Operator Reference

create_ocr_class_mlpT_create_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp (Operator)

create_ocr_class_mlpT_create_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp — Create an OCR classifier using a multilayer perceptron.

Signature

create_ocr_class_mlp( : : WidthCharacter, HeightCharacter, Interpolation, Features, Characters, NumHidden, Preprocessing, NumComponents, RandSeed : OCRHandle)

Description

create_ocr_class_mlpcreate_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp creates an OCR classifier that uses a multilayer perceptron (MLP). The handle of the OCR classifier is returned in OCRHandleOCRHandleOCRHandleOCRHandleocrhandle.

For a description on how an MLP works, see create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp. create_ocr_class_mlpcreate_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp creates an MLP with OutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'softmax'"softmax""softmax""softmax""softmax". The length of the feature vector of the MLP (NumInputNumInputNumInputnumInputnum_input in create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp) is determined from the features that are used for the OCR, which are passed in FeaturesFeaturesFeaturesfeaturesfeatures. The features are described below. The number of units in the hidden layer is determined by NumHiddenNumHiddenNumHiddennumHiddennum_hidden. The number of output variables of the MLP (NumOutputNumOutputNumOutputnumOutputnum_output in create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp) is determined from the names of the characters to be used in the OCR, which are passed in CharactersCharactersCharacterscharacterscharacters. As described with create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp, the parameters PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing and NumComponentsNumComponentsNumComponentsnumComponentsnum_components can be used to specify a preprocessing of the data (i.e., the feature vectors). The OCR already approximately normalizes the features. Hence, PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing can typically be set to 'none'"none""none""none""none". The parameter RandSeedRandSeedRandSeedrandSeedrand_seed has the same meaning as in create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp. Furthermore, like for general MLP classifiers (see create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp and set_regularization_params_class_mlpset_regularization_params_class_mlpSetRegularizationParamsClassMlpSetRegularizationParamsClassMlpset_regularization_params_class_mlp), it may be desirable to regularize OCR classifiers. This can be achieved by calling set_regularization_params_ocr_class_mlpset_regularization_params_ocr_class_mlpSetRegularizationParamsOcrClassMlpSetRegularizationParamsOcrClassMlpset_regularization_params_ocr_class_mlp before training the OCR classifier. In addition, like for general MLP classifiers (see create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpcreate_class_mlp and set_rejection_params_class_mlpset_rejection_params_class_mlpSetRejectionParamsClassMlpSetRejectionParamsClassMlpset_rejection_params_class_mlp), it might be desirable to equip the OCR classifiers with the capability to reject unknown characters. The rejection class is by convention an additional symbol chr(26) that must be provided in CharactersCharactersCharacterscharacterscharacters. The parameters of the rejection class can be set by calling set_rejection_params_ocr_class_mlpset_rejection_params_ocr_class_mlpSetRejectionParamsOcrClassMlpSetRejectionParamsOcrClassMlpset_rejection_params_ocr_class_mlp before training the OCR classifier.

The features to be used for the classification are determined by FeaturesFeaturesFeaturesfeaturesfeatures. FeaturesFeaturesFeaturesfeaturesfeatures can contain a tuple of several feature names. Each of these feature names results in one or more features to be calculated for the classifier. Some of the feature names compute gray value features (e.g., 'pixel_invar'"pixel_invar""pixel_invar""pixel_invar""pixel_invar"). Because a classifier requires a constant number of features (input variables), a character to be classified is transformed to a standard size, which is determined by WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character and HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character. The interpolation to be used for the transformation is determined by InterpolationInterpolationInterpolationinterpolationinterpolation. It has the same meaning as in affine_trans_imageaffine_trans_imageAffineTransImageAffineTransImageaffine_trans_image. The interpolation should be chosen such that no aliasing effects occur in the transformation. For most applications, InterpolationInterpolationInterpolationinterpolationinterpolation = 'constant'"constant""constant""constant""constant" should be used. It should be noted that the size of the transformed character is not chosen too large, because the generalization properties of the classifier may become bad for large sizes. In particular, large sizes will lead to the fact that small segmentation errors will have a large influence on the computed features if gray value features are used. This happens because segmentation errors will change the smallest enclosing rectangle of the regions, which leads to the fact that the character is zoomed differently than the characters in the training set. In most applications, sizes between 6x8 and 10x14 should be used.

