Abstract—We introduce a novel rich local descriptor of an image point, we call the (labeled) distance set, which is determined by the spatial arrangement of image features around that point. We describe a two-dimensional (2-D) visual object by the set of (labeled) distance sets associated with the feature points of that object. Based on a dissimilarity measure between (labeled) distance sets and a dissimilarity measure between sets of (labeled) distance sets, we address two problems that are often encountered in object recognition: object segmentation, for which we formulate a distance sets shape filter, and shape matching. The use of the shape filter is illustrated on printed and handwritten character recognition and detection of traffic signs in complex scenes. The shape comparison procedure is illustrated on handwritten character classification, COIL-20 database object recognition and MPEG-7 silhouette database retrieval. Index Terms—Character recognition, distance set, image database retrieval, MPEG-7, object recognition, segmentation, shape descriptor, shape filter, traffic sign recognition. I.

We propose a biologically motivated computational step, called nonclassical receptive field (non-CRF) inhibition, more generally surround inhibition or suppression, to improve contour detection in machine vision. Non-CRF inhibition is exhibited by 80 % of the orientation-selective neurons in the primary visual cortex of monkeys and has been demonstrated to influence the visual perception of man as well. The essence of this mechanism is that the response of an edge detector in a certain point is suppressed by the responses of the operator in the region outside the area of operator support. We combine classical edge detection with two types of inhibitory mechanism, isotropic and anisotropic inhibition, both of which have counterparts in biology. For edge detection, we also use a biologically motivated method (the Gabor energy operator). The resulting operator responds strongly to isolated lines, edges, and contours, but exhibits a weaker or no response to edges that make part of texture. We use natural images with associated ground truth contour maps to assess the performance of the proposed operator regarding the detection of contours while suppressing texture edges. The results show that our method enhances contour detection in cluttered visual scenes more effectively than classical edge detectors used in machine vision (Canny edge detector). Therefore, the proposed operator is more useful for contour-based object recognition tasks, such as shape comparison, than traditional edge detectors, which do not distinguish between contour and texture edges. Traditional edge detection algorithms can, however, also be extended with surround suppression. Next to the advancement of contour detection in machine vision, this study contributes to the understanding of inhibitory mechanisms in biology.

On-road vehicle detection is an important problem with application to driver assistance systems and autonomous, self-guided vehicles. The focus of this paper is on the problem of feature extraction and classication for rear-view vehicle detection. Specically, we propose using Gabor filters for vehicle feature extraction and Support Vector Machines (SVMs) for vehicle detection. Gabor filters provide a mechanism for obtaining some degree of invariance to intensity due to global illumination, selectivity in scale, and selectivity in orientation. Basically, they are orientation and scale tunable edge and line detectors. Vehicles do contain strong edges and lines at different orientation and scales, thus, the statistics of these features (e.g., mean, standard deviation, and skewness) could be very powerful for vehicle detection. To provide robustness, these statistics are not extracted from the whole image but rather are collected from several subimages obtained by subdiving the original image into subwindows. These features are then used to train a SVM classifier. Extensive experimentation and comparisons using real data, different features (e.g., based on Principal Components Analysis (PCA)), and different classifiers (e.g., Neural Networks (NNs)) demonstrate the superiority of the proposed approach which has achieved an average accuracy of 94.81% on completely novel test images.

Appearance-based methods represent a promising research direction to the problem of vehicle detection. These methods learn the characteristics of the vehicle class from a set of training images which capture the variability in vehicle appearance. First, training images are represented by a set of features. Then, the decision boundary between the vehicle and non-vehicle classes is computed by modelling the probability distribution of the features in each class or through learning. The purpose of this study is to investigate the e#ectiveness of two important types of features for vehicle detection based on Haar wavelets and Gabor filters. In both cases, the decision boundary is computed using Support Vector Machines (SVMs), a recent development in classification algorithms which performs structural risk minimization to maximize generalization on novel data. Both wavelet and Gabor features have demonstrated good performance in various application domains including face detection and image retrieval. Wavelet features encode edge information, a good feature for vehicle detection. Most importantly, they capture the structure of vehicles at multiple scales. Gabor filters provide a mechanism for obtaining orientation and scale tunable edge and line detectors. Vehicles do contain strong edges and lines at di#erent orientation and scales, thus, this type of features are also very attractive for vehicle detection. Our experimental results and comparisons using real data illustrate the e#ectiveness of both types of features for vehicle detection, with Gabor features performing better than Haar wavelet features. Careful examination of our results revealed that the two feature sets yield di#erent misclassification errors which led us to the idea of combining them for improving perfor...

