Recently, the optimal distance measure for a given object discrimination task under the nearest neighbor framework was derived [1]. For ease of implementation and efficiency consi...
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically...
Choosing appropriate values for kernel parameters is one of the key problems in many kernel-based methods because the values of these parameters have significant impact on the per...
In this paper, we present a new approach for hand-written character and digit recognitions based on shape descriptor and the Hausdorff Context. We start at finding the correspondi...
Psychophysical studies have shown that humans actively exploit temporal information such as contiguity of images in object recognition. We have recently developed a recognition sy...
Arnulf B. A. Graf, Christian Wallraven, Heinrich H...