On Robust Automatic Offline Isolated Handwrjtten Word Verification Algorithm On Robust Automatic Offline Isolated Handwrjtten Word Verification Algorithm

ABSTRACT

Automatic Offiine Isolated handwriting word verification system using

template matching (pixel by pixel matching) is proposed in the research

work. The composition of 400 word essay, the handwritten biometrics of 50

people (students); 25 males and 25 females to handwrite the essay five times

in separate sheet of papers the aim here is to verify if a particular

handwriting is from that same person or is a fake. No speclfzcation for pen

type and color were given. The collected documents were digitized and

stored in a .bmp files. Different pre-processing stages such binarization,

noise removal, thinning, line and word segmentation were carried on the file

before matching the files. The use of template matching considering pixel by

pixel matching to do exhaustive test on different files to get a match. The

results were quite impressive different channels distortion were gotten based

on the similarity and dissimilarity tests. For the similarity test all channel

distortion are Zero (0) meaning that the files are the same, while in the

dissimilarity test channel distortion varies telling us that the files are ji-om

d[fferent people.

Read Download