Past work on vehicle detection has emphasized the issues of feature extraction and classification, however, less attention has been given on the critical issue of feature selection. The focus of this paper is on improving the performance of on-road vehicle detection by employing a set of Gabor filters that have been specifically customized for the problem of vehicle detection. The key idea is optimizing the parameters of Gabor filters such that they respond stronger to features present in vehicles than to non-vehicles, therefore, improving discrimination between the two classes. Specifically, we propose a systematic and general evolutionary Gabor filter optimization (EGFO) approach with the objective of producing a more optimal set of filters for vehicle detection. The EGFO approach unifies filter design and filter selection by integrating Genetic Algorithms (GAs) with an incremental clustering approach. Filter design is performed using GAs, a global optimization approach that encodes the parameters of Gabor filters in a chromosome and uses genetic operators to optimize them. Filter selection is performed by grouping together filters having similar characteristics using an incremental clustering approach in the parameter space. This step eliminates redundant filters, leading to a compact, optimized set of filters. The resulted filters are evaluated using an application-oriented fitness criterion based on Support Vector Machines (SVMs). We have tested the proposed framework using real data collected in Dearborn, Michigan in Summer and Fall 2001, using Ford's proprietary low light camera. Our experimental results demonstrate that the set of Gabor filters, specifically optimized for the problem of vehicle detection, are more sensitive to local features present in vehicles ...

This paper is focused on the Co-segmentation problem [1] – where the objective is to segment a similar object from a pair of images. The background in the two images may be arbitrary; therefore, simultaneous segmentation of both images must be performed with a requirement that the appearance of the two sets of foreground pixels in the respective images are consistent. Existing approaches [1, 2] cast this problem as a Markov Random Field (MRF) based segmentation of the image pair with a regularized difference of the two histograms – assuming a Gaussian prior on the foreground appearance [1] or by calculating the sum of squared differences [2]. Both are interesting formulations but lead to difficult optimization problems, due to the presence of the second (histogram difference) term. The model proposed here bypasses measurement of the histogram differences in a direct fashion; we show that this enables obtaining efficient solutions to the underlying optimization model. Our new algorithm is similar to the existing methods in spirit, but differs substantially in that it can be solved to optimality in polynomial time using a maximum flow procedure on an appropriately constructed graph. We discuss our ideas and present promising experimental results. 1.

strategies based image registration via feature matching

Robust and reliable vehicle detection from images acquired by a moving vehicle (i.e., on-road vehicle detection) is an important problem with applications to driver assistance systems and autonomous, self-guided vehicles. The focus of this work is on the issues of feature extraction and classification for rear-view vehicle detection. Specifically, by treating the problem of vehicle detection as a two-class classification problem, we have investigated several di#erent feature extraction methods such as Principal Component Analysis (PCA), Wavelets, and Gabor filters. To evaluate the extracted features, we have experimented with two popular classifiers, Neural Networks(NNs) and Support Vector Machines(SVMs). Based our evaluation results, we have developed an on-board real-time monocular precrash vehicle detection system that is capable of acquiring grey-scale images, using Ford's proprietary low light camera, achieving an average detection rate of 10 Hz. Our vehicle detection algorithm consists of two main steps: a multi-scale driven hypothesis generation step and an appearance-based hypothesis verification step. During the hypothesis generation step, image locations where vehicles might be present are extracted. This step uses multi-scale techniques to speed up detection but also to improve system robustness. The appearance-based hypothesis verification step verifies the hypotheses using Gabor features and SVMs. The system has been tested in Ford's concept vehicle under di#erent tra#c conditions (e.g., structured highway, complex urban streets, varying weather conditions), illustrating good performance. Keywords--- Vehicle detection, Principal Component Analysis, Wavelets, Gabor filters, Neural Networks, Support Vector Machines.

One of the fundamental issues in image processing and machine vision is texture, specifically texture feature extraction, classification and abnormality detection. This thesis is concerned with the analysis and classification of natural and random textures, where the building elements and the structure of texture are not clearly determinable, hence statistical and signal processing approaches are more appropriate. We investigate the advantages of multi-scale/multidirectional signal processing methods, higher order statistics-based schemes, and computationally low cost texture analysis algorithms. Consequently these advantages are combined to form novel algorithms.

Connected filters are edge-preserving morphological operators, which rely on a notion of connectivity. This is usually the standard 4 and 8-connectivity, which is often too rigid since it cannot model generalized groupings such as object clusters or partitions. In the set-theoretical framework of connectivity, these groupings are modeled by the more general second-generation connectivity. In this paper, we present both an extension of this theory, and provide an efficient algorithm based on the Max-Tree to compute attribute filters based on these connectivities. We first look into the drawbacks of the existing framework that separates clustering and partitioning and is directly dependent on the properties of a preselected operator. We then propose a new type of second-generation connectivity termed mask-based connectivity which eliminates all previous dependencies and extends the ways the image domain can be connected. A previously developed Dual-Input Max-Tree algorithm for area openings is adapted for the wider class of attribute filters on images characterized by second-generation connectivity. CPU-times for the new algorithm are comparable to the original algorithm, typically deviating less than 10 percent either way.