Investigation of Distance, Machine and Kernel Learning Similarity Methods for Visual Search in Content Based Image Retrieval

Background/Objectives: The major objective of this work is to increase the retrieval accuracy of medical images by measuring the visual similarity of Content-Based Image Retrieval (CBIR) system. Methods/Statistical Analysis: This paper presents an On-line Multiple Kernel Similarity (OMKS) learning framework for performing classification based on kernel-based proximity functions. In accordance with many existing methods some other related issues are also discussed and retrieval performance evaluation of the existing and proposed OMKS learning strategy is also discussed. Findings: Several number of the distance based learning algorithm has been proposed in recent works. It is mainly aimed for the sake of measuring the visual similarity corresponding to the images. This paper involves in providing a comprehensive review of the technical achievements of distance learning, machine learning along with kernel learning methods for conducting visual similarity search. The methods cited have limitation in their capability of the similar measurement with complicated patterns in most practical applications. Similarity of multimodal data identified through the multiple resources²⁸, cannot be handled. Application/Improvements: Evaluation of the technique proposed for CBIR is performed on a huge amount of image data sets where motivating results indicate that OMKS performs better than the state-of the- art techniques significantly. At last, based on OMKS technology and the rise of requisitions from practical-world applications, and idealistic future research directions have been identified as suggestions²⁹.