Web-page Recommendation source Code Download

Project Discription

INTRODUCTION

Traditional approach is used for searching the information over the internet, i.e., searching the information on the basis of textual data. But compared to text, visual content is easy to identify. As the technology grows rapidly, huge amount of image database, audio and video database has been stored over the internet and is continuously managed by w3c. Now, one can also search the information that he / she desires not only on the basis of keywords, but also through images or audio / video files. A number of search engines are configured in such a way that they can easily search the information on the basis of the image provided.

Proposed Work

Whole Whole work is divide into different modules base on the steps of calculation from the user query to final output on the screen. In fig. it is seen that there are three different modules. First phase utilizing the features of the image retrieve images, after this find distance from one image feature to other base on the different values of the feature and final rank of those feature combination is prepared.

Conclusion

World Wide Web has necessitated the users to make use of automated tools to locate desired information resources and to follow. Web image re-ranking has been widely used to reduce the user searching time on the internet; its success mainly depend on the accuracy of image features similarities. The integration of image-based features has recently attracted a lot of attention. In this thesis, we have given an overview of recent works in this field, then compared them and discussed some of their limitations. The main objective of this study is to tackle this problem in an adaptable and effective way. This work present utilizing of the  visual features for ranking the image as both make the re-ranking process more powerful, which is shown in results.

Swcond include query pre-processing then fetch  annotated images from the database and make initial rank of the images base on the most similar feature value with query.

Project Sample Image