The parameter FeaturesFeaturesFeaturesfeaturesfeatures can contain the following feature names for the classification of the characters.

'default'"default""default""default""default": 'ratio'"ratio""ratio""ratio""ratio" and 'pixel_invar'"pixel_invar""pixel_invar""pixel_invar""pixel_invar" are selected.
'pixel'"pixel""pixel""pixel""pixel": Gray values of the character (WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character x HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).
'pixel_invar'"pixel_invar""pixel_invar""pixel_invar""pixel_invar": Gray values of the character with maximum scaling of the gray values (WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character x HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).
'pixel_binary'"pixel_binary""pixel_binary""pixel_binary""pixel_binary": Region of the character as a binary image zoomed to a size of WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character x HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character (WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character x HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).
'gradient_8dir'"gradient_8dir""gradient_8dir""gradient_8dir""gradient_8dir": Gradients are computed on the character image. The gradient directions are discretized into 8 directions. The amplitude image is decomposed into 8 channels according to these discretized directions. 25 samples on a 5x5 grid are extracted from each channel. These samples are used as features (200 features).
'projection_horizontal'"projection_horizontal""projection_horizontal""projection_horizontal""projection_horizontal": Horizontal projection of the gray values (see gray_projectionsgray_projectionsGrayProjectionsGrayProjectionsgray_projections, HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).
'projection_horizontal_invar'"projection_horizontal_invar""projection_horizontal_invar""projection_horizontal_invar""projection_horizontal_invar": Maximally scaled horizontal projection of the gray values (HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).
'projection_vertical'"projection_vertical""projection_vertical""projection_vertical""projection_vertical": Vertical projection of the gray values (see gray_projectionsgray_projectionsGrayProjectionsGrayProjectionsgray_projections, WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character features).
'projection_vertical_invar'"projection_vertical_invar""projection_vertical_invar""projection_vertical_invar""projection_vertical_invar": Maximally scaled vertical projection of the gray values (WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character features).
'ratio'"ratio""ratio""ratio""ratio": Aspect ratio of the character (see height_width_ratioheight_width_ratioHeightWidthRatioHeightWidthRatioheight_width_ratio, 1 feature).
'anisometry'"anisometry""anisometry""anisometry""anisometry": Anisometry of the character (see eccentricityeccentricityEccentricityEccentricityeccentricity, 1 feature).
'width'"width""width""width""width": Width of the character before scaling the character to the standard size (not scale-invariant, see height_width_ratioheight_width_ratioHeightWidthRatioHeightWidthRatioheight_width_ratio, 1 feature).
'height'"height""height""height""height": Height of the character before scaling the character to the standard size (not scale-invariant, see height_width_ratioheight_width_ratioHeightWidthRatioHeightWidthRatioheight_width_ratio, 1 feature).
'zoom_factor'"zoom_factor""zoom_factor""zoom_factor""zoom_factor": Difference in size between the character and the values of WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character and HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character (not scale-invariant, 1 feature).
'foreground'"foreground""foreground""foreground""foreground": Fraction of pixels in the foreground (1 feature).
'foreground_grid_9'"foreground_grid_9""foreground_grid_9""foreground_grid_9""foreground_grid_9": Fraction of pixels in the foreground in a 3x3 grid within the smallest enclosing rectangle of the character (9 features).
'foreground_grid_16'"foreground_grid_16""foreground_grid_16""foreground_grid_16""foreground_grid_16": Fraction of pixels in the foreground in a 4x4 grid within the smallest enclosing rectangle of the character (16 features).
'compactness'"compactness""compactness""compactness""compactness": Compactness of the character (see compactnesscompactnessCompactnessCompactnesscompactness, 1 feature).
'convexity'"convexity""convexity""convexity""convexity": Convexity of the character (see convexityconvexityConvexityConvexityconvexity, 1 feature).
'moments_region_2nd_invar'"moments_region_2nd_invar""moments_region_2nd_invar""moments_region_2nd_invar""moments_region_2nd_invar": Normalized 2nd moments of the character (see moments_region_2nd_invarmoments_region_2nd_invarMomentsRegion2ndInvarMomentsRegion2ndInvarmoments_region_2nd_invar, 3 features).
'moments_region_2nd_rel_invar'"moments_region_2nd_rel_invar""moments_region_2nd_rel_invar""moments_region_2nd_rel_invar""moments_region_2nd_rel_invar": Normalized 2nd relative moments of the character (see moments_region_2nd_rel_invarmoments_region_2nd_rel_invarMomentsRegion2ndRelInvarMomentsRegion2ndRelInvarmoments_region_2nd_rel_invar, 2 features).
'moments_region_3rd_invar'"moments_region_3rd_invar""moments_region_3rd_invar""moments_region_3rd_invar""moments_region_3rd_invar": Normalized 3rd moments of the character (see moments_region_3rd_invarmoments_region_3rd_invarMomentsRegion3rdInvarMomentsRegion3rdInvarmoments_region_3rd_invar, 4 features).
'moments_central'"moments_central""moments_central""moments_central""moments_central": Normalized central moments of the character (see moments_region_centralmoments_region_centralMomentsRegionCentralMomentsRegionCentralmoments_region_central, 4 features).
'moments_gray_plane'"moments_gray_plane""moments_gray_plane""moments_gray_plane""moments_gray_plane": Normalized gray value moments and the angle of the gray value plane (see moments_gray_planemoments_gray_planeMomentsGrayPlaneMomentsGrayPlanemoments_gray_plane, 4 features).
'phi'"phi""phi""phi""phi": Sinus and cosinus of the orientation (angle) of the character (see elliptic_axiselliptic_axisEllipticAxisEllipticAxiselliptic_axis, 2 feature).
'num_connect'"num_connect""num_connect""num_connect""num_connect": Number of connected components (see connect_and_holesconnect_and_holesConnectAndHolesConnectAndHolesconnect_and_holes, 1 feature).
'num_holes'"num_holes""num_holes""num_holes""num_holes": Number of holes (see connect_and_holesconnect_and_holesConnectAndHolesConnectAndHolesconnect_and_holes, 1 feature).
'cooc'"cooc""cooc""cooc""cooc": Values of the binary cooccurrence matrix (see gen_cooc_matrixgen_cooc_matrixGenCoocMatrixGenCoocMatrixgen_cooc_matrix, 8 features).
'num_runs'"num_runs""num_runs""num_runs""num_runs": Number of runs in the region normalized by the height (1 feature).
'chord_histo'"chord_histo""chord_histo""chord_histo""chord_histo": Frequency of the runs per row (not scale-invariant, HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character features).

