Systemy rozpoznawania twarzy dla obrazów widzialnych i podczerwieni z wykorzystaniem CCA

• Autorzy: Szaber M. , Kamenskaya E.
• Języki publikacji: PL

Abstrakty

EN

Face recognition systems based on visual images have reached a significant level of maturity with some practical success. However, the performance of visual face recognition may degrade under poor illumination conditions and in completely darkness. Infrared images represent a viable alternative to visible images in the search for practical face recognition. In the article, we investigate the face recognition scheme where category of identified face images differs from that stored in face database. CCA (Canonical Correlation Analysis) method is used to build face recognition system with using visual and infrared images. Next, we considered three scenarios for this kind of system: during a day, at night and at dusk. We presented CCA method for this system that is proper for this tasks the schemes of scenario and examples of their working.

Słowa kluczowe

EN

CCA; recognition system; visible; infrared and thermal images

• Wydawca: Komisja Informatyki Polskiej Akademii Nauk, Oddział w Gdańsku
• Czasopismo: Metody Informatyki Stosowanej
• Rocznik: 2008
• Tom: nr 3 (Tom 16)
• Strony: 223--236
• Opis fizyczny: Bibliogr. 10 poz., rys.

Twórcy

autor

Szaber M.

• Politechnika Szczecińska, Wydział Informatyki

autor

Kamenskaya E.

• St.-Petersburg Electrotechnical University

Bibliografia

• [1] Heo J., Kong S., Abidi B., Abidi M., Fusion of Visual and Thermal Signatures with Eyeglass Removal for Robust Face Recognition, IEEE Workshop on Object Tracking and Classification Beyond the Visble Spectrum in conjunction with CVPR, s.94–99, 2004
• [2] Singh S., Gyaourova A., Bebis G. and Pavlidis I., Infrared and visible image fusion for face recognition. In Proc. SPIE Defense and Security Symposium (Biometric Technology for Human Identification), pp. 585–596, 2004
• [3] Kong S. G., Heo J., Boughorbel F., Zheng Y., Abidi B. R., Koschan A., Yi M., and Abidi M. A., Multiscale Fusion of Visible and Thermal IR images for illumination invariant Face Recognition, International Journal of Computer Vision 71(2), 215–233, 2007
• [4] Stan Z. Li, RuFeng Chu, ShengCai Liao, Lung Zang, Illumination Invariant Face Recognition Using Near-Infrared Images, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 29, No.4, s. 627–639, April 2007
• [5] Kukharev G., Szaber M., Nowosielski A., Transform Function for Visual and Infrared Images for the Face Recognition System, Polish Journal of Environmental Studies Vol. 16, No 3C, 293–296, 2007
• [6] Szaber M., Rozpoznawanie twarzy dla obrazów widzialnych i podczerwieni z zastosowaniem funkcji w przestrzeni cech, Metody Informatyki Stosowanej nr 2, 2008
• [7] Hotelling H., Relations between two sets of variates, Biometrika, Vol. 28, No. 3-4, 321–377, 1936
• [8] Forczmański P., Kukharev G., Comparative analysis of simple facial features extractors. Journal of Real-Time Image Proc, 239–255, 2007
• [9] Kukharev G., Mikłasz M., Nguyen The Binh, Strategia budowy systemów klasy „Face Retrieval”. Metody Informatyki Stosowanej nr 2, 61 – 72, 2007
• [10] http://www.equinoxsensors.com/products/HID.html