Please download to get full document.

View again

of 6
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
International Scientific and Research Group
  International Journal of Computer science engineering Techniques-– Volume 2 Issue 4, May - June 20! ISSN: 2455-135X http://www.ijcsejournal.org  Page 6 Exploration of Ticket/Label Based Representation by Social Re-Grading E.Arulmurugan 1 , E.Dilipkumar 2   1 PG Student,  2 Associate Professor 1 ,  2 , Department of MCA, Dhanalakshmi Srinivasan College of Engineering and Technology 1. INTRODUCTION  Data Mining is the analysis step of the “Knowledge discovery in Database” (KDD). Data Mining is the extraction of hidden predictive information from large databases, is a powerful new technology with great potential to help companies focus on the most important information in their Data Warehouses. Data Mining is discovering the hidden values in your Data Warehouse. It uses the mathematical algorithms to segregate the data. Image mining is the process of searching and discovering valuable information and knowledge in large volumes of data. Some of the domains used to gather knowledge are Data Mining, Image Processing and Artificial Intelligence. In these domains Image Mining can be done in two different approaches. One is to extract from databases or collections of images and the other is to mine a combination of associated alphanumeric data and collections of images. We use pattern recognition and image processing dimensionality reduction techniques. When the input data is too large to be processed and it is suspected to be notoriously redundant, then the input data will be transformed into a reduced representation set of features. Feature extraction involves simplifying the amount of resources required to describe a large set of data accurately. Several features are used in the Image Retrieval system. The popular amongst them are Color features, Texture features and shape features. 2. LITERATURE SURVEY [1] Xiaoxiao Liu received the B.S. degree from the Xi’an University of Post and Telecomunications, Xi’an, China, in 2011, and the M.S. degree from the School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China, in 2014. [2] Dan Lu Abstract: Social media sharing websites like flickr shares images with their respective tags. According to this tag, images are retrieved and this process is called as tag-based image retrieval. However, making the tagged images as top ranked result relevant is challenging. In this paper, we propose a social re-grading system for tag-based image search with the consideration of image retrieval and diversity. Images are re-graded according to their visual information, semantic information, and social clues. The initial results include images contributed by different social users. Usually each user contributes several images by their views. First, we sort these images by inter- user re-grading and intra-user re-grading. Each user’s contributed image comes higher position and thus images are stored in social image dataset in the database to sort images and it is also re-graded by tag-based image search. Experimental results on a flickr dataset show that our social re-grading method is effective and efficient.  Keywords —Image search, re-ranking, social clues, social media, tag-based image retrieval.   RESEARCH ARTICLE OPEN ACCESS  International Journal of Computer science engineering Techniques-– Volume 2 Issue 4, May - June 20! ISSN: 2455-135X http://www.ijcsejournal.org  Page 7 received the B.S. degree from Chang’an University, Xi’an, China, in 2013, and is currently working toward the M.S. degree at the School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an, China. She is now a Post-Graduate at the SMILES Laboratory, Xi’an Jiaotong Univeristy. Her current research interests include tag-based image retrieval [3] X. Qian, H. Feng, G. Zhao, and T. Mei, “Personalized recommendation combining user interest and social circle,”  IEEE Trans. Knowl.  Data Eng. ,[4] X. Qian, X. Tan, Y. Zhang, R. Hong, and M. Wang, “Enhancing sketchbased image retrieval by re-ranking and relevance feedback,”  IEEE Trans.  Image Process. , In the existing system, it shows all the images which are specified in the tag based on attribute image search and it occupies high Memory space and also has Image duplication. Tag-based ranking algorithm, which can automatically rank tags according to their relevance with the image content. A modified probabilistic relevance estimation method is proposed by taking the size factor of objects into account and random walk based refinement is utilized. Tag fusion method for tag relevance estimation to solve the limitations of a single measurement on tag relevance. Besides, early and late fusion schemes for a neighbor voting based tag relevance estimator are conducted. Tag clarity score measurement approach to evaluate the correctness of a tag in describing the visual content of its annotated images. Disadvantages Of Existing System   ã   Tag mismatch.   ã   Query ambiguity.   ã   High time consumption.   ã   Hard to maintain the database. ã   Complication in searching due to similar tag naming.  3. PROPOSED SYSTEM In this paper, we propose Attribute-based image search for higher re-graded images so that, the image duplication is avoided and satisfactory level is high when considering to user query. It occupies low memory space with deliverance of image is faster to avoid image complication. We propose the inter-user re-ranking method and intra-user re-ranking method to achieve a good trade-off between the diversity and relevance performance. These methods not only reserve the relevant images, but also effectively eliminate the similar images from the same user in the ranked results. In the intra-user re-ranking process, we fuse the visual, semantic and views information into a regularization framework to learn the relevance score of every image in each user’s image set. To speed up the learning speed, we use the co-occurrence word set of the given query to estimate the semantic relevance matrix. This system is more considerate when compared to existing systems. Advantages Of Proposed System  The main objective of this paper is to provide the Attribute-based image search for image search. ã   Makes the user comfortable for searching. ã   Low time consumption for searching images.  International Journal of Computer science engineering Techniques-– Volume 2 Issue 4, May - June 20! ISSN: 2455-135X http://www.ijcsejournal.org  Page 8 ã   Extremely flexible and easy for the user. ã   User can get higher re-graded images. ã   Can view the high ranked trending tags in the page. 4. SYSTEM ARCHITECTURE MODULE 1:Upload images   ã   User enters their details in the registration form. ã   After completion of registration, user login into the website. ã   Many user can upload their desired images from their account. ã   Thus the uploaded images can be viewed and it is stored into the database MODULE 2: Surfing exact images using attribute key   ã   User can surf the desired images based on key and tag. ã   According to the surfing details multiple images can be viewed. ã   ABIR algorithm is used for surfing the exact images. MODULE 3: Re-grading images based on viewer’s contribution   ã   Depends on viewer’s contribution the images are re-graded. ã   Viewer’s contribution is nothing but users like . MODULE 4: Retrieval of an images   ã   According to the user preference images are retrieved effectively. ã   It displays exact images based on attribute key. ã   After the retrieval of an exact image, user can logout from their account. LOGIN PAGE -   International Journal of Computer science engineering Techniques-– Volume 2 Issue 4, May - June 20! ISSN: 2455-135X http://www.ijcsejournal.org  Page 9 UPLOAD IMAGE SEARCH RANDOM SEARCH RANK BASED SEARCH
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks