Retreival of Content Based Histology Images Using Multifeature Fusion Model

Content Based Image Retrieval plays a major role in medical activities, education field and in research areas. Feature combination plays a significant role in Content Based Image Retrieval. The aim of this system is to obtain the most representative fusion model for a particular keyword that is associated with multiple query images by automatically combining heterogeneous visual features. The core approach of the system is Multiobjective learning method which aims at understanding the concept of optimal visual-semantic matching function by jointly considering the different preferences of the group of images. In this system, a new strategy called Multiobjective Optimization strategy is employed in order to handle contradictions which arise in the query images associated with the same keyword. Index Terms — Multifeature Fusion Model, Multiobjective Optimization, Pareto Archived Evolution Strategy (PAES).