Abstract
this paper is practically interested in the unchangeable feature of Arabic handwritten character. It presents results of comparative study achieved on certain features extraction techniques of handwritten character, based on Hough transform, Fourier transform, Wavelet transform and Gabor Filter. Obtained results show that Hough Transform and Gabor filter are insensible to the rotation and translation, Fourier Transform is sensible to the rotation but insensible to the translation, in contrast to Hough Transform and Gabor filter, Wavelets Transform is sensitive to the rotation as well as to the translation.
Highlights
In order to improve the recognition rate of Arabic handwritten character, several techniques based on geometric correction or mathematic transform have been tested and applied on the input image of such writing
We calculate the gravity center of the connected component contained in each block which is used in the voting procedure of the Hough transform
Interpretation: The previous results show that: The four feature extraction techniques can give interesting recognition rates depending to the initial conditions of the Arabic writing, Hough Transform and Gabor filter are insensible to the rotation and translation, Hough Transform and Gabor filter are efficient and strong tools for the detection of remarkable shapes in a picture, Hough Transform, was very slow because of the corresponding complexity, Fourier Transform is sensible to the rotation but insensible to the translation, In contrast to Hough Transform and Gabor filter, Wavelets Transform is sensitive to the rotation as well as to the translation, The writing size variation doesn’t have an influence on the recognition average time for the four studied extraction techniques
Summary
Abstract—this paper is practically interested in the unchangeable feature of Arabic handwritten character. It presents results of comparative study achieved on certain features extraction techniques of handwritten character, based on Hough transform, Fourier transform, Wavelet transform and Gabor Filter. Obtained results show that Hough Transform and Gabor filter are insensible to the rotation and translation, Fourier Transform is sensible to the rotation but insensible to the translation, in contrast to Hough Transform and Gabor filter, Wavelets Transform is sensitive to the rotation as well as to the translation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
