Optical Character Recognition

Provides access to internal data of the CharacterSample structure.

Ready-to-use tool for extracting and splitting character to single characters.

Splits an array of blobs by distance to computed base lines.

Loads serialized OcrMlpModel object from AVDATA file.

Creates training font samples from the provided regions.

Converts OcrModel to OcrMlpModel.

Converts OcrSvmModel(old type) to OcrModel.

Classifies input regions into characters. Based on the Multi-Layer Perceptron model.

Usually the last, yet the most important step of optical character recognition or verification.

Saves serialized OcrMlpModel object as AVDATA file.

Splits the input region into a fixed-size array of regions corresponding to individual characters.

Text segmentation when the number of characters is known, usually followed by a RecognizeCharacters filter.

Trains an OCR multilayer perceptron classifier.