After the classifier has been created, it is trained using trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlptrainf_ocr_class_mlp. After this, the classifier can be saved using write_ocr_class_mlpwrite_ocr_class_mlpWriteOcrClassMlpWriteOcrClassMlpwrite_ocr_class_mlp. Alternatively, the classifier can be used immediately after training to classify characters using do_ocr_single_class_mlpdo_ocr_single_class_mlpDoOcrSingleClassMlpDoOcrSingleClassMlpdo_ocr_single_class_mlp or do_ocr_multi_class_mlpdo_ocr_multi_class_mlpDoOcrMultiClassMlpDoOcrMultiClassMlpdo_ocr_multi_class_mlp.

HALCON provides a number of pretrained OCR classifiers (see the “Solution Guide I”, chapter 'OCR', section 'Pretrained OCR Fonts'). These pretrained OCR classifiers can be read directly with read_ocr_class_mlpread_ocr_class_mlpReadOcrClassMlpReadOcrClassMlpread_ocr_class_mlp and make it possible to read a wide variety of different fonts without the need to train an OCR classifier. Therefore, it is recommended to try if one of the pretrained OCR classifiers can be used successfully. If this is the case, it is not necessary to create and train an OCR classifier.

A comparison of the MLP and the support vector machine (SVM) (see create_ocr_class_svmcreate_ocr_class_svmCreateOcrClassSvmCreateOcrClassSvmcreate_ocr_class_svm) typically shows that SVMs are generally faster at training, especially for huge training sets, and achieve slightly better recognition rates than MLPs. The MLP is faster at classification and should therefore be preferred in time critical applications. Please note that this guideline assumes optimal tuning of the parameters.

Execution Information

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Processed without parallelization.

