International Journal of Life science and Pharma Reviews (IJLPR)  
International Journal of Life science and Pharma Research (IJLPR)
Life Science
Volume 11 Issue 2, March 2021    Pages:38-44
An Efficient Image Search for Content Based Image Retrieval using Semantic-Assisted Visual Hashing  

Ms. N.Valarmathi and Ms.S.Annapoorani
[View PDF]
The CBIR system can be used to recover medical images associated with different diseases. The purpose of medicine information system is about providing the right information, at the right time, in the right place, to the right person. This improves the quality and efficiency of the patient care process. In clinical decision manufacturing process, it is important to find other images for a given query. . This is done using the content-based image recovery technique. Data mining is the technique of sorting through massive figured devices in get awareness about the human habits and place up human relationships to resolve problems via figure evaluation. Data gold mining apparatus gives business to anticipate the future qualities. Quality content material-based search offers a large volume of picture selections totally, while both effectiveness and performance are essential problems. An advanced indexing form is essential to scale the large statistics, facilitate the correct assessment.. This is a new technology that supports scalable content-based image retrieval (CBIR) hashing. Recently, CBIR has been focused with the future directions in the field of research. The Unsupervised visual hashing approach called semantic assisted visual hashing (SAVH) has a semi-supervised and supervised visual blending process. This approach is based on a strictly hidden rich semantics integrated into auxiliary image texts to increase the efficiency of visual clutter without any semantic labels. The most native technique for CBIR is to examine query photographs with each sample saved in the database sequentially. Its linear intricacy results in the poor expressions and performance scalability in the actual environment. Also, visual features normally have high dimensions. Picture access is normally transported out while using the complementing features of any predicament picture with the types within the photo data source. It may end up being categorized as textual content, which is primarily contentbased. To extend the scope, an unsupervised framework is deviced to learn hash codes simultaneously preserving the visual similarities of the images, integrating the semantic assistance of the texts on modeling high inter-image relationships, and defining correlations between images and shared content. The present study recommends a book unsupervised visible hashing system, termed as SAVH, to perform visual hashing learning effectively.
Keywords: Feature extraction, image processing, content-based image retrieval system, Unsupervised Learning
© 2010-2015 IJLPR. All rights reserved. Specialized online journals by ubijournal. Website by Ubitech Solutions