Word recognition using fuzzy logic

Abstract

This paper presents an offline word-recognition system based on structural information in the unconstrained written word. Oriented features in the word are extracted with the Gabor filters. We estimate the Gabor filter parameters from the grayscale images. A two-dimensional fuzzy word classification system is developed where the spatial location and shape of the membership functions are derived from the training words. The system achieves an average recognition rate of 74% for the word being correctly classified in the top position and an average of 96% for the word being correctly classified within the top five positions.

Input-dependent neural network trained by real-coded genetic algorithm and its industrial applications

“…The recognition is realized practically in a prototyped electronic book. In general, the neural/neural-fuzzy network approaches are model-free and are good for graffiti recognition (Buse et al 2002;Gader and Khabou 1996;Zhang et al 1997;Lovell et al 1997;Perez et al 2003;Holmström et al 1997). In this example, the digits 0 to 9 and three (control) characters (backspace, carriage return and space) are recognized by the IDNN.…”

A Paper Checking Instrument with Fuzzy Pattern Recognition

“…For pages with similar contents, colour difference, and position difference etc al is existent, so quantitative mathematic disciplinarian is not suited to solving the problem of page checking. And this is a problem of fuzzy recognition actually, and needs to be solved via theory of fuzzy pattern recognition [2] [3] [4] [5] [6] [7] [8] [9] [10].…”

On Interpretation of Graffiti Digits and Characters for eBooks: Neural-Fuzzy Network and Genetic Algorithm Approach

“…Examples of structural techniques include grammatical [16] and graphical [17] methods. In general, the main idea of the neural/neural-fuzzy network approaches [18] is to learn the features of the training patterns through some processes. The input's features can then be recognized using the trained neural/NFN.…”