发明名称 Methods and apparatus for adaptive auto image binarization
摘要 Bi-level pixel values are generated from a set of input pixel values corresponding to an image. Various described methods and apparatus are well suited for applications with limited computational capability and/or limited available resources to be used for performing image processing. Corresponding to an individual input pixel being processed, a plurality of windows including the pixel are evaluated to determine statistics including a variance for each window. Based upon the determined variances, one of a plurality of binarization threshold generation functions is selected. A binarization threshold for the input pixel is determined using the selected binarization threshold generation function. A bi-level pixel value is generated based on a comparison of the input pixel value to the generated binarization threshold. In various embodiments, the binarization threshold determination functions use non-zero integer powers of one or more variances, and intentionally avoid performing a square root operation, thus limiting computational complexity.
申请公布号 US9025897(B1) 申请公布日期 2015.05.05
申请号 US201313857605 申请日期 2013.04.05
申请人 Accusoft Corporation 发明人 Elton John H;Martucci Stephen A
分类号 G06K9/00;G06K9/36;G06K9/46;G06T5/00 主分类号 G06K9/00
代理机构 Straub & Pokotylo 代理人 Straub & Pokotylo ;Straub Michael P.;Straub Stephen T.
主权项 1. A method of generating bi-level pixel values from a set of input pixel values corresponding to an image, the method comprising: determining a first variance, said first variance being a variance of input pixel values in a first window of said image, said first window being of a first size and including an input pixel value being processed; determining a second variance, said second variance being a variance of input pixel values in a second window of said image, said second window at least partially overlapping said first window and including said input pixel value being processed inaddition to at least some pixel values not included in said first window; selecting, based on said first variance and said second variance, a binarization threshold generation function from a plurality of binarization threshold generation functions, said plurality of binarization threshold generation functions including at least a first binarization threshold generation function and a second binarization threshold function; and generating a bi-level pixel value from said input pixel value based on a comparison of said input pixel value to a binarization threshold generated by the selected binarization threshold generation function.
地址 Tampa FL US