We propose a biologically motivated computational step, called non-classical receptive field (non-CRF) inhibition, to improve contour detection in images of natural scenes. We aug...
Cosmin Grigorescu, Nicolai Petkov, Michel A. Weste...
Visual attention is obtained through determination of contrasts of low level features or attention cues like intensity, color etc. We propose a new texture attention cue that is s...
We investigate the problem of pedestrian detection in
still images. Sliding window classifiers, notably using the
Histogram-of-Gradient (HOG) features proposed by Dalal
and Trig...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
We propose a novel solution to object detection, localization and pose estimation with applications in robot vision. The proposed method is especially applicable when the objects ...