Classifying materials from their appearance is challenging. Impressive results have been obtained under varying illumination and pose conditions. Still, the effect of scale variations and the possibility to generalise across different material samples are still largely unexplored. This paper (A preliminary version of this work was presented in Hayman et al. [E. Hayman, B. Caputo, M.J. Fritz, J.-O. Eklundh, On the significance of real world conditions for material classification, in: Proceedings of the ECCV, Lecture Notes in Computer Science, vol. 4, Springer, Prague, 2004, pp. 253-266].) addresses these issues, proposing a pure learning approach based on support vector machines. We study the effect of scale variations first on the artificially scaled CUReT database, showing how performance depends on the amount of scale information available during training. Since the CUReT database contains little scale variation and only one sample per material, we introduce a new database containing 10 CUReT materials at different distances, pose and illumination. This database provides scale variations, while allowing to evaluate generalisation capabilities: does training on the CUReT database enable recognition of another piece of sandpaper? Our results demonstrate that this is not yet possible, and that material classification is far from being solved in scenarios of practical interest.

This payer concerns acquisition of dense depth maps tn the. context of image segmentation. which is fundamental m various vision applications. Focusing on stereoscopic vision as the methodology, our goal here is to develop a scheme which is computationally simple but still allows a dense disparity map. For the estima-tion of stereo disparity, for thus reason, we employ an approach based on local Fourier phase obtained by com-plex bandpass filters. We consider the characteristics of this search-free and thus fast approach as suitable to compute stereo disparity as a basic cue for image seg-mentation. Within the framework of the phase-based al-gorithm. in this paper, two tssues are discussed. One is the use of the derivative-based filters, and the other is the certainty-weighted disparity propagation.

This paper presents a technique for disparity selection in the context of camera vergence in binocular pursuit. For vergence control in binocular pursuit, it is a crucial problem to find a disparity which is corresponding to the target among multiple disparities generally observed in a scene. To solve the problem of the selection, we propose an approach based on histogramming the disparities obtained from a phase-based disparity estimation algorithm. The idea is to slice the scene using the disparity histogram so that only the target remains. The slice is chosen around a peak in the histogram, a peak which is found by keeping track of the peak as it moves in time, using prediction of the targets disparity and location in the image. The tracking of the peak enables robustness against any dominant objects in the scene. The approach is investigated through experiments and shown to work appropriately.

We will discuss how hypotheses of geomemc structure can be generated in an active computer vision system. These hypotheses are built on sparse but reliable observations and can communicate with higher level hypotheses as well as the basic classified data hypotheses. We present experiments with such hypotheses, where we have chosen to form hypotheses about the existence of planar surfaces in a scene, given classified edges and junctions. The results of the experiments illustrate clearly the benefit of the approach. A goal directed active vision system could easily use this idea to make both powerful verifications of generated predictions as well as hew hypotheses and predictions at different level of abstraction.