An Experimental Evaluation of Preprocessing Parameters for GA Based OCR Segmentation

【摘要】：Automated learning systems used to extract information from images, play a major role in document analysis. Optical character recognition or OCR has been widely used to automatically segment and index the documents from a wide space. Most of the methods used for OCR recognition and extraction like HMM’s, Neural etc, mentioned in literature have errors which require human operators to be rectified and fail to extract images with blur as well as illumination variance. The paper presents the analysis of GA based image enhancement algorithm previously proposed by the author [1] which is much superior over the other algorithms mentioned in literature. This paper analyses the variation in results due to the deviation in histogram (bins) of the algorithm. The histogram is the most important feature of the image depicting the distribution of the image. A small variation in histogram will result into an important change in the final result of the operations performed on the image. Hence it is extremely important to analyse the pre- processing parameters involved before the final algorithm is executed. The histogram of the image is distributed into different bins and further the variation in the results is observed proclaiming the best possible solution for histogram of the image. The system described is capable of extracting normal as well as blurred images and images for different lighting conditions. The paper further elaborates the limitations of the method.