Method and apparatus for connected and degraded text recognition

A text recognition system, the system comprising:

• means for performing image enhancement on a scanned text image;
• means, coupled to the means for performing image enhancement, for performing sub-character segmentation, each resulting sub-character segment comprising a substantially vertical portion of said scanned text image;
• means, coupled to the means for performing sub-character segmentation, for performing feature extraction based on sub-character segments;
• means, coupled to the means for performing feature extraction, for performing recognition of text based on a comparison of extracted sub-character features and stochastic models of known characters;
• and
• memory means, coupled to the means for performing recognition of text, for storing the results of text recognition,
• wherein said means for performing sub-character segmentation comprises:
• means for determining one or more groups of nodes, wherein a node comprises a set of consecutive scanned pixels of a first binary value;
• means for determining one or more strokes in the scanned text image based on characteristics of said determined groups of nodes, wherein each stroke comprises a line segment characterizing a group of nodes;
• and
• means for segmenting the scanned text image into one or more of said substantially vertical sub-character segments based on one or more of said determined strokes.

A method of training an optical text character recognition system with use of a plurality of sets of pixel signals representing text characters, the system including a memory for storing training information signals, the method comprising the steps of:

• segmenting each set of pixel signals into one or more sub-character segments, each sub-character segment comprising a substantially vertical portion of said set of pixel signals;
• generating one or more feature signals characterizing a sub-character segment of a given set of pixel signals;
• generating signals reflecting a stochastic representation of a particular sub-character segment, which signals reflect occurrences of feature signals corresponding to said sub-character segment in said sets of pixel signals;
• and
• storing said signals reflecting said stochastic representation of said particular sub-character segment in said memory,
• wherein said step of segmenting each set of pixel signals comprises the steps of:
• determining one or more groups of nodes, wherein a node comprises a set of consecutive scanned pixels of a first binary value;
• determining one or more strokes in the set of pixel signals based on characteristics of said determined groups of nodes, wherein each stroke comprises a line segment characterizing a group of nodes;
• and
• segmenting the set of pixel signals into one or more of said substantially vertical sub-character segments based on one or more of said determined strokes.