BINK: Biological binary keypoint descriptor.

Learning robust keypoint descriptors has become an active research area in the past decade. Matching local features is not only important for computational applications, but may also play an important role in early biological vision for disparity and motion processing. Although there were already some floating-point descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compute and to match.

Proto-object categorisation and local gist vision using low-level spatial features.

Object categorisation is a research area with significant challenges, especially in conditions with bad lighting, occlusions, different poses and similar objects. This makes systems that rely on precise information unable to perform efficiently, like a robotic arm that needs to know which objects it can reach. We propose a biologically inspired object detection and categorisation framework that relies on robust low-level object shape.

Multi-scale lines and edges in V1 and beyond: brightness, object categorization and recognition, and consciousness.

In this paper we present an improved model for line and edge detection in cortical area V1. This model is based on responses of simple and complex cells, and it is multi-scale with no free parameters. We illustrate the use of the multi-scale line/edge representation in different processes: visual reconstruction or brightness perception, automatic scale selection and object segregation.

Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection.

End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-detail). The importance of the multi-scale keypoint representation is studied in this paper.

Modelling spatial vision at the threshold level.

Some available single- and multiple-channel models are reviewed. Multichannel models are generalized and tested against threshold data on various stimulus sets. Without using the explicit assumption of spatial probability summation, simple multichannel models are shown to provide good simultaneous predictions of threshold curves of sinewave gratings and other gratings.

Brightness versus apparent contrast. 3: Blurred disks and concentric cosine gratings.

Matching either the centre-brightness or the apparent contrast of incremental 1-deg disks, with varying edge-sharpness, yields quite different results. These suggest that the maximum brightness gradient at the edge determines apparent-contrast perception. However, no significant differences are found in matching the brightness maxima, the brightness minima, or the apparent contrast of concentric cosine gratings with varying spatial frequency.

Brightness versus apparent contrast. 2: Large-field asymmetry.

Experiments were performed on the quasi-static perception of brightness and of apparent contrast of a foveal 1-deg disk, presented either as a luminance increment or decrement against a 300 cd.m-2 background. Results suggest that the perceptual attributes of brightness and apparent (or subjective) contrast should be distinguished.

Abstract processes in texture discrimination.

In this study some experiments on texture segmentation are reported using the local Gabor power spectrum. The techniques applied are: (1) supervised pixel classification; (2) boundary detection by spectral dissimilarity estimation; (3) region-based segmentation based on Gaussian spectral estimation; and (4) the same as (3) but based on central moments of the local spectrum. It is shown that very-acceptable-to-excellent results can be obtained.

Brightness versus apparent contrast. 1: Incremental and decremental disks with varying diameter.

This study describes the matching of the brightness and of the apparent contrast of foveal disks, presented as an increment or decrement with varying diameter against a 300 cd.m-2 background. If the brightness in the centre of the disks is matched with a constant reference brightness, the well-known spatial Broca-Sulzer phenomenon is obtained.

Detection symmetry and asymmetry.

Experiments were performed on the detection symmetry and asymmetry of incremental and decremental disks, as a function of both disk diameter and duration. It was found that, for a background luminance of 300 cd.m-2, thresholds of dynamic (briefly presented) foveal disks are symmetrical for all diameters, and that thresholds of quasi-statically presented disks are symmetrical for large diameters only.