International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 120 - Number 24 |
Year of Publication: 2015 |
Authors: Yogita D. Shinde, Sudeep D. Thepade |
10.5120/21408-4419 |
Yogita D. Shinde, Sudeep D. Thepade . Content based Image Retrieval using Sectorisation of Self Mutated Hybrid Wavelet Transforms. International Journal of Computer Applications. 120, 24 ( June 2015), 16-19. DOI=10.5120/21408-4419
Content based image retrieval (CBIR) is an image retrieval process which involves mainly extraction of features based on contents of an image which uniquely identifies an image from other images in the database. Hybrid Wavelet Transform is formed using two orthogonal transforms. In this paper, Self Mutated Hybrid Wavelet transform (SMHWT) is used which is formed by using same component transform. In Proposed algorithm, feature extraction is done by applying sectorisation on Self Mutated Hybrid Wavelet transformed images. To test the performance of the proposed method, total 1000 queries were fired on the image database containing 1000 images of 10 categories. Manhattan Distance is used for similarity measurement. Performances proposed algorithm is evaluated using average precision. Results show that the proposed Self Mutated Hybrid Wavelet Transform containing Sine transform as a component gives better performance improvement across all tried variations of SMHWTs.