An Artificial Neural Network Based Segmentation Algorithm for Off-line Handwriting Recognition M. Blumenstein and B. Verma
نویسندگان
چکیده
Artificial Neural Networks (ANNs) have been successfully applied to Optical Character Recognition (OCR) yielding excellent results. This paper presents a method for segmentation of difficult handwriting with the use of conventional algorithms in conjunction with ANNs. The segmentation algorithm is heuristic in nature detecting important features which may represent a prospective segmentation point. An Artificial Neural Network is subsequently used to verify the authenticity of the segmentation points found by the algorithm. The C programming language, the SP2 supercomputer and a SUN workstation were used for the experiments. The algorithm has been tested on real-world handwriting obtained from the CEDAR database. Some preliminary experimental results are presented in this paper.
منابع مشابه
Artificial Neural Network Based Segmentation Algorithm for Off-line Handwriting Recognition
متن کامل
Conventional vs Neuro-Conventional Segmentation Techniques for Handwriting Recognition: A Comparison
− The success of Artificial Neural Networks (ANNs) has been prominent in many real-world applications including handwriting recognition. This paper compares two techniques for the task of segmenting touching and cursive handwriting. The first technique uses a conventional heuristic algorithm to detect prospective segmentation points in handwritten words. For each segmentation point a character ...
متن کاملFusion of Segmentation Strategies for Off-Line Cursive Handwriting Recognition
Cursive handwriting recognition is a challenging task for many real-world applications such as document authentication, form processing, postal address recognition, reading machines for the blind, bank check recognition, and interpretation of historical documents. Therefore, in the last few decades, researchers have put an enormous effort into developing various techniques for handwriting recog...
متن کاملA Novel Feature Extraction Technique for the Recognition of Segmented Handwritten Characters
High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word recognition systems. This research describes neural network-based techniques for segmented character recognition that may be applied to the segmentation and recognition components of an off-line handwritten word recognition system. Two neural architectures along with two differe...
متن کاملEnhancing Neural Confidence-based Segmentation for Cursive Handwriting Recognition
This paper proposes some directions for enhancing a neural network-based technique for automatically segmenting cursive handwriting. The technique fuses confidence values obtained from left and center character recognition outputs in addition to a Segmentation Point Validation output. Specifically, this paper describes the use of a recently proposed feature extraction technique (Modified Direct...
متن کامل