A fuzzy statistical rule generation method for handwriting recognition
نویسندگان
چکیده
This paper presents a statistical approach for rule-base generation of handwriting recognition. The new proposed method integrates the heuristic feature selection with the statistical evaluation and thus improves the generation speed and the performance of the fuzzy rule-based handwriting recognition system. Fuzzy statistical measures are employed to identify relevant features from a given large handwriting data-base. First an automatic rule-base mechanism is presented. To reduce the time needed for this generation mechnism an additonal heuristic feature selection step is introduced. Tests show that this generated rule-base improved the recognition results over previous approaches.
منابع مشابه
A hybrid approach of automatic fuzzy rule generation for handwriting recognition
This paper presents a hybrid approach of automatic fuzzy rule generation for on-line handwriting recognition. The fuzzy rules contain the feature information extracted from a given prototype data set. The fuzzy statistical measures and neural networks are used to select the associative features from the input symbols. The final decision is enhanced through additional combination with expert’s k...
متن کاملAutomatic Generation of a Fuzzy Rule Base for Online Handwriting Recognition
An automatic method to generate fuzzy rules and their membership functions to recognize handwritten characters is described. Firstly an initial rule base is created on the basis of a referential data set containing handwriting prototypes. Subsequently the classification behavior of the fuzzy rules is optimized with a genetic algorithm, which is regarded as a typical solution to NP-complete prob...
متن کاملFuzzy handwriting description language: : FOHDEL
In this paper we present a new fuzzy language } FOHDEL } for the syntactic description of handwritten symbols. The presented language incorporates the fuzzy logic techniques to describe the syntactic relations of the semantic features extracted from a symbol pattern. A FOHDEL rule-base represents the compact feature information extracted from a small number of character prototypes and covers va...
متن کاملMulti-Script Handwriting Recognition with FOHDEL*
Until now handwritten character recognition systems used script specific methodologies. In this paper we present a unified syntactic approach for multi-script recognition. The fuzzy pattern description language -FOHDELis used to store fuzzy features in the form of fuzzy rules. First we briefly describe the proposed recognition methodology for Latin, Devanagari and Kanji scripts by analyzing the...
متن کاملA Fuzzy Syntactic Method for On-Line Handwriting Recognition
Fuzzy logic has proved to be a powerful tool to represent imprecise and irregular patterns. Thus the representation of handwriting parameters is accomplished with fuzzy linguistic modeling. The development of a multi-layered rule based handwriting recognition system is described. The selection of the representative features, which describe the shapes and location of segments, is the core of the...
متن کامل