Adaptive thresholding ASIC for image processing application

Author

Talukdar, Dipankar ; Sridhar, Ramalingam

Author_Institution

Dept. of Electr. & Comput. Eng., State Univ. of New York, Buffalo, NY, USA

fYear

1993

Firstpage

104

Lastpage

107

Abstract

The ASIC implementation of a simple and effective image thresholding method is presented. The method uses a novel weight based clustering technique using a neural-network-like structure to compute a global threshold. The uniqueness of the method is its simplicity and ease of implementation. The method has been found to perform well on mailpiece images. It is a single pass algorithm that requires minimal post processing. The network structure and implementation issues are discussed

Keywords

CMOS digital integrated circuits; adaptive signal processing; application specific integrated circuits; digital signal processing chips; image classification; neural chips; neural net architecture; CMOS technology; WC Thresh; adaptive thresholding ASIC; global threshold; image processing; image thresholding; mailpiece images; network structure; neural-network-like structure; single pass algorithm; weight based clustering technique; Application software; Application specific integrated circuits; Artificial neural networks; Clustering algorithms; Computer networks; Image processing; Layout; Neural networks; Pattern recognition; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

ASIC Conference and Exhibit, 1993. Proceedings., Sixth Annual IEEE International

Conference_Location

Rochester, NY

Print_ISBN

0-7803-1375-5

Type

conf

DOI

10.1109/ASIC.1993.410819

Filename

410819