All Published Papers Search Service

Title

Distance Measures for Identification of Inks

Author

Haritha Dasari, Chakravarthy Bhagvati

Vol. 7  No. 6  pp. 51-56

Abstract

An important problem in questioned document examination is detection of alterations done by inserting words or additional lines of text. In this paper, we present a statistical pattern recognition driven approach that views it as a two-class problem. Given two sample words, one of which is a suspected alteration, it is necessary to determine if the two belong to the same class or different classes. It requires the comparison of images for differences in ink colour dominant wavelength, colour distribution and the striations or traces that the instruments leave. The comparison of images is done by using distance measures that are more sensitive to subtle variations in colour and dealing with the more general features like mean colour vectors etc. Two new distance measures in HSV colour space are formulated that have enhanced sensitivity in detecting similar colours. Several colour distance measures are used and are analyzed for their colour discriminating abilities with reference to forensic document examination. Our experimental results involving more than 95000 pairs of word images show that the approach gives an accuracy of over 90%.

Keywords

Image Processing, Forensic Document Examination, Distance Measures, HSV colour space