A connectionist computational method for face recognition

In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods.

The pattern articulation unit of Illiac III; homogenous Boolean functions in the iterative array,

"Supported in part by Contract AT(11-1) 1018 with the U.S. Atomic Energy Commission and the Advanced Research Projects Agency."

The pattern articulation unit of ILLIAC III : implementation of the homogeneous instruction "BOOLE" /

Supported by: Contract AT (11-1)-1018 with the U.S. Atomic Energy Commission and the Advanced Research Projects Agency.

A First Order Predicate Logic Formulation of the 3D Reconstruction Problem and its Solution Space

This paper defines the 3D reconstruction problem as the process of reconstructing a 3D scene from numerous 2D visual images of that scene. It is well known that this problem is ill-posed, and numerous constraints and assumptions are used in 3D reconstruction algorithms in order to reduce the solution space. Unfortunately, most constraints only work in a certain range of situations and often constraints are built into the most fundamental methods (e.g. Area Based Matching assumes that all the pixels in the window belong to the same object). This paper presents a novel formulation of the 3D reconstruction problem, using a voxel framework and first order logic equations, which does not contain any additional constraints or assumptions. Solving this formulation for a set of input images gives all the possible solutions for that set, rather than picking a solution that is deemed most likely. Using this formulation, this paper studies the problem of uniqueness in 3D reconstruction and how the solution space changes for different configurations of input images. It is found that it is not possible to guarantee a unique solution, no matter how many images are taken of the scene, their orientation or even how much color variation is in the scene itself. Results of using the formulation to reconstruct a few small voxel spaces are also presented. They show that the number of solutions is extremely large for even very small voxel spaces (5 x 5 voxel space gives 10 to 10(7) solutions). This shows the need for constraints to reduce the solution space to a reasonable size. Finally, it is noted that because of the discrete nature of the formulation, the solution space size can be easily calculated, making the formulation a useful tool to numerically evaluate the usefulness of any constraints that are added.

Fuzzy modeling based recognition of multi-font numerals

In this paper, we present a new scheme for off-line recognition of multi-font numerals using the Takagi-Sugeno (TS) model. In this scheme, the binary image of a character is partitioned into a fixed number of sub-images called boxes. The features consist of normalized vector distances (gamma) from each box. Each feature extracted from different fonts gives rise to a fuzzy set. However, when we have a small number of fonts as in the case of multi-font numerals, the choice of a proper fuzzification function is crucial. Hence, we have devised a new fuzzification function involving parameters, which take account of the variations in the fuzzy sets. The new fuzzification function is employed in the TS model for the recognition of multi-font numerals.

Distinct contrast response functions in striate and extra-striate regions of visual cortex revealed with magnetoencephalography (MEG)

Objective: To spatially and temporally characterise the cortical contrast response function to pattern onset stimuli in humans. Methods: Magnetoencephalography (MEG) was used to investigate the human cortical contrast response function to pattern onset stimuli with high temporal and spatial resolution. A beamformer source reconstruction approach was used to spatially localise and identify the time courses of activity at various visual cortical loci. Results: Consistent with the findings of previous studies, MEG beamformer analysis revealed two simultaneous generators of the pattern onset evoked response. These generators arose from anatomically discrete locations in striate and extra-striate visual cortex. Furthermore, these loci demonstrated notably distinct contrast response functions, with striate cortex increasing approximately linearly with contrast, whilst extra-striate visual cortex followed a saturating function. Conclusions: The generators that underlie the pattern onset visual evoked response arise from two distinct regions in striate and extra-striate visual cortex. Significance: The spatially, temporally and functionally distinct mechanisms of contrast processing within the visual cortex may account for the disparate results observed across earlier studies and assist in elucidating causal mechanisms of aberrant contrast processing in neurological disorders. © 2005 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

Are poor mathematics skills associated with visual deficits in temporal processing?

