LightBlog
Contact at mumbai.academics@gmail.com or 8097636691/9323040215
Responsive Ads Here

Thursday, 14 June 2018

SURVEY PAPER ON CONTENT BASED IMAGE RETRIEVAL USING AUGMENTED K-MEANS CLUSTERING ALGORITHM

ABSTRACT:-

 In this paper, we are surveying the different ways through which we can access the content of any image. As processors become increasingly powerful, and memories become increasingly cheaper, the deployment of large image databases for a variety of applications have now become realizable. Databases of art works, satellite and medical imagery have been attracting more and more users in various professional fields for example, geography, medicine, architecture, advertising, design, fashion, and publishing. "Content-based" means that the search will analyze the actual contents of the image rather than the metadata such as keywords, tags, or descriptions associated with the image .

INTRODUCTION:-

 Image retrieval is the processing of searching and retrieving images from a huge dataset. As the images grow complex and diverse, retrieval the right images becomes a difficult challenge. For centuries, most of the images retrieval is text-based which means searching is based on those keyword and text generated by human’s creation.[1] The text-based image retrieval systems only concern about the text described by humans, instead of looking into the content of images. Images become a mere replica of what human has seen since birth, and this limits the images retrieval. This may leads to many drawbacks which will be state in related works. For decades, text in a given language has been set to order, to categorize and to search from, be it manually in the ancient Bibliotheke, or automatically Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. To overcome those drawbacks of text-based image retrieval, content-based images retrieval (CBIR) was introduced [2][3]. With extracting the images features, CBIR perform well than other methods in searching, browsing and content mining etc. The need to extract useful information from the raw data becomes important and widely discussed. Furthermore, clustering technique is usually introduced into CBIR to perform well and easy retrieval. Although many research improve and discuss about those issues, still many difficulties hasn’t been solved. The rapid growing images information and complex diversity has build up the bottle neck. Interpretation of what we see is hard to characterize, and even more so to teach a machine such that any automated organization can be possible. Yet, over the past decade, ambitious attempts have been made to make machines learn to understand, index and annotate images representing a wide range of concepts, with much progress. 

No comments:

Post a Comment