Abstract

Content-Based Image Retrieval (CBIR) allows to automatically extracting target images according to objective visual contents of the image itself. Although classical wavelet transform is effective in representing image feature and is suitable in CBIR, it still encounters problems especially in implementation; e.g. floatingpoint operation and decomposition speed. We use the advantages of lifting scheme, a novel spatial approach for constructing biorthogonal wavelet filters, which provides feasible alternative for problems facing its classical counterpart. Lifting scheme has such intriguing properties as convenient construction, simple structure, integer-to-integer transform, low computational complexity as well as flexible adaptivity, revealing its potentials in CBIR. In this paper, we use Haar and Daubechies (D4) lifting schemes to decompose color images into multilevel scale and wavelet coefficients, with which we perform image feature extraction and similarity match by means of F-norm theory. Furthermore, we also provide a progressive image retrieval strategy to achieve flexible CBIR. The retrieval performances are compared with those of its classical counterpart in terms of retrieval accuracy and speed, the results outperforms its classical counterpart. We also compared our algorithm with existing Wavelet histogram technique.

Keywords: Content-Based Image Retrieval, lifting scheme, wavelet coefficients.
(P1150733003, 1.11 MB)

	Y.Madhaveelatha, born on January, 1972, completed her graduation and post graduation from JNT University, Hyderabad. She has been working at G.Narayanamma Institute of Science and Technology, JNT University, Hyderabad since 8 years as a Associate Professor in the Department of Electronics and Communication Engineering. Currently she pursuing Ph.D at JNT University under guidance of Dr.B.C.Jinaga . Her research interest includes Image and Video processing, Multimedia Systems Design.
	Dr.B.C. Jinaga, born on June, 1950, graduation from Karnataka University, Dharwad, Post Graduation from Regional Engineering, Warangal and Ph.D. from Indian Institute of Technology, Delhi. He has been with JNT University since 21 years. Prof.B.C. Jinaga was occupied various key positions at JNT University and presently Rector at JNT University. He guided several students for Ph.D. He has published quit number of papers in reputed international and National journals. His research interest includes signal Processing and Coding Techniques. He received Best Teacher Award for the year 2002 - Awarded by Government of Andhra Pradesh.
	V.S.K.Reddy, born on June 1967, graduated from S.V. University, Tirupati, India, and Post Graduation from JNT University, Hyderabad. His Doctoral Research from IIT Kharagpur in the area of VLSI Signal Processing. He has been working at Sreenidhi Institute of Science and Technology since 1998 at various key positions. Currently he is the Director of Sreenidhi-Vaughn college of Aeronautics and Technology [USA collaboration]. He has published quit number of papers in reputed international and National journals .His specialized fields are Image and Video Processing, TCP/IP Networks and Protocols, VLSI Architectures Signal Processing and DSP Processors.

@ARTICLE{P1150733003,

AUTHOR = {Y. M. Latha and B.C. Jinaga and V.S.K. Reddy},

TITLE = {A Precise Content-based Color Image Retrieval: Lifting Scheme},

JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing, GVIP},

YEAR = {2008},

VOLUME = {08},

ISSUE ={1},

PAGES={25--32}

}

(P1150733003, 1.11 MB)