Topic
Intelligent word recognition
About: Intelligent word recognition is a research topic. Over the lifetime, 2480 publications have been published within this topic receiving 45813 citations.
Papers published on a yearly basis
Papers
More filters
••
19 Aug 2001TL;DR: This paper describes an offline cursive handwritten word recognition system that combines hidden Markov models (HMM) and neural networks (NN) and presents the preprocessing and the recognition process as well as the training procedure for the NN-HMM hybrid system.
Abstract: This paper describes an offline cursive handwritten word recognition system that combines hidden Markov models (HMM) and neural networks (NN). Using a fast left-right slicing method, we generate a segmentation graph that describes all possible ways to segment a word into letters. The NN computes the observation probabilities for each letter hypothesis in the segmentation graph. Then, the HMM compute the likelihood for each word in the lexicon by summing the probabilities over all possible paths through the graph. We present the preprocessing and the recognition process as well as the training procedure for the NN-HMM hybrid system. Another recognition system based on discrete HMM is also presented for performance comparison. The latter is also used for bootstrapping the NN-HMM hybrid system. Recognition performances of the two recognition systems using two image databases of French isolated words are presented. This paper is one of the first publications using the IRONOFF database, and thus can be used as a reference for future work on this database.
41 citations
•
21 Jan 1998
TL;DR: In this article, the authors proposed a method of handwritten input character recognition on the basis of the result of the comparison between ordinary strokes and transition strokes and/or start-end (s-e) strokes.
Abstract: The invention aims at recognition of a handwritten input character on-line with quite high accuracy. The method of on-line handwritten input character recognition of the invention is characterized in that ordinary strokes and transition strokes and/or start-end (s-e) strokes of a handwritten input character sampled on-line are compared with ordinary strokes and transition strokes and/or s-e strokes of dictionary's characters previously registered in a dictionary and the character corresponding to the handwritten input character is recognized on the basis of the result of the comparison. Otherwise, when the dictionary's character most similar to the input character corresponds to a preset character, the handwritten input character is identified by using characteristic features of the corresponding character. Thus, by comparing ordinary strokes and transition strokes and/or s-e strokes of a handwritten input character sampled on-line with ordinary strokes and transition strokes and/or s-e strokes of dictionary's characters previously registered in a dictionary and recognizing the character corresponding to the handwritten input character on the basis of the result of the comparison, a handwritten input character which was difficult to recognize only by means of ordinary strokes can be recognized with high accuracy.
41 citations
••
01 Aug 1968
TL;DR: A prototype of a postal code number reader capable of recognizing handwritten arabic numerals has been developed and tested successfully and the use of sequential recognition logic helps reduce the capacity of core memory required to obtain the desired high rate of recognition.
Abstract: A prototype of a postal code number reader capable of recognizing handwritten arabic numerals has been developed and tested successfully. Recognition of handwritten arabic numerals requires sufficient system flexibility to cope with both unlimited variations in character shape and a large number of writing instruments. This flexibility has been achieved by combining the use of a stored recognition table and a hardware microprogram. The recognition logic obtained by computer simulation is immediately stored in the core memory as a table. The numerals are recognized by extracting a sequence of the geometrical features in horizontal zones of the character after normalization of the height of the character and the width of the strokes. The use of sequential recognition logic helps reduce the capacity of core memory required to obtain the desired high rate of recognition. The correct recognition rate of a single digit for a large sample of letters averaged 95 percent. For a three-digit sorting with 13 stackers the sorter incorrectly recognized approximately 0.1 percent, a rate of error consistent with manual sorting.
41 citations
••
23 May 2014TL;DR: This work applied Sparse Representation Classifier on the image zone density, an image domain statistical feature extracted from the character image, to classify the Bangla numerals and demonstrates an excellent accuracy of 94% on the off-line handwritten Bangla numeral database CMATERdb 3.1.
Abstract: We present a framework for handwritten Bangla digit recognition using Sparse Representation Classifier. The classifier assumes that a test sample can be represented as a linear combination of the train samples from its native class. Hence, a test sample can be represented using a dictionary constructed from the train samples. The most sparse linear representation of the test sample in terms of this dictionary can be efficiently computed through l 1 -minimization, and can be exploited to classify the test sample. We applied Sparse Representation Classifier on the image zone density, an image domain statistical feature extracted from the character image, to classify the Bangla numerals. This is a novel approach for Bangla Optical Character Recognition, and demonstrates an excellent accuracy of 94% on the off-line handwritten Bangla numeral database CMATERdb 3.1.1. This result is promising, and should be investigated further.
41 citations