), and processing the data (doing the actual count). Look at them separately in order to select the best method for each stage. The main challenges in these images and OCR are: a) images have low resolution. For example the # 1 image has resolution of about 72 dpi. Suggested resolution for such text quality is to scan at 300 to 400 dpi, but it is clear that re-scanning or controlling scan resolution is not applicable now. That’s why one option is to clean and increase the size using image pre-processing tools. This is what the original #1 image snippet looks like after adaptive binarization and zoomed at 300%. It is clear that each character has too few pixels and characters can be easily misread.   b) GIF format in #1 is not supported by many OCR...

Answer on StackOverflow: Detecting text in images

This question was answered on www.StackOverflow.com QUESTION Is there any good way of detecting whether an image contains text or not? I’m not looking for a way to retrieve the text, only to detect if there is one or more characters present in the image. I can understand that there is no foolproof way of detecting text, like when the font is a bit off standard; it might be hard to recognize. I’m after a “as good as can be” solution. See examples of text in images below: ANSWER Detecting if there is text is nearly the same as extracting the text, i.e. if you are able to extract text, it confirms that there is text. Detecting the text is roughly 90% same steps as extracting the text, the last 10% being some optimizations for specific languages and text types within OCR to produce better text recognition. Most of the heavy lifting happens at the beginning of the process, specifically image binarization and backgrounds removal, segmentation into objects, document analysis for layout, object type detection, and recognition of each object separately. For background information, take a look at the blog post I wrote many months ago about detecting and extracting various text via OCR from complex pictures and images: http://www.ocr-it.com/user-scenario-process-digital-camera-pictures-and-ocr-to-extract-specific-numbers For given images, take these steps one after another, and you will be able to decide if today’s technology can see text in these, and any other pictures. Binarization. Convert images to black & white. After this conversion can you see printed text characters. If no – end of of process – no text can be detected. If yes, proceed...

Tips for recognizing multiple languages and processing documents with mixed languages

OCR-IT API can recognize text in over 180 languages, more than most other OCR systems in or out of Cloud environments.  This powerful feature makes this API useful in every region of the World without the need to change API structure, develop different code, or sign up to any other services.  We currently have numerous users implementing our API to process text from images generated globally, and we continue to expand to more and more supported languages.  Language setting is one of primary parameters for successful OCR conversion, and it is FREE for you to use, unless you turn on one of specialty languages (see list below, costs extra).  Selecting incorrect language for a document most likely will cause degraded speed and quality of OCR, and frequently all text may become unreadable, so it is an important parameter. Auto-detect multiple languages?  Sure! If you do not know in advance what language will be present on the next picture or in the next document, select several language choices at once, and OCR-IT API will select the best language to use.  For example, in Canada, a user may take a picture of something in French, immediately followed by another picture in English.  Or a company in Germany may receive a fax in English, followed by a fax in German, followed by a fax in French languages.  In such situations, selecting multiple languages in OCR-IT API automatically resolves this complex technical challenge.  But there are a few suggestions which will optimize your multi-language environment: Use fewest number of possible languages for highest recognition result.  If you can precisely know which language to use with which document, such as separate folders by language, that...

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...