S. A. Gladilin, A. A. Kotov, D. P. Nikolaev, S. A. Usilin, “Construction of robust features for detection and classification of objects without characteristic brightness contrasts”, Informatsionnye Tekhnologii i Vychslitel'nye Sistemy, 2014, Issue 1,Pages <nobr>53

IMAGE PROCESSING TECHNIQUES

Construction of robust features for detection and classification of objects without characteristic brightness contrasts

S. A. Gladilin^a, A. A. Kotov^a, D. P. Nikolaev^a, S. A. Usilin^b

^a Institute for Information Transmission Problems of the Russian Academy of Sciences (Kharkevich Institute), Moscow
^b Institute for Systems Analysis of Russian Academy of Sciences

Abstract: The paper describes a new class of feature for object detection and classification in images. These features are shown to be robust to significant illumination changes. The performance of the proposed method is studied on the modified Viola-Jones algorithm as applied to vehicle axle detection and embossed number recognition tasks.

Keywords: computer vision, object detection, robust features, Viola-Jones algorithm.