A Content Based Image Information Retrieval for Medical MRI Brain Images based on Hadoop and Lucene (LIRe)

Abhay R. Palle, Dr. R. B. Kulkarni

Abstract: CBIR technique is one of the important techniques for feature extraction in medical field in order to store, manage, and retrieve image data based on user query. Searching is done by means of matching the image features such as texture, shape, or different combinations of them. We propose a robust retrieval using a supervised classifier which concentrates on extracted features. Gray level co-occurrence matrix algorithm is implemented to extract the texture features from images. The feature optimization is done on the extracted features to select best features out of it to train the classifier. Hadoop platform is used to store large dataset of images. The purpose of this research work is to conclude normal and abnormal image using content based image retrieval on hadoop platform.

Keywords: CBIR, Hadoop, Lucene