Image retrieval using efficient feature vectors generated from compressed domain

Author

Daidi Zhong ; Defee, Irek

Author_Institution

Dept. of Inf. Technol., Tampere Univ. of Technol., Tampere, Finland

fYear

2007

fDate

3-7 Sept. 2007

Firstpage

1580

Lastpage

1584

Abstract

We consider the use of quantized block transform coefficients to the image database retrieval problem. Based on the transform coefficients feature vectors are constructed. These feature vectors are used in histograms and combination of histograms with similarity measure for database retrieval. Experiments on public face image database show good performance of the approach in comparison with other methods.

Keywords

face recognition; feature extraction; image coding; image retrieval; quantisation (signal); visual databases; compressed domain; database retrieval; feature vectors; histograms; image database retrieval problem; image retrieval; public face image database; quantized block transform coefficients; similarity measure; transform coefficient feature vectors; Face; Histograms; Image databases; Quantization (signal); Training; Transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Conference, 2007 15th European

Conference_Location

Poznan

Print_ISBN

978-839-2134-04-6

Type

conf

Filename

7099072

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=706136