Using Haralick Features for the Distance Measure Classification of Digital Mammograms
Kishore Bhamidipati, Vijaya R Arjunan, Rupsa Saha, S. Tamil Selvan · 2014
Texture analysis is one of the primary ways of extracting relevant information from digital images. Analysis of digital mammograms is essential in distinguishing between normal tissue and tissues that are showing early signs of breast cancer. In this paper, we compute certain Haralick texture features (Angular Second Moment, Contrast, Correlation and Entropy) and compare the performance of simple distance-measure classifications with each of these features, as well as the mean of all four. The correlation feature and the mean of all four features shows better accuracy when applied on digital mammograms to classify them into normal tissues and cancerous tissues.