Developmental learning disabilities such as dyslexia and dyscalculia have a high rate of co-occurrence in pediatric populations, suggesting that they share underlying cognitive and neurophysiological mechanisms. Dyslexia and other developmental disorders with a strong heritable component have been associated with reduced sensitivity to coherent motion stimuli, an index of visual temporal processing on a millisecond time-scale. Here we examined whether deficits in sensitivity to visual motion are evident in children who have poor mathematics skills relative to other children of the same age. We obtained psychophysical thresholds for visual coherent motion and a control task from two groups of children who differed in their performance on a test of mathematics achievement. Children with math skills in the lowest 10% in their cohort were less sensitive than age-matched controls to coherent motion, but they had statistically equivalent thresholds to controls on a coherent form control measure. Children with mathematics difficulties therefore tend to present a similar pattern of visual processing deficit to those that have been reported previously in other developmental disorders. We speculate that reduced sensitivity to temporally defined stimuli such as coherent motion represents a common processing deficit apparent across a range of commonly co-occurring developmental disorders.

The chromatic visual evoked response as an indication of visual development

In an endeavour to provide further insight into the maturation of the cortical visual system in human infants, chromatic transient pattern reversal visual evoked potentials to red/green stimuli, were studied in a group of normal full term infants between the ages of 1 and 14 weeks post term in both cross sectional and longitudinal studies. In order to produce stimuli in which luminance cues had been eliminated with an aim to eliciting a chromatic response, preliminary studies of isoluminance determination in adults and infants were undertaken using behavioural and electrophysiological techniques. The results showed close similarity between the isoluminant ratio for adults and infants and all values were close to photometric isoluminance. Pattern reversal VEPs were recorded to stimuli of a range of red/green luminance ratios and an achromatic checkerboard. No transient VEP could be elicited with an isoluminant chromatic pattern reversal stimulus from any infant less than 7 weeks post term and similarly, all infants more than 7 weeks post term showed clear chromatic VEPs. The chromatic response first appeared at that age as a major positive component (P1) of long latency. This was delayed and reduced in comparison to the achromatic response. As the infant grew older, the latency of the P1 component decreased with the appearance of N1 and N by the 10th week post term. This finding was consistent throughout all infants assessed. In a behavioural study, no infant less than 7 weeks post term demonstrated clear discrimination of the chromatic stimulus, while those infants older than 7 weeks could do so. These findings are reviewed with respect to current neural models of visual development.

The effect of stimulus location on the major components of the visual evoked response

The topographical distribution of the pattern reversal Visual Evoked Response (VER) was recorded from a localised montage of 20 electrodes over the visual cortex. The response was recorded after stimulation with a black and white checkerboard stimulus. The effect of field location on the major components was investigated in 11 subjects (age range (23-55). The major components of the half field response were; a negative around 75ms (N75) followed by a positivity around 80ms (P80), then a positivity around 100ms (P100) followed by another positivity at around 120ms (P120) and a negativity at approximately 145ms (N145). No effect of field size could be demonstrated on either the amplitude or latency of the late negativity, N145. No significant effect of field size or location was shown on the latency of the P100 response. A delay previously shown in the upper half field response was therefore not substantiated. In contrast the amplitude of the major positivity, P100 was significantly affected by the field size and location. The amplitude of both P100 and N145 were significantly reduced following upper field stimulation when compared with the lower field response. No significant amplitude difference between the upper and lower field responses was demonstrated using electroretinography, the amplitude may therefore be reduced as a result of the ventral position of the upper field representation on the visual cortex. The lateral half field VEP was compared with the distribution of the visual evoked magnetic response (VEMR). The distribution of the VEMR supported the proposal that the paradoxical lateralisation of the VEP half field response is the result of the source being directed ipsilaterally. The morphology of the VEP following octant and double octant stimulation suggests that the response is generated in the striate cortex, with a reversal in response distribution following stimulation of the upper vertical and horizontal meridia.

