Package net.sourceforge.lept4j

Class L_Recog

  • Direct Known Subclasses:
    L_Recog.ByReference, L_Recog.ByValue
    public class L_Recog
extends com.sun.jna.Structure
    recog.h

    
     This is a simple utility for training and recognizing individual
    
     machine-printed text characters.  It is designed to be adapted
    
     to a particular set of character images; e.g., from a book.
    
     There are two methods of training the recognizer.  In the most
    
     simple, a set of bitmaps has been labeled by some means, such
    
     a generic OCR program.  This is input either one template at a time
    
     or as a pixa of templates, to a function that creates a recog.
    
     If in a pixa, the text string label must be embedded in the
    
     text field of each pix.
    
     If labeled data is not available, we start with a bootstrap
    
     recognizer (BSR) that has labeled data from a variety of sources.
    
     These images are scaled, typically to a fixed height, and then
    
     fed similarly scaled unlabeled images from the source (e.g., book),
    
     and the BSR attempts to identify them.  All images that have
    
     a high enough correlation score with one of the templates in the
    
     BSR are emitted in a pixa, which now holds unscaled and labeled
    
     templates from the source.  This is the generator for a book adapted
    
     recognizer (BAR).
    
     The pixa should always be thought of as the primary structure.
    
     It is the generator for the recog, because a recog is built
    
     from a pixa of unscaled images.
    
     New image templates can be added to a recog as long as it is
    
     in training mode.  Once training is finished, to add templates
    
     it is necessary to extract the generating pixa, add templates
    
     to that pixa, and make a new recog.  Similarly, we do not
    
     join two recog; instead, we simply join their generating pixa,
    
     and make a recog from that.
    
     To remove outliers from a pixa of labeled pix, make a recog,
    
     determine the outliers, and generate a new pixa with the
    
     outliers removed.  The outliers are determined by building
    
     special templates for each character set that are scaled averages
    
     of the individual templates.  Then a correlation score is found
    
     between each template and the averaged templates.  There are
    
     two implementations; outliers are determined as either:
    
      (1) a template having a correlation score with its class average
    
          that is below a threshold, or
    
      (2) a template having a correlation score with its class average
    
          that is smaller than the correlation score with the average
    
          of another class.
    
     Outliers are removed from the generating pixa.  Scaled averaging
    
     is only performed for determining outliers and for splitting
    
     characters; it is never used in a trained recognizer for identifying
    
     unlabeled samples.
    
     Two methods using averaged templates are provided for splitting
    
     touching characters:
    
      (1) greedy matching
    
      (2) document image decoding (DID)
    
     The DID method is the default.  It is about 5x faster and
    
     possibly more accurate.
    
     Once a BAR has been made, unlabeled sample images are identified
    
     by finding the individual template in the BAR with highest
    
     correlation.  The input images and images in the BAR can be
    
     represented in two ways:
    
      (1) as scanned, binarized to 1 bpp
    
      (2) as a width-normalized outline formed by thinning to a
    
          skeleton and then dilating by a fixed amount.
    
     The recog can be serialized to file and read back.  The serialized
    
     version holds the templates used for correlation (which may have
    
     been modified by scaling and turning into lines from the unscaled
    
     templates), plus, for arbitrary character sets, the UTF8
    
     representation and the lookup table mapping from the character
    
     representation to index.
    
     Why do we not use averaged templates for recognition?
    
     Letterforms can take on significantly different shapes (eg.,
    
     the letters 'a' and 'g'), and it makes no sense to average these.
    
     The previous version of this utility allowed multiple recognizers
    
     to exist, but this is an unnecessary complication if recognition
    
     is done on all samples instead of on averages.

    native declaration : recog.h:126
    This file was autogenerated by JNAerator,
    a tool written by Olivier Chafik that uses a few opensource projects..
    For help, please visit NativeLibs4Java or JNA.

    • Nested Class Summary

      Nested Classes 
      Modifier and Type Class Description
      static class  L_Recog.ByReference  
      static class  L_Recog.ByValue  

      • Nested classes/interfaces inherited from class com.sun.jna.Structure

        com.sun.jna.Structure.FieldOrder, com.sun.jna.Structure.StructField

    • Constructor Summary

      Constructors 
      Constructor Description
      L_Recog()  
      L_Recog​(com.sun.jna.Pointer peer)  

    • Method Summary

      Modifier and Type Method Description
      protected java.util.List<java.lang.String> getFieldOrder()
      Gets this Structure's field names in their proper order.

      • Methods inherited from class com.sun.jna.Structure

        allocateMemory, allocateMemory, autoAllocate, autoRead, autoRead, autoWrite, autoWrite, cacheTypeInfo, calculateSize, clear, createFieldsOrder, createFieldsOrder, createFieldsOrder, createFieldsOrder, dataEquals, dataEquals, ensureAllocated, equals, fieldOffset, getAutoRead, getAutoWrite, getFieldList, getFields, getNativeAlignment, getNativeSize, getNativeSize, getPointer, getStringEncoding, getStructAlignment, hashCode, newInstance, newInstance, read, readField, readField, setAlignType, setAutoRead, setAutoSynch, setAutoWrite, setStringEncoding, size, sortFields, toArray, toArray, toString, toString, useMemory, useMemory, write, writeField, writeField, writeField

      • Methods inherited from class java.lang.Object

        clone, finalize, getClass, notify, notifyAll, wait, wait, wait

    • Field Detail

      • scalew

        public int scalew
        scale all examples to this width;
        C type : l_int32

      • scaleh

        public int scaleh
        scale all examples to this height;
        C type : l_int32

