作者: Jeng-Daw Yang , Yung-Sheng Chen , Wen-Hsing Hsu
DOI: 10.1016/0167-8655(94)90043-4
关键词:
摘要: Abstract This paper presents an adaptive raster-scan thresholding algorithm which can deal with image acquired under imperfect illumination. A statistical measurement called LSSD (Largest Static State Difference) relating to the gray-level variation is found first. According measurement, pixels are separated into static and transient states treated by two different procedures, respectively. hardware implementation of this shows that real-time requirement be met. Experiments applying extracting characters from documents confirmed a reasonable binary efficiently effectively obtained various illuminations.