Fuzzy logic based handwritten character recognition

Abstract

In this paper. an attempt is made to develop off-line recognition strategies for the isolated. handwritten English characters (A to Z. a to z). The preprocessing of characters comprises bounding of characters for translation invariance and normalization of characters for size invariance. The variability in a character introduced by the rotation and deformation is the main concern of this paper. This variability has been taken into account by devising a fuzzy logic based approach using normalized angle features.

PIXBAS "Pixel Based Offline Signature Verification"

“…As a result, individuals who do not sign their names in a consistent manner series of signatures that are similar enough that the system can locate a large percentage of the common characteristics between the enrollment signatures. For the purpose of signature detection and verification of forgeries TS model I used in the existing methods [8,9]. During verification enough characteristics must remain constant to determine with confidence that the authorized person signed.…”

India Handwritten Digits Recognition

“…Where, (xi , yi) are the co-ordinates of a pixel in a sector and (xm , yn) are the co-ordinates of the center of the digit image [10].…”

Grey target theory based equipment condition monitoring and wear mode recognition

“…But there are some subjective factors in fuzzy logic, such as defining a proper membership grade function and selecting a representative characteristic number. How to establish a membership grade function in the fuzzy logic based pattern recognition algorithm needs further studies [6][7][8][9][10]. Moreover, fuzzy logic has poor learning capability, though it has good adaptability in expressing approximate and quantitative knowledge [11].…”