International Journal of Pattern Recognition and Artificial Intelligence

In this paper, we study the problem of recovering approximate shape from the shading of a three-dimensional object in a single image when knowledge about the object is available. The application of knowledge-based methods to low-level image processing tasks will help overcome problems that arise from processing images using a pixel-based approach. Shape-from-shading has generally been approached by precognitive vision methods where a standard operator is applied to the image based on assumptions about the imaging process and generic properties of what appears. This paper explores some advantages of applying knowledge and hypotheses about what appears in the image. The knowledge and hypotheses used here come from domain knowledge and edge-matching. Specifically, we are able to find solutions to some problems that cannot be solved by other methods and gain advantages in terms of computation speed over similar approaches. Further, we can fully automate the derivation of the approximate shape of an object. This paper demonstrates the efficacy of using knowledge in the basic operation of an early vision operator, and so introduces a new paradigm for computer vision that may be applied to other early vision operators.

The Reciprocal-Wedge Transform (RWT) facilitates space-variant image representation. In this paper a V-plane projection method is presented as a model for imaging using the RWT. It is then shown that space-variant sensing with this new RWT imaging model is suitable for fixation control in active stereo that exhibits vergence and versional eye movements and scanpath behaviors. A computational interpretation of stereo fusion in relation to disparity limit in space-variant imagery leads to the development of a computational model for binocular fixation. The vergence-version movement sequence is implemented as an effective fixation mechanism using the RWT imaging. A fixation system is presented to show the various modules of camera control, vergence and version.

The main aim of this paper is to introduce the single nearest neighbor approach for pattern recognition and the concept of incremental learning of a fuzzy classifier where decision making is based on data available up to time t rather than what may be available at the start of the trial, i.e. at t = 0. The single nearest neighbor method is explained in the context of solving the classic two-spiral benchmark. The proposed approach is further tested on the electronic nose coffee data to judge its performance on a real problem. This paper illustrates: (1) a novel fuzzy classifier system based on the single nearest neighbor method, (2) its application to the spiral benchmark taking the incremental pattern recognition approach, and (3) results obtained when solving the two-spiral problem with both nonincremental and incremental methods and coffee classification with the nonincremental method. The results show that incremental learning leads to improved recognition performance for spiral data and it is possible to study the behavioral characteristics of the classifier with possibility related parameters.

This paper proposes a novel Forward–Backward Smoothing-Based Learning Subspace Method (FBSLSM), which can satisfy the equirements of being insensitive to the order of presentation of the training samples, and is of faster convergence speed. This method is applied to the recognition of simulating High Resolution Radar (HRR) targets (two for ships, one for chaff). Moreover, for recognition of HRR targets, a new selection method of subspace dimensionality is given. The computer simulating experiments show that the corresponding performance of proposed FBSLSM such as rate of correct recognition and convergence speed is better than that of the ALSM presented by Oja.

The application of the orthogonal complex AR model approach has been extended for the recognition of partially occluded objects. The 2-D boundary of an object is extracted and is divided into a number of line segments by locating the turning points. Each line segment is resampled into a fixed number of data points and a complex AR model is used to represent each line segment. An orthogonal estimator is implemented to determine the correct model order and to estimate the corresponding AR model parameters. Each line segment is associated with a minimum feature vector denoting the estimated AR model parameters and similar line segments for different patterns have similar AR model parameters. Recognition of an occluded object based on the matching of line segments of two patterns is derived. An algorithm for finding the turning points has also been devised, which is quite robust to various object sizes and orientation, resolution and noise effect of the object image. Experimental results were obtained to show the effectiveness of the proposed approach for the recognition of objects which are partly covered or partially occluded, and the approach is robust to different object sizes and orientation.

In the field of mobile communications new robust Voiced/Unvoiced (V/UV) classification algorithms are required in that correct voicing detection is a crucial point in the perceived quality and naturalness of a very low bit-rate speech coding system. The paper shows that a valid and more convenient alternative to deal with the problem of voicing decision is to use methodologies like fuzzy logic which are suitable for problems requiring approximate rather than exact solutions, and which can be represented through descriptive or qualitative expressions. The Fuzzy Voicing Detector proposed is based on a pattern recognition approach in which the matching phase is performed using three fuzzy rules. The rules have been obtained using FuGeNeSys, a new hybrid learning tool based on Genetic Algorithm and Neural Networks. The fuzzy classifier is computationally very simple and more efficient than traditional methods, which are affected by misclassification errors, above all in the presence of background noise.

The backtracking algorithm is a prominent search technique in AI, particularly due to its use in Constraint Satisfaction Problems (CSPs), Truth Maintenance Systems (TMS), and PROLOG. In the context of CSPs, Dechter⁵ and Gashnig¹⁰ proposed two variants of the backtracking algorithm known as backjumping algorithms. One is graph-based and the other is failure-based backjumping algorithm. These algorithms attempt to backjump to the source of failure in case of a dead-end situation. This improves the backtracking performance. However, these algorithms are not consistent in the selection of the variable to backjump.

In this paper, the modifications of both types of backjumping algorithms are proposed. These algorithms adopt a technique to select the variable to backjump in a consistent manner. This further increases the search efficiency in them. The merits of these modified algorithms are investigated theoretically. Experimental results on the zebra problem and random problems show that the modified algorithms give better results on most occasions.

In computerized radiography (CR) imaging, collimation is frequently employed to shield body parts from unnecessary radiation exposure and minimize radiation scattering using X-ray opaque material. The radiation field is therefore the diagnostic region of interest which has been exposed directly to X-rays. We present an image analysis system for the recognition of the collimation, or equivalently, detection of the radiation field. The purpose is to (1) facilitate optimal tone scale enhancement, which can be driven only by the diagnostically useful part of the image data, and (2) minimize the viewing flare caused by the unexposed area. This system consists of three stages of operations: (1) pixel-level detection and classification of collimation boundary transition pixels; (2) line-level delineation of candidate collimation blades; and (3) region-level determination of the collimation configuration. This system has been reduced to practice and tested over 807 images of 11 exam types and a success rate in excess of 99% has been achieved for tone scale enhancement and masking. Due to the novel design of the system, its computational efficiency lends itself to online operations.