This operator returns a handle. Note that the state of an instance of this handle type may be changed by specific operators even though the handle is used as an input parameter by those operators.

Parameters

WidthCharacterWidthCharacterWidthCharacterwidthCharacterwidth_character (input_control) integer → (integer)

Width of the rectangle to which the gray values of the segmented character are zoomed.

Default: 8

Suggested values: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 20

Value range: 4 ≤ WidthCharacter WidthCharacter WidthCharacter widthCharacter width_character ≤ 20

HeightCharacterHeightCharacterHeightCharacterheightCharacterheight_character (input_control) integer → (integer)

Height of the rectangle to which the gray values of the segmented character are zoomed.

Default: 10

Suggested values: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 20

Value range: 4 ≤ HeightCharacter HeightCharacter HeightCharacter heightCharacter height_character ≤ 20

InterpolationInterpolationInterpolationinterpolationinterpolation (input_control) string → (string)

Interpolation mode for the zooming of the characters.

Default: 'constant' "constant" "constant" "constant" "constant"

List of values: 'bicubic'"bicubic""bicubic""bicubic""bicubic", 'bilinear'"bilinear""bilinear""bilinear""bilinear", 'constant'"constant""constant""constant""constant", 'nearest_neighbor'"nearest_neighbor""nearest_neighbor""nearest_neighbor""nearest_neighbor", 'weighted'"weighted""weighted""weighted""weighted"

FeaturesFeaturesFeaturesfeaturesfeatures (input_control) string(-array) → (string)

Features to be used for classification.

Default: 'default' "default" "default" "default" "default"

List of values: 'anisometry'"anisometry""anisometry""anisometry""anisometry", 'chord_histo'"chord_histo""chord_histo""chord_histo""chord_histo", 'compactness'"compactness""compactness""compactness""compactness", 'convexity'"convexity""convexity""convexity""convexity", 'cooc'"cooc""cooc""cooc""cooc", 'default'"default""default""default""default", 'foreground'"foreground""foreground""foreground""foreground", 'foreground_grid_16'"foreground_grid_16""foreground_grid_16""foreground_grid_16""foreground_grid_16", 'foreground_grid_9'"foreground_grid_9""foreground_grid_9""foreground_grid_9""foreground_grid_9", 'gradient_8dir'"gradient_8dir""gradient_8dir""gradient_8dir""gradient_8dir", 'height'"height""height""height""height", 'moments_central'"moments_central""moments_central""moments_central""moments_central", 'moments_gray_plane'"moments_gray_plane""moments_gray_plane""moments_gray_plane""moments_gray_plane", 'moments_region_2nd_invar'"moments_region_2nd_invar""moments_region_2nd_invar""moments_region_2nd_invar""moments_region_2nd_invar", 'moments_region_2nd_rel_invar'"moments_region_2nd_rel_invar""moments_region_2nd_rel_invar""moments_region_2nd_rel_invar""moments_region_2nd_rel_invar", 'moments_region_3rd_invar'"moments_region_3rd_invar""moments_region_3rd_invar""moments_region_3rd_invar""moments_region_3rd_invar", 'num_connect'"num_connect""num_connect""num_connect""num_connect", 'num_holes'"num_holes""num_holes""num_holes""num_holes", 'num_runs'"num_runs""num_runs""num_runs""num_runs", 'phi'"phi""phi""phi""phi", 'pixel'"pixel""pixel""pixel""pixel", 'pixel_binary'"pixel_binary""pixel_binary""pixel_binary""pixel_binary", 'pixel_invar'"pixel_invar""pixel_invar""pixel_invar""pixel_invar", 'projection_horizontal'"projection_horizontal""projection_horizontal""projection_horizontal""projection_horizontal", 'projection_horizontal_invar'"projection_horizontal_invar""projection_horizontal_invar""projection_horizontal_invar""projection_horizontal_invar", 'projection_vertical'"projection_vertical""projection_vertical""projection_vertical""projection_vertical", 'projection_vertical_invar'"projection_vertical_invar""projection_vertical_invar""projection_vertical_invar""projection_vertical_invar", 'ratio'"ratio""ratio""ratio""ratio", 'width'"width""width""width""width", 'zoom_factor'"zoom_factor""zoom_factor""zoom_factor""zoom_factor"

CharactersCharactersCharacterscharacterscharacters (input_control) string-array → (string)

All characters of the character set to be read.

