PROJECT TITLE :

A Fast Fault-Tolerant Architecture for Sauvola Local Image Thresholding Algorithm Using Stochastic Computing - 2016

ABSTRACT:

Binarization plays an vital role in document image processing, particularly in degraded document pictures. Among all local image thresholding algorithms, Sauvola has excellent binarization performance for degraded document images. But, this algorithm is computationally intensive and sensitive to the noises from the inner computational circuits. In this paper, we present a stochastic implementation of Sauvola algorithm. Our experimental results show that the stochastic implementation of Sauvola desires a lot of less time and space and can tolerate a lot of faults, while consuming less power in comparison with its conventional implementation.