Back to Adaptive Vision Studio website

You are here: Start » Filter Reference » Optical Character Recognition

Optical Character Recognition

Select a filter from the list below.

Icon Name Description
AccessCharacterSample Provides access to internal data of the CharacterSample structure.
AccessOcrCandidate Returns fields of OcrCandidate structure.
ExtractText Ready-to-use tool for extracting and splitting character to single characters.
GroupRegionsByLines Splits an array of blobs by distance to a computed base lines
MakeCharacterSamples Creates training font samples from the provided regions.
OcrMlpModelToOcrModel Converts OcrMlpModel(old type) to OcrModel
OcrModelToOcrMlpModel Converts OcrModel to OcrMlpModel
OcrModelToOcrSvmModel Converts OcrModel to OcrSvmModel
OcrSvmModelToOcrModel Converts OcrSvmModel(old type) to OcrModel
ReadText Ready-to-use tool for reading text from images using the OCR technique.
RecognizeCharacters Usually the last, yet the most important step of optical character recognition or verification.
SplitRegionIntoExactlyNCharacters Text segmentation when the number of characters is known, usually followed by a RecognizeCharacters filter.
SplitRegionIntoMultipleCharacters Text segmentation when the number of characters is unknown, usually followed by a RecognizeCharacters filter.
TrainOcr_MLP Trains an OCR multilayer perceptron classifier.
TrainOcr_SVM Trains an OCR support vector machines classifier.