Experimental Analysis of Medical Image Classification and Retrieval Techniques

Medical Image classification and similar image retrieval are the two important processes in diagnosis and automatic annotation. These help the doctors and radiologists in their decision making during decease identification and decision making. Image classification is usually done by checking its content similarity. Image content is its visual features referring to mathematical attributes. Similarity checking is done by using similarity or dissimilarity measures which are also known as distance metrics. As image attributes are wide in range, the similarity measure worked well for one feature set may not show the similar performance for other. For this reason in this paper we explored various existing similarity measures viz. Manhattan, Cosine, Chi-square and Cramer distances and their effect with respect to image intensity features and wavelet based texture features. We drawn certain conclusions on the performance of these distance metrics in classification and retrieval of IRMA data sets. Mean Average Precision and Average Recall Rates are used in analyzing retrieval performance for analyzing the medical image retrieval and classification task.