The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 28-891
Full Name: Vitomir Štruc
Position: Researcher
Age: ON
Sex: Male
Address: Tržaška cesta 25, SI-1000 Ljubljana
Country: SLOVENIA
Tel: +386 1 4768 839
Tel prefix: +386
Fax: +386 1 4768 316
E-mail address: vitomir.struc@fe.uni-lj.si
Other E-mails: vitos@fe.uni-lj.si
Title of the Paper: Histogram remapping as a preprocessing step for robust face recognition
Authors as they appear in the Paper: Vitomir Štruc, Janez Žibert, Nikola Pavešiæ
Email addresses of all the authors: vitomir.struc@fe.uni-lj.si,janez.zibert@fe.uni-lj.si,nikola.pavesic@fe.uni-lj.si
Number of paper pages: 10
Abstract: Image preprocessing techniques represent an essential part of a face recognition systems, which has a great impact on the performance and robustness of the recognition procedure. Amongst the number of techniques already presented in the literature, histogram equalization has emerged as the dominant preprocessing technique and is regularly used for the task of face recognition. With the property of increasing the global contrast of the facial image while simultaneously compensating for the illumination conditions present at the image acquisition stage, it represents a useful preprocessing step, which can ensure enhanced and more robust recognition performance. Even though, more elaborate normalization techniques, such as the multiscale retinex technique, isotropic and anisotropic smoothing, have been introduced to field of face recognition, they have been found to be more of a complement than a real substitute for histogram equalization. However, by closer examining!
the characteristics of histogram equalization, one can quickly discover that it represents only a specific case of a more general concept of histogram remapping techniques (which may have similar characteristics as histogram equalization does). While histogram equalization remapps the histogram of a given facial image to a uniform distribution, the target distribution could easily be replaced with an arbitrary one. As there is no theoretical justification of why the uniform distribution should be preferred to other target distributions, the question arises: how do other (non-uniform) target distributions influence the face recognition process and are they better suited for the recognition task. To tackle this issues, we present in this paper an empirical assessment of the concept of histogram remapping with the following target distributions: the uniform, the normal, the lognormal and the exponential distribution. We perform comparative experiments on the publicly availabl!
e XM2VTS and YaleB databases and conclude that similar or even better
recognition results that those ensured by histogram equalization can be achieved when other (non-uniform) target distribution are considered for the histogram remapping. This enhanced performance, however, comes at a price, as the nonuniform distributions rely on some parameters which have to be trained or selected appropriately to achieve the optimal performance.
Keywords: Biometrics, Face recognition, Image preprocessing, Histogram equalization, Histogram remapping
EXTENSION of the file: .pdf
Special (Invited) Session: Image Normalization Techniques for Robust Face Recognition
Organizer of the Session: 609-312
How Did you learn about congress: Boštjan Vesnicer (bostjan.vesnicer@fe.uni-lj.si), Simon Dobrišek (simon.dobrisek@fe.uni-lj.si)
IP ADDRESS: 193.2.84.130
