Publications

Abstract : This method refers to the analysis of handwritten image to extract the characteristics of the image. As a part of the preprocessing stage the image is checked for noise removal, skew correction and slant removal. After preprocessing stage the text line is detected and word wise character wise segmentation is performed. The integer to integer wavelet transform is applied to the segmented image to extract the characteristics of the handwritten image. The high frequency part of the wavelet coefficients denotes the image details, the features deduced from wavelet coefficients can be used to retrieve the texture image and this method is not sensitive to luminance, these virtues cannot be found in tradition.