      • linew

        public int linew
        use a value > 0 to convert the bitmap
        C type : l_int32

      • templ_use

        public int templ_use
        template use: use either the average
        C type : l_int32

      • maxarraysize

        public int maxarraysize
        initialize container arrays to this
        C type : l_int32

      • setsize

        public int setsize
        size of character set
        C type : l_int32

      • threshold

        public int threshold
        for binarizing if depth > 1
        C type : l_int32

      • maxyshift

        public int maxyshift
        vertical jiggle on nominal centroid
        C type : l_int32

      • charset_type

        public int charset_type
        one of L_ARABIC_NUMERALS, etc.
        C type : l_int32

      • charset_size

        public int charset_size
        expected number of classes in charset
        C type : l_int32

      • min_nopad

        public int min_nopad
        min number of samples without padding
        C type : l_int32

      • num_samples

        public int num_samples
        number of training samples
        C type : l_int32

      • minwidth_u

        public int minwidth_u
        min width averaged unscaled templates
        C type : l_int32

      • maxwidth_u

        public int maxwidth_u
        max width averaged unscaled templates
        C type : l_int32

      • minheight_u

        public int minheight_u
        min height averaged unscaled templates
        C type : l_int32

      • maxheight_u

        public int maxheight_u
        max height averaged unscaled templates
        C type : l_int32

      • minwidth

        public int minwidth
        min width averaged scaled templates
        C type : l_int32

      • maxwidth

        public int maxwidth
        max width averaged scaled templates
        C type : l_int32

      • ave_done

        public int ave_done
        set to 1 when averaged bitmaps are made
        C type : l_int32

      • train_done

        public int train_done
        set to 1 when training is complete or
        C type : l_int32

      • max_wh_ratio

        public float max_wh_ratio
        max width/height ratio to split
        C type : l_float32

      • max_ht_ratio

        public float max_ht_ratio
        max of max/min template height ratio
        C type : l_float32

      • min_splitw

        public int min_splitw
        min component width kept in splitting
        C type : l_int32

      • max_splith

        public int max_splith
        max component height kept in splitting
        C type : l_int32

      • sa_text

        public Sarray.ByReference sa_text
        text array for arbitrary charset
        C type : Sarray*

      • dna_tochar

        public L_Dna.ByReference dna_tochar
        index-to-char lut for arbitrary charset
        C type : L_Dna*

      • centtab

        public com.sun.jna.ptr.IntByReference centtab
        table for finding centroids
        C type : l_int32*

      • sumtab

        public com.sun.jna.ptr.IntByReference sumtab
        table for finding pixel sums
        C type : l_int32*

      • pixaa_u

        public Pixaa.ByReference pixaa_u
        all unscaled templates for each class
        C type : Pixaa*

      • ptaa_u

        public Ptaa.ByReference ptaa_u
        centroids of all unscaled templates
        C type : Ptaa*

      • naasum_u

        public Numaa.ByReference naasum_u
        area of all unscaled templates
        C type : Numaa*

      • pixaa

        public Pixaa.ByReference pixaa
        all (scaled) templates for each class
        C type : Pixaa*

      • ptaa

        public Ptaa.ByReference ptaa
        centroids of all (scaledl) templates
        C type : Ptaa*

      • naasum

        public Numaa.ByReference naasum
        area of all (scaled) templates
        C type : Numaa*

      • pixa_u

        public Pixa.ByReference pixa_u
        averaged unscaled templates per class
        C type : Pixa*

      • pta_u

        public Pta.ByReference pta_u
        centroids of unscaled ave. templates
        C type : Pta*

      • nasum_u

        public Numa.ByReference nasum_u
        area of unscaled averaged templates
        C type : Numa*

      • pixa

        public Pixa.ByReference pixa
        averaged (scaled) templates per class
        C type : Pixa*

      • pta

        public Pta.ByReference pta
        centroids of (scaled) ave. templates
        C type : Pta*

      • nasum

        public Numa.ByReference nasum
        area of (scaled) averaged templates
        C type : Numa*

      • pixa_tr

        public Pixa.ByReference pixa_tr
        all input training images
        C type : Pixa*

      • pixadb_ave

        public Pixa.ByReference pixadb_ave
        unscaled and scaled averaged bitmaps
        C type : Pixa*

      • pixa_id

        public Pixa.ByReference pixa_id
        input images for identifying
        C type : Pixa*

      • pixdb_ave

        public Pix.ByReference pixdb_ave
        debug: best match of input against ave.
        C type : Pix*

      • pixdb_range

        public Pix.ByReference pixdb_range
        debug: best matches within range
        C type : Pix*

      • pixadb_boot

        public Pixa.ByReference pixadb_boot
        debug: bootstrap training results
        C type : Pixa*

      • pixadb_split

        public Pixa.ByReference pixadb_split
        debug: splitting results
        C type : Pixa*

      • bmf_size

        public int bmf_size
        font size of bmf; default is 6 pt
        C type : l_int32

      • rch

        public L_Rch.ByReference rch
        temp data used for holding best char
        C type : L_Rch*

      • rcha

        public L_Rcha.ByReference rcha
        temp data used for array of best chars
        C type : L_Rcha*

    • Constructor Detail

      • L_Recog

        public L_Recog()

      • L_Recog

        public L_Recog​(com.sun.jna.Pointer peer)

    • Method Detail

      • getFieldOrder

        protected java.util.List<java.lang.String> getFieldOrder()
        Gets this Structure's field names in their proper order.
        Overrides:
        getFieldOrder in class com.sun.jna.Structure
        Returns:
        list of ordered field names