No abstract

No abstract

We present an improved, biologically inspired and multiscale keypoint operator. Models of single-and double-stopped hypercomplex cells in area V1 of the mammalian visual cortex are used to detect stable points of high complexity at multiple scales. Keypoints represent line and edge crossings, junctions and terminations at fine scales, and blobs at coarse scales. They are detected by applying first and second derivatives to responses of complex cells in combination with two inhibition schemes to suppress responses along lines and edges. A number of optimisations make our new algorithm much faster than previous biologically-inspired models, achieving real-time performance on modern GPUs and competitive speeds on CPUs. In this paper we show that the keypoints exhibit state-of-the-art repeatability in standardised benchmarks, often yielding best-in-class performance. This makes them interesting both in biological models and as a useful detector in practice. We also show that keypoints can be used as a data selection step, significantly reducing the complexity in state-of-the-art object categorisation.

No abstract

Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.

Abstract. Scene interpretation systems are often conceived as extensions of low-level image analysis with bottom-up processing for high-level interpretations. In this contribution we show how a generic high-level interpretation system can generate hypotheses and initiate feedback in terms of top-down controlled low-level image analysis. Experimental results are reported about the recognition of structures in building facades.

The preservation of topological properties during digitization is a hard problem in 3 and higher dimensions. Only for the very restricted class of r-regular shapes it is known that the connectivity and inclusion properties of shape components do not change.In a previous paper it was shown for the 2D case, how a much wider class of shapes, for which the morphological open-close and the close-open-operator with an r-disc lead to the same result, can be digitized correctly in this sense by using an additional repairing step. This paper extends this to the arbitrary dimensions and analyses the difficulties which occur in 3 or higher dimensional spaces.The repairing step is easy to compute, parallelizable and does not change as much hyper-voxels as a preprocessing regularization step. The results are applicable for arbitrary, even irregular, sampling grids in arbitrary dimensions.

Appearance-based classification is a difficult task in many domains due to ambiguous evidence. Knowledge about the relationships between objects in the scene can help resolve this problem. In this paper, we present a new probabilistic classification framework based on the cooperation of decision trees and Bayesian Compositional Hierarchies, and show that introducing contextual knowledge in the form of dynamic priors significantly improves classification performance in the façade domain.