Multi-layer multi-level color distribution – User feedback model with wavelet analysis for color image retrieval. (April 2018)

• Record Type: Journal Article
• Authors: Kandasamy, A; Sundaram, Dr. M
• Is Part Of: Computers & electrical engineering. Volume 67(2018)
• Page Start: 825
• Page End: 835
• Publication Date: 2018-04
• Subjects: Image retrieval -- Large database -- Color histogram -- Color distribution -- Wavelet analysis -- MLMLCD; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.06.026
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: To avoid misclassification during retrieval, this paper proposes an efficient multi-layer multi-level color distribution (MLMLCD) approach to improve the image retrieval quality. Here, the MLMLCD Vector Generation stage applies the wavelet transform over the image layers and hence color distribution vectors are generated. In MLMLCD Image Retrieval stage, the similarity measurement of MLMLCD color distribution vector value is made between the proposed technique and the values from larger databases. Finally, the precise retrieval result is produced with user feedback and query model, which is iterated over several runs. The performance of the proposed technique is tested between two datasets namely: McGill and CalTech database. Here, the performance is tested in terms of retrieval efficiency, classification rate and time complexity. A higher retrieval efficiency (98.5%)with less false classification rate(3.4%) is achieved, when compared with conventional techniques and a significance improvement is noted.