Investigation into visual defects attributed to Vigabatrin

Vigabatrin (VGB) is a transaminase inhibitor that elicits its anitepileptic effect by increasing GABA concentrations in the brain and retina. - Assess whether certain factors predispose patients to develop severe visual field loss. - Develop a sensitive algorithm for investigating the progression of visual field loss. - Determine the most sensitive clinical regimen for diagnosing VGB-attributed visual field loss. - Investigate whether the reports of central retinal sparing are accurate. The investigations have resulted in a number of significant findings: - The anatomical evidence in combination with the pattern of visual field loss suggests that the damage induced by VGB therapy occurs at retinal level, and is most likely a toxic effect. - The quantitative algorithm, designed within the course of this investigation, provided increased sensitivity in determining the severity of visual field loss. - Maximum VGB dose predisposes patients to develop severe visual field loss. - The SITA Standard algorithm was found to be as sensitive and significantly faster, in diagnosing visual field defects attributed to VGB, when compared to the Full Threshold algorithm. The Full Threshold was found to be the most repeatable between visits. - The normal SWAP 10-2 database provided an effective method of differentiating SWAP defects. - SWAP, FDT and the mfERG have increased sensitivity in detecting visual field loss attributed to VGB. The pattern of visual field loss from these investigations suggests that VGB produces a diffuse effect across the retina including subtle central abnormalities and more severe peripheral defects. - Abnormalities detected using the mfERG have suggested that VGB adversely affects the photoreceptors Müller, amacrine and ganglion cells in the retina. An urgent review of the manufacturers recommended maximum dose for VGB is required.

The Riesz transform and simultaneous representations of phase, energy and orientation in spatial vision

To represent the local orientation and energy of a 1-D image signal, many models of early visual processing employ bandpass quadrature filters, formed by combining the original signal with its Hilbert transform. However, representations capable of estimating an image signal's 2-D phase have been largely ignored. Here, we consider 2-D phase representations using a method based upon the Riesz transform. For spatial images there exist two Riesz transformed signals and one original signal from which orientation, phase and energy may be represented as a vector in 3-D signal space. We show that these image properties may be represented by a Singular Value Decomposition (SVD) of the higher-order derivatives of the original and the Riesz transformed signals. We further show that the expected responses of even and odd symmetric filters from the Riesz transform may be represented by a single signal autocorrelation function, which is beneficial in simplifying Bayesian computations for spatial orientation. Importantly, the Riesz transform allows one to weight linearly across orientation using both symmetric and asymmetric filters to account for some perceptual phase distortions observed in image signals - notably one's perception of edge structure within plaid patterns whose component gratings are either equal or unequal in contrast. Finally, exploiting the benefits that arise from the Riesz definition of local energy as a scalar quantity, we demonstrate the utility of Riesz signal representations in estimating the spatial orientation of second-order image signals. We conclude that the Riesz transform may be employed as a general tool for 2-D visual pattern recognition by its virtue of representing phase, orientation and energy as orthogonal signal quantities.

Abnormal visual habituation in pediatric photosensitive epilepsy

Objective - To investigate visual habituation – a measure of visual cortical excitability – in photosensitive patients in pediatric age and compare the findings with a matched sample with idiopathic generalized epilepsies without photosensitivity and with normally developing children. Methods - We presented a full-field black-and-white checkerboard pattern, at 3 reversal/s with 100% contrast binocularly for 600 consecutive trials and measured the N75–P100 and P100–N145 pattern-reversal visual evoked potential inter-peak amplitudes and N75, P100, N145 latencies for the six blocks of 100 responses. As a measure of habituation we used the slope of the linear regression line of the N75–P100 and P100–N145 peak-to-peak amplitudes. The slope of the linear regression line of the N75–P100 and P100–N145 latencies was also analyzed. Results - Statistical analysis revealed significant differences between the three groups in the slope index of N75–P100 PR-VEP amplitude, with increased or constant amplitude in the PS group compare to the IGE and ND across the six blocks. Conclusions - Our results support the notion that photosensitivity is associated with altered control of excitatory and inhibitory cortical processes. The causal relationship between habituation deficit and photo-paroxysmal response needs to be further investigated with longitudinal studies. Significance This study supports the hypothesis that suppression of PR-VEP is a sensitive intermediate phenotype, which discriminates patients with photosensitivity from those with generalized epilepsies in pediatric age.