OCRBeamSearchDecoder
OCRBeamSearchDecoder class provides an interface for OCR using Beam Search algorithm.
@note - (C++) An example on using OCRBeamSearchDecoder recognition combined with scene text detection can be found at the demo sample: https://github.com/opencv/opencv_contrib/blob/master/modules/text/samples/word_recognition.cpp
Member of Text
-
Creates an instance of the OCRBeamSearchDecoder class. Initializes HMMDecoder.
Declaration
Objective-C
+ (nonnull OCRBeamSearchDecoder *)create:(nonnull OCRBeamSearchDecoderClassifierCallback *)classifier vocabulary:(nonnull NSString *)vocabulary transition_probabilities_table:(nonnull Mat *)transition_probabilities_table emission_probabilities_table:(nonnull Mat *)emission_probabilities_table mode:(decoder_mode)mode beam_size:(int)beam_size;
Swift
class func create(classifier: OCRBeamSearchDecoderClassifierCallback, vocabulary: String, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: decoder_mode, beam_size: Int32) -> OCRBeamSearchDecoder
Parameters
classifier
The character classifier with built in feature extractor.
vocabulary
The language vocabulary (chars when ASCII English text). vocabulary.size() must be equal to the number of classes of the classifier.
transition_probabilities_table
Table with transition probabilities between character pairs. cols == rows == vocabulary.size().
emission_probabilities_table
Table with observation emission probabilities. cols == rows == vocabulary.size().
mode
HMM Decoding algorithm. Only OCR_DECODER_VITERBI is available for the moment (http://en.wikipedia.org/wiki/Viterbi_algorithm).
beam_size
Size of the beam in Beam Search algorithm.
-
Creates an instance of the OCRBeamSearchDecoder class. Initializes HMMDecoder.
Declaration
Objective-C
+ (nonnull OCRBeamSearchDecoder *)create:(nonnull OCRBeamSearchDecoderClassifierCallback *)classifier vocabulary:(nonnull NSString *)vocabulary transition_probabilities_table:(nonnull Mat *)transition_probabilities_table emission_probabilities_table:(nonnull Mat *)emission_probabilities_table mode:(decoder_mode)mode;
Swift
class func create(classifier: OCRBeamSearchDecoderClassifierCallback, vocabulary: String, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: decoder_mode) -> OCRBeamSearchDecoder
Parameters
classifier
The character classifier with built in feature extractor.
vocabulary
The language vocabulary (chars when ASCII English text). vocabulary.size() must be equal to the number of classes of the classifier.
transition_probabilities_table
Table with transition probabilities between character pairs. cols == rows == vocabulary.size().
emission_probabilities_table
Table with observation emission probabilities. cols == rows == vocabulary.size().
mode
HMM Decoding algorithm. Only OCR_DECODER_VITERBI is available for the moment (http://en.wikipedia.org/wiki/Viterbi_algorithm).
-
+createFromFile:
vocabulary: transition_probabilities_table: emission_probabilities_table: mode: beam_size: Creates an instance of the OCRBeamSearchDecoder class. Initializes HMMDecoder from the specified path.
Declaration
Objective-C
+ (nonnull OCRBeamSearchDecoder *) createFromFile:(nonnull NSString *)filename vocabulary:(nonnull NSString *)vocabulary transition_probabilities_table:(nonnull Mat *)transition_probabilities_table emission_probabilities_table:(nonnull Mat *)emission_probabilities_table mode:(decoder_mode)mode beam_size:(int)beam_size;
Swift
class func create(filename: String, vocabulary: String, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: decoder_mode, beam_size: Int32) -> OCRBeamSearchDecoder
-
Creates an instance of the OCRBeamSearchDecoder class. Initializes HMMDecoder from the specified path.
Declaration
Objective-C
+ (nonnull OCRBeamSearchDecoder *) createFromFile:(nonnull NSString *)filename vocabulary:(nonnull NSString *)vocabulary transition_probabilities_table:(nonnull Mat *)transition_probabilities_table emission_probabilities_table:(nonnull Mat *)emission_probabilities_table mode:(decoder_mode)mode;
Swift
class func create(filename: String, vocabulary: String, transition_probabilities_table: Mat, emission_probabilities_table: Mat, mode: decoder_mode) -> OCRBeamSearchDecoder
-
Recognize text using Beam Search.
Takes image on input and returns recognized text in the output_text parameter. Optionally provides also the Rects for individual text elements found (e.g. words), and the list of those text elements with their confidence values.
Declaration
Objective-C
- (nonnull NSString *)run:(nonnull Mat *)image min_confidence:(int)min_confidence component_level:(int)component_level;
Swift
func run(image: Mat, min_confidence: Int32, component_level: Int32) -> String
Parameters
image
Input binary image CV_8UC1 with a single text line (or word).
text elements found (e.g. words).
recognition of individual text elements found (e.g. words).
for the recognition of individual text elements found (e.g. words).
component_level
Only OCR_LEVEL_WORD is supported.
-
Recognize text using Beam Search.
Takes image on input and returns recognized text in the output_text parameter. Optionally provides also the Rects for individual text elements found (e.g. words), and the list of those text elements with their confidence values.
Declaration
Objective-C
- (nonnull NSString *)run:(nonnull Mat *)image min_confidence:(int)min_confidence;
Swift
func run(image: Mat, min_confidence: Int32) -> String
Parameters
image
Input binary image CV_8UC1 with a single text line (or word).
text elements found (e.g. words).
recognition of individual text elements found (e.g. words).
for the recognition of individual text elements found (e.g. words).