OCR Character Classifier

  • After the ABBYY document analysis technology has divided the line into words it starts on the most important and arduous task — processing individual characters such as letters and numbers and signs.
  • Breaking words into characters and recognizing these characters are all part of one single procedure, which is also true of all the other Multilevel Document Analysis (MDA) processes.
  • Once the process of division words into characters is completed, images of characters found by the program are then submitted for recognition by classifiers (special mechanisms of character recognition).

The following types of classifiers are used in ABBYY OCR technology:

  • Raster classifier
  • Feature classifier
  • Contour classifier
  • Structure classifier
  • Feature differentiating classifier
  • Structure differentiating classifier

Raster classifier

This classifier compares the character image with a set of pattern images. A pattern is a specially prepared image that combines all the possible ways of writing a given character. Patterns are created by superimposing many images of the same letter written in different ways. Depending on which pattern image is the best match for a given character image, ABBYY OCR technology will advance its hypotheses. The raster classifier work fast, but it cannot provide the required level of accuracy. However, it is widely used in many modern OCR programs.

Note: Custom Character Pattern can be trained, but please keep in mind they be only a part of the core recognition technologies applied to identify a character properly.

Feature classifier

Like the raster classifier, the feature classifier advances its hypotheses by comparing character images with pattern images. It calculates certain features of the characters under scrutiny, such as their perimeter, number of black dots in certain areas or along certain lines, etc. It is widely used in OCR programs. In certain conditions it will work just as fast as the raster classifier. Its accuracy largely depends on the right choice of features for each character. The right choice here means that the selected features must provide necessary and sufficient information about the shape of a letter. This basic selection is made by ABBYY specialists and can not be influenced in the final product.

Contour classifier

This is a type of feature classifier. It is different from the feature classifier in that it calculates the features not of the entire character but of its contour. This fast-working classifier is used for recognizing decorative fonts (e.g. Gothic script, Old Russian, etc.).

Structure classifier

This is one of the break-through technologies developed by ABBYY. It was developed and used for recognizing hand-written characters, but used for printed texts as well. This classifier analyses the structure of a character by decomposing it into constituent components (lines, arcs, circles, and dots) and recreating the exact structure of the analysed character. This structural description is then compared with pattern structures. The structure classifier works slower than the raster or feature classifiers but provides excellent recognition accuracy. This classifier can “restore” the missing or blotted out parts of characters.

Feature differentiating classifier

This classifier is used for distinguishing between very similar objects, for example the letter “m” and the ligature “rn”. This classifier is fundamentally different from the classifiers described above as it does not analyse the entire image.
Instead, it investigates only those parts of the image which may hold a clue to the solution (remember the “tree or river” example above). In the case of “m” and “n”, the clue is to be found in that part of the image where the candidate characters touch upon each other: if there is a gap between them and this gap is wide enough, the program 'understands' that it is dealing with two separate characters.

Image Description: The feature differentiating classifier at work. To choose between two similar characters (e.g. between the letters “D” and “O”), the classifier calculates feature parameters (the slope of a line in a crucial area).

Structure differentiating classifier

This is a very accurate classifier which might even be called the 'heavy artillery of OCR'. Like the structure classifier, it was initially developed and used for recognizing hand-written texts. It is also used for distinguishing between very similar characters but is a lot more precise as it analyses the structure of characters. It can recognize even distorted letters.

Image Description: The feature differentiating classifier at work. To choose between similar characters (e.g. between the combination “f1” and the letter “A”, the classifier compares the structure of the letters paying particular attention to their contours.


Back To: Inside OCR