AN EFFICIENT APPROACH FOR CONTENT BASED IMAGE RETRIEVAL USING HIERARCHICAL PART-TEMPLATE AND TREE MODELING
| Autor: | B. Eswara Reddy, Pushpalatha S Nikkam |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Scheme (programming language)
Matching (graph theory) Computer science 02 engineering and technology lcsh:Computer applications to medicine. Medical informatics Content-based image retrieval lcsh:Telecommunication 030218 nuclear medicine & medical imaging Image (mathematics) Part-Template 03 medical and health sciences Svm classifier 0302 clinical medicine HOG lcsh:TK5101-6720 0202 electrical engineering electronic engineering information engineering Tree-Formation computer.programming_language business.industry Shape Pattern recognition SVM Classifier Tree (data structure) Template Content (measure theory) lcsh:R858-859.7 Hierarchical Template Tree 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Zdroj: | ICTACT Journal on Image and Video Processing, Vol 8, Iss 2, Pp 1607-1613 (2017) |
| ISSN: | 0976-9102 0976-9099 |
| DOI: | 10.21917/ijivp.2017.0226 |
| Popis: | Image based content recognition and retrieval is critical in many applications. Existing mechanisms for content based image retrieval lack in terms of performance. In this paper a hierarchical template tree based CBIR system is described. Content in image is represented using a combination of shape features and low level features. Comprehensive feature set definitions proposed enables in achieving better performance. Shape and low level features are considered as templates. Templates of similar categories are further decomposed to form a hierarchical template tree. Query image is converted into a query template and is decomposed. A part template based matching scheme and SVM classifier is used to retrieve visually similar images. Results presented in the paper prove superior performance of proposed technique when compared to recent existing mechanisms in place. An improvement of 10.45% and 9.69% in mean average precision and mean retrieval accuracy is reported using proposed approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|