DocumentCode :
2939066
Title :
Optimizing JPEG quantization table for low bit rate mobile visual search
Author :
Ling-Yu Duan ; Xiangkai Liu ; Jie Chen ; Tiejun Huang ; Wen Gao
Author_Institution :
Inst. of Digital Media, Peking Univ., Beijing, China
fYear :
2012
fDate :
27-30 Nov. 2012
Firstpage :
1
Lastpage :
6
Abstract :
Smart phones is bringing about emerging potentials in mobile visual search. Extensive research efforts have been made in compact visual descriptors. However, directly extracting visual descriptors on a mobile device is computationally intensive and time consuming. Towards low bit rate visual search, we propose to deeply compress query images by learning a customized JPEG quantization table in the context of visual search. Distinct from traditional image compression, by incorporating pair-wise image matching precision into distortion measure, we optimize quantization table to seek a better trade-off between image compression rate and visual search performance. An evolutionary algorithm is employed to learn an optimal quantization table. Under MPEG CDVS evaluation framework, extensive evaluation has been done including image retrieval and pair-wise matching over 1 million database images. Experimental results have demonstrated that our optimized quantization table works much better than JPEG default one in terms of retrieval/matching performance vs. a set of different operating points. The proposed low bit rate solution may be easily deployed to smart phones without hardware support, as a useful complement to the ongoing MPEG CDVS standardization efforts.
Keywords :
data compression; evolutionary computation; feature extraction; image coding; image matching; image retrieval; learning (artificial intelligence); quantisation (signal); smart phones; JPEG quantization table optimization; MPEG CDVS evaluation framework; compact visual descriptor extraction; distortion measure; evolutionary algorithm; image database; image retrieval; low bit rate mobile visual search performance; pairwise image matching precision; query image compression rate; smart phones; Bit rate; Feature extraction; Image coding; Mobile communication; Quantization; Transform coding; Visualization; Image compression; Image matching; Image retrieval; Mobile visual search; Quantization table;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Visual Communications and Image Processing (VCIP), 2012 IEEE
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4673-4405-0
Electronic_ISBN :
978-1-4673-4406-7
Type :
conf
DOI :
10.1109/VCIP.2012.6410738
Filename :
6410738
Link To Document :
بازگشت