Loading...
120 results
Search Results
Now showing 1 - 10 of 120
- Multi-scale lines and edges in V1 and beyond: brightness, object categorization and recognition, and consciousnessPublication . Rodrigues, J. M. F.; du Buf, J. M. H.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. A two-level object categorization scenario is tested in which pre-categorization is based on coarse scales only and final categorization on coarse plus fine scales. We also present a multi-scale object and face recognition model. Processing schemes are discussed in the framework of a complete cortical architecture. The fact that brightness perception and object recognition may be based on the same symbolic image representation is an indication that the entire (visual) cortex is involved in consciousness.
- Segmentação de imagem em três dimensõesPublication . Rodrigues, J. M. F.; du Buf, J. M. H.
- Modelfest and contrast-interrelation-function data predicted by a retinal modelPublication . du Buf, J. M. H.The automatic implementation of decoders for a visual perception is achieved as follows. The action described by a production rule is realized by means of the decoder in which a pattern of connections coreesponds to that of stimuli. According to "S.Karasawa,(Proc. of CCCT, Vol.5, pp.194-1999, Austin, Texas, August, 2004)", each program mable controllable connection among inputs is realized by a floating gate avalanche injection MOS FET, where inverted signals are used at writing, and the detection of matching between inputs and connections is carried out by using the signal source in which low level signal is provided via comparatively smaller resistance than high level.
- BINK: Biological binary keypoint descriptorPublication . Saleiro Filho, Mario; Terzic, Kasim; Rodrigues, João; du Buf, J. M. H.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 floatingpoint 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. Most of these descriptors are based on purely computational methods. The few descriptors that take some inspiration from biological systems are still lagging behind in terms of performance. In this paper, we propose a new biologically inspired binary keypoint descriptor: SINK. Built on responses of cortical V1 cells, it significantly outperforms the other biologically inspired descriptors. The new descriptor can be easily integrated with a V1-based keypoint detector that we previously developed for real-time applications. (C) 2017 Elsevier B.V. All rights reserved.
- Improved line/edge detection and visual reconstructionPublication . Rodrigues, J. M. F.; du Buf, J. M. H.Lines and edges provide important information for object categorization and recognition. In addition, one brightness model is based on a symbolic interpretation of the cortical multi-scale line/edge representation. In this paper we present an improved scheme for line/edge extraction from simple and complex cells and we illustrate the multi-scale representation. This representation can be used for visual reconstruction, but also for nonphotorealistic rendering. Together with keypoints and a new model of disparity estimation, a 3D wireframe representation of e.g. faces can be obtained in the future.
- Abstract processes in texture discriminationPublication . du Buf, J. M. H.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. It is argued, however, that the shortcomings of region-based and boundary-based approaches require that both processes should act in parallel, not only in digital image processing but also in the modelling of visual perception.
- Luminance, colour, viewpoint and border enhanced disparity energy modelPublication . Martins, Jaime; Rodrigues, Joao; du Buf, J. M. H.The visual cortex is able to extract disparity information through the use of binocular cells. This process is reflected by the Disparity Energy Model, which describes the role and functioning of simple and complex binocular neuron populations, and how they are able to extract disparity. This model uses explicit cell parameters to mathematically determine preferred cell disparities, like spatial frequencies, orientations, binocular phases and receptive field positions. However, the brain cannot access such explicit cell parameters; it must rely on cell responses. In this article, we implemented a trained binocular neuronal population, which encodes disparity information implicitly. This allows the population to learn how to decode disparities, in a similar way to how our visual system could have developed this ability during evolution. At the same time, responses of monocular simple and complex cells can also encode line and edge information, which is useful for refining disparities at object borders. The brain should then be able, starting from a low-level disparity draft, to integrate all information, including colour and viewpoint perspective, in order to propagate better estimates to higher cortical areas.
- The detection of thin structures in imagesPublication . Spann, M.; Horne, C.; du Buf, J. M. H.An algorithm is presented which extracts thin regions from images. The algorithm requires no a priori knowledge about the region direction, exact width, phase etc. Results on a range of natural imagery are presented. © 1989.
- Modelling spatial vision at the threshold level.Publication . du Buf, J. M. H.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. They fail in predicting threshold curves of disk-shaped stimuli. If global or local spatial probability summation within channels is incorporated into the models, correctly shaped threshold curves of disks can be predicted. However, the predicted curves appear still too low if compared to measured curves. The same holds for noise gratings. Possible extensions of the models, based on local summation between channel responses and/or models consisting of initial isotropic channels (retina) followed by anisotropic channels (cortex), are discussed.
- Detection symmetry and asymmetry.Publication . du Buf, J. M. H.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. Threshold curves of quasi-static incremental and decremental disks are mutually shifted along the log area axis. In order to obtain a better insight into the underlying detection mechanism, additional experiments were performed with halfwave-rectified concentric cosine gratings, i.e. with either incremental or decremental phases. Threshold curves of these gratings proved to be identical, that is independent of polarity, and of the same shape as those obtained with fullwave cosine gratings, though 0.3 log unit shifted in amplitude. The discrepancy between threshold curves of quasi-static disks (asymmetry) and halfwave-rectified gratings (symmetry) is discussed in terms of a multiple-channel theory.