Abstract
Evolution of ubiquitous computing in the areas of personal computing technology has produced staggeringly large data It is difficult to search mainly the image data by understanding users objective only by keywords and phrases and this leads to uncertain outcomes. For producing these outcomes effectively, this paper introduces a new approach to the problem of image learning to enable search engines to learn about visual content over time based on user feedback through one click activity and images from a pool recovered by text based query are re-ranked depending on both visual and text based query. Content Based Image Retrieval (CBIR) techniques are used for accessing semantically-relevant images from an image data source depending on automatically-derived image functions for features like Geometric moments, Global histogram, Color Moments, Local histogram. Documents can also be retrieved using the text based query by the user.
Highlights
One of the main problems highlighted was difficulty in locating a desired image in a large and varied collection while it is feasible to identify a desired image from a small collection by browsing
The search engine retrieves thousands of images ranked by the keywords extracted from the surrounding text
It is known that text-based image search sometimes results in ambiguity of query keywords
Summary
One of the main problems highlighted was difficulty in locating a desired image in a large and varied collection while it is feasible to identify a desired image from a small collection by browsing. More effective techniques are needed with database containing thousands of items. Journalists collecting photographs of a particular type of event, designers searching for materials with a particular color or texture need some access by image content. Users type query keywords to find a certain type of images. The search engine retrieves thousands of images ranked by the keywords extracted from the surrounding text. It is known that text-based image search sometimes results in ambiguity of query keywords. The keywords provided by users tend to be short
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
