text_OCRHMMDecoder_create1
import { text_OCRHMMDecoder_create1 } from '@banou/opencv-wasm'Use after await initOpenCV(). See the initialization and named imports guide.
HMM Decoding algorithm (only Viterbi for the moment) Creates an instance of the OCRHMMDecoder class. Loads and initializes HMMDecoder from the specified path
text_OCRHMMDecoder_create1(filename: EmbindString, vocabulary: EmbindString, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: number, classifier: number): text_OCRHMMDecoder | null;3 available overloads
text_OCRHMMDecoder_create1(classifier: EmbindString, vocabulary: EmbindString, transition_probabilities_table: Mat, emission_probabilities_table: Mat): text_OCRHMMDecoder | null;text_OCRHMMDecoder_create1(classifier: EmbindString, vocabulary: EmbindString, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: number): text_OCRHMMDecoder | null;text_OCRHMMDecoder_create1(filename: EmbindString, vocabulary: EmbindString, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: number, classifier: number): text_OCRHMMDecoder | null;classifierThe character classifier with built in feature extractor.
vocabularyThe language vocabulary (chars when ascii english text). vocabulary.size() must be equal to the number of classes of the classifier.
transition_probabilities_tableTable with transition probabilities between character pairs. cols == rows == vocabulary.size().
emission_probabilities_tableTable with observation emission probabilities. cols == rows == vocabulary.size().
modeHMM Decoding algorithm. Only OCR_DECODER_VITERBI is available for the moment (http://en.wikipedia.org/wiki/Viterbi_algorithm).
filenamefilename argument (EmbindString).
The text_OCRHMMDecoder | null result.
These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.