Set Of Feature Detectors Research Articles

LOCAL FEATURE EXTRACTION IN IMAGES

The methods of the local feature point extraction are analyzed. The analysis shows that the most effective detectors are based on the brightness gradient determination. They usually use the Harris angle detector, which is complex in calcu­la­tions. The algorithm complexity minimization contradicts both the detector effective­ness and to the high dynamic range of the analyzed image. As a result, the high-speed methods could not recognize the feature points in the heavy luminance conditions. The modification of the high dynamic range (HDR) image compression algorithm based on the Retinex method is proposed. It contains an adaptive filter, which preserves the image edges. The filter is based on a set of feature detectors perfor­ming the Harris-Laplace transform which is much simpler than the Harris angle detector. A prototype of the HDR video camera is designed which provides sharp images. Its structure simplifies the design of the artificial intelligence engine, which is implemented in FPGA of medium or large size.

An iterative combination scheme for multimodal visual feature detection

We address the problem of multimodal visual feature detection where several individual heterogeneous measures (i.e., feature detectors) are merged into a single saliency value. We survey a number of techniques for the normalization and integration steps used in existing combination methods. A new approach, the iterative combination scheme, is proposed to iteratively learn a classifier that infers a non-linear model to combine different feature detectors. We evaluate and compare the combination strategies presented using an objective methodology, the repeatability criterion, and a dataset with real images of 21 cluttered scenes of 3D objects. Initially, our evaluation tested the performance of individual feature detectors. Considering the overall performance for all 7 scenes in the testing dataset, the Difference of Gaussian detector achieved the best repeatability rate, 54.41%. In our evaluation, we tested the performance of combining all possible sets of feature detectors. Among all possible sets, the triplet composed of Laplacian of Gaussian, Hessian Matrix, and Gradient Magnitude achieved the best performance of 58.93% repeatability. We used this combination of detectors to initialize the iterative combination scheme which was able to improve the performance to 66.62%.

Auditory Cortex Encodes the Perceptual Interpretation of Ambiguous Sound

The confounding of physical stimulus characteristics and perceptual interpretations of stimuli poses a problem for most neuroscientific studies of perception. In the auditory domain, this pertains to the entanglement of acoustics and percept. Traditionally, most study designs have relied on cognitive subtraction logic, which demands the use of one or more comparisons between stimulus types. This does not allow for a differentiation between effects due to acoustic differences (i.e., sensation) and those due to conscious perception. To overcome this problem, we used functional magnetic resonance imaging (fMRI) in humans and pattern-recognition analysis to identify activation patterns that encode the perceptual interpretation of physically identical, ambiguous sounds. We show that it is possible to retrieve the perceptual interpretation of ambiguous phonemes-information that is fully subjective to the listener-from fMRI measurements of brain activity in auditory areas in the superior temporal cortex, most prominently on the posterior bank of the left Heschl's gyrus and sulcus and in the adjoining left planum temporale. These findings suggest that, beyond the basic acoustic analysis of sounds, constructive perceptual processes take place in these relatively early cortical auditory networks. This disagrees with hierarchical models of auditory processing, which generally conceive of these areas as sets of feature detectors, whose task is restricted to the analysis of physical characteristics and the structure of sounds.

Feature controlled adaptive difference operators

Differential operators are essential for many image processing applications which require the computation of typical characteristics of continuous surfaces, as e.g. tangents, curvature, flatness, shape descriptors. We propose to replace differential operators by the combined action of sets of feature detectors and locally adaptive difference operators, resulting in a more accurate computation of the required derivatives in each pixel neighborhood. Both the set of feature detectors and the set of difference operators have a rigid mathematical structure, which is described by a set of Groebner bases for each class of fitting functions. This representation allows a systematic description of the hierarchical structure with ordering relations for all different function classes. The explicit computation of fitting functions is avoided by our technique and replaced by a function classification process. A set of simple local feature detectors is used to find the class of fitting functions which locally yields the best approximation for the digitized image surface. By a systematic optimization process, we determine for each fitting function class a difference operator which is an optimal approximation for a particular differential operator. As an example, we describe how to compute the best discrete approximation for the Laplacian differential operator in each pixel neighborhood and illustrate how the Laplacian of Gaussian edge detection method can benefit from these results.

Feature discovery by competitive learning

This paper reports the results of our studies with an unsupervised learning paradigm which we have called “Competitive Learning.” We have examined competitive learning using both computer simulation and formal analysis and have found that when it is applied to parallel networks of neuron-like elements, many potentially useful learning tasks can be accomplished. We were attracted to competitive learning because it seems to provide a way to discover the salient, general features which can be used to classify a set of patterns. We show how a very simply competitive mechanism can discover a set of feature detectors which capture important aspects of the set of stimulus input patterns. We also show how these feature detectors can form the basis of a multilayer system that can serve to learn categorizations of stimulus sets which are not linearly separable. We show how the use of correlated stimuli con serve as a kind of “teaching” input to the system to allow the development of feature detectors which would not develop otherwise. Although we find the competitive learning mechanism a very interesting and powerful learning principle, we do not, of course, imagine thot it is the only learning principle. Competitive learning is an essentially nonassociative statistical learning scheme. We certainly imagine that other kinds of learning mechanisms will be involved in the building of associations among patterns of activation in a more complete neural network. We offer this analysis of these competitive learning mechanisms to further our understanding of how simple adaptive networks can discover features important in the description of the stimulus environment in which the system finds itself.

The role of spatial redundancy in grapheme recognition: perception or inference?

The question under investigation is whether spatial redundancy operates by restricting the number of valid alternatives at each serial position or whether it serves a perceptual function by keeping visually confusable graphemes from appearing in the same array and/or maximizing the distance between such graphemes when they do occur in the same array. The first experiment used the same-different task to establish a confusion matrix for 12 non-linguistic symbols. The spatial relation between the members of two pairs of confusable symbols was manipulated in a second experiment, which had subjects look for the presence or absence of a predetermined target symbol in single six-symbol linear arrays. Facilitation was found to be dependent upon the perceptual consequences of serial position constraint rather than upon the constraint per se. The constraint was most effective when it served to prevent members of visually confusable pairs from occurring in the same array. Since spatial redundancy may operate at the feature extraction stage by minimizing competition for the same sets of feature detectors and since words are likely to be high in spatial redundancy, the possibility is raised that part of the word superiority effect may be due to visual factors rather than to linguistic context.