Default: ['0','1','2','3','4','5','6','7','8','9']

NumHiddenNumHiddenNumHiddennumHiddennum_hidden (input_control) integer → (integer)

Number of hidden units of the MLP.

Default: 80

Suggested values: 1, 2, 3, 4, 5, 8, 10, 15, 20, 30, 40, 50, 60, 70, 80, 90, 100, 120, 150

Restriction: NumHidden >= 1

PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing (input_control) string → (string)

Type of preprocessing used to transform the feature vectors.

Default: 'none' "none" "none" "none" "none"

List of values: 'canonical_variates'"canonical_variates""canonical_variates""canonical_variates""canonical_variates", 'none'"none""none""none""none", 'normalization'"normalization""normalization""normalization""normalization", 'principal_components'"principal_components""principal_components""principal_components""principal_components"

NumComponentsNumComponentsNumComponentsnumComponentsnum_components (input_control) integer → (integer)

Preprocessing parameter: Number of transformed features (ignored for PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing = 'none'"none""none""none""none" and PreprocessingPreprocessingPreprocessingpreprocessingpreprocessing = 'normalization'"normalization""normalization""normalization""normalization").

Default: 10

Suggested values: 1, 2, 3, 4, 5, 8, 10, 15, 20, 30, 40, 50, 60, 70, 80, 90, 100

Restriction: NumComponents >= 1

RandSeedRandSeedRandSeedrandSeedrand_seed (input_control) integer → (integer)

Seed value of the random number generator that is used to initialize the MLP with random values.

Default: 42

OCRHandleOCRHandleOCRHandleOCRHandleocrhandle (output_control) ocr_mlp → (handle)

Handle of the OCR classifier.

Example (HDevelop)

read_image (Image, 'letters')
* Segment the image.
binary_threshold(Image,&Region, 'otsu', 'dark', &UsedThreshold);
dilation_circle (Region, RegionDilation, 3.5)
connection (RegionDilation, ConnectedRegions)
intersection (ConnectedRegions, Region, RegionIntersection)
sort_region (RegionIntersection, Characters, 'character', 'true', 'row')
* Generate the training file.
count_obj (Characters, Number)
Classes := []
for J := 0 to 25 by 1
    Classes := [Classes,gen_tuple_const(20,chr(ord('a')+J))]
endfor
Classes := [Classes,gen_tuple_const(20,'.')]
write_ocr_trainf (Characters, Image, Classes, 'letters.trf')
* Generate and train the classifier.
read_ocr_trainf_names ('letters.trf', CharacterNames, CharacterCount)
create_ocr_class_mlp (8, 10, 'constant', 'default', CharacterNames, 20, \
                      'none', 81, 42, OCRHandle)
trainf_ocr_class_mlp (OCRHandle, 'letters.trf', 100, 0.01, 0.01, Error, \
                      ErrorLog)
* Re-classify the characters in the image.
do_ocr_multi_class_mlp (Characters, Image, OCRHandle, Class, Confidence)

Result

If the parameters are valid, the operator create_ocr_class_mlpcreate_ocr_class_mlpCreateOcrClassMlpCreateOcrClassMlpcreate_ocr_class_mlp returns the value 2 ( H_MSG_TRUE) . If necessary, an exception is raised.

Possible Successors

trainf_ocr_class_mlptrainf_ocr_class_mlpTrainfOcrClassMlpTrainfOcrClassMlptrainf_ocr_class_mlp, set_regularization_params_ocr_class_mlpset_regularization_params_ocr_class_mlpSetRegularizationParamsOcrClassMlpSetRegularizationParamsOcrClassMlpset_regularization_params_ocr_class_mlp, set_rejection_params_ocr_class_mlpset_rejection_params_ocr_class_mlpSetRejectionParamsOcrClassMlpSetRejectionParamsOcrClassMlpset_rejection_params_ocr_class_mlp

Alternatives

create_ocr_class_svmcreate_ocr_class_svmCreateOcrClassSvmCreateOcrClassSvmcreate_ocr_class_svm

Module

OCR/OCV

Operators