Robust Face Recognition in Low Resolution and Blurred Image Using Joint Information in Space and Frequency

Abstract : Recognizing faces in low resolution and blurred images is common yet challenging task. Local Frequency Descriptor (LFD) has been proved to be effective for this problem and is extracted from a spatial neighborhood of each pixel of a frequency plane regardless of correlations between frequencies. To explore the frequency correlations and preserve low resolution and blur insensitive simultaneously, we propose Enhanced LFD (ELFD) in which information in space and frequency is jointly utilized so as to be more descriptive and discriminative than LFD. The selection of window size of short-term of Fourier transform adaptive to the testing image is also analyzed. In addition, linear weighting fusion of recognition results given by magnitude and phase is proposed. The experiments conducted on Yale and FERET databases demonstrate that promising results have been achieved by the proposed ELFD, adaptive window size selection and fusion scheme.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-01551341
Contributor : Hal Ifip <>
Submitted on : Friday, June 30, 2017 - 10:35:53 AM
Last modification on : Friday, December 1, 2017 - 1:09:59 AM
Long-term archiving on : Monday, January 22, 2018 - 8:48:08 PM

File

978-3-642-35606-3_73_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Guoqing Li, Guangling Sun, Xinpeng Zhang. Robust Face Recognition in Low Resolution and Blurred Image Using Joint Information in Space and Frequency. 9th International Conference on Network and Parallel Computing (NPC), Sep 2012, Gwangju, South Korea. pp.616-624, ⟨10.1007/978-3-642-35606-3_73⟩. ⟨hal-01551341⟩

Share

Metrics

Record views

68

Files downloads

123