A new approach for image enhancement applied to low-contrast-low-illumination IC and document images

Machine vision has become an integral part of today's electronic industry. Digital images capturing low contrast and low illumination conditions often cause serious problems in optical character recognition systems. This paper uses poorly digitized images of integrated circuits and documents to demonstrate the effectiveness of using the Generalized Fuzzy Operator with Histogram Equalization and Partially Overlapped Sub-Block Histogram Equalization in reducing background noise and increasing the readability of text by contrast enhancement. (c) 2004 Elsevier B.V. All rights reserved.