| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 407448 | Neurocomputing | 2016 | 17 Pages |
The object present in an image is an important content and can be used in CBIR applications. Identifying and representing the shape of the object is indeed complex due to the uncertainties in the boundary of the object of interest. In this paper, we have proposed Fuzzy-Object-Shape to capture the shape of the object of interest along with the degree of impreciseness in the boundary information. The Fuzzy-Object-Shape information is extracted from each object in an image. This information provides a measure of closeness of the object of interest with well-known shapes. For each object, the fuzzy membership values are calculated and considered as feature vector. A similarity measure is proposed for measuring the degree of closeness of objects present in both query and database images. The performance of the proposed approach is compared with some of the recently proposed similar approaches. Benchmark dataset and uncontrolled dataset are used for the experiments and the performance of the proposed approach is encouraging.
