International Journal of Pattern Recognition and Artificial Intelligence

This paper introduces an effective method for signature separation from nonhomogeneous noisy background. It also introduces a solution to the problem of simulated signature verification in off-line systems. Extraction of shape and density features and the effectiveness of using each and both of them are discussed in the light of experimental results.

An optical character reader for processing typeset documents must be able to handle proportional spacing, the presence of touching characters and a wide variety of type fonts. This paper describes the design of a multifont character recognizer which uses a binary decision tree to classify a character on the basis of 197 geometric features. The algorithm for designing the decision tree is based upon an entropy minimization procedure, and makes no assumptions on the distribution or independence of the binary features.

The decision tree classifier provides confidence measures which may be used to reduce the substitution error rate at the expense of higher rejection rates. Methods of reducing the overall error rate by combining the decision tree classifier with other classifiers were examined. In particular, the paper evaluates the performance of a classifier using a combination of multiple decision trees, template matching and contextual post-processing. Error rates were highly sensitive to typeface and varied between 10 percent and 0.1 percent. Computer processing times for the various stages of the system are presented.

In this work the performance and computer time requirements of 15 classifiers are compared in images modeled by two-dimensional Gaussian Markov random fields which are represented by a causal autoregressive model of the second order. The per-pixel classifier and the object classifier directly or indirectly utilizing spectral-spatial characteristies of images are among them. The probability of misclassification (PMC) calculated analytically and experimentally on modeled data was used as a measure of a classifier performance. The influence of such factors as the object size and form, the inadequacy of a classifier and data models, the accuracy of spatial correlation estimation on the PMC is investigated.

The following main results are obtained. The performance of object classifiers is much better than that of per-pixel classifiers. The PMC of object classifiers decreases rapidly with the increase of the size of an object. The performance of object classifiers indirectly incorporating spatial characteristics of an object (OCIND) and that of object classifiers directly incorporating spatial characteristics (OCDIR) is similar for the linear decision rule. The performance of OCDIR is much better than that of OCIND for the quadratic decision rule. Computationally, averaging object classifiers are fastest, next are OCIND and finally OCDIR. The cross-shaped object classifier is better and faster than the square-shaped object classifier for the same number of pixels.

The realization of the paper-free office seems to be difficult that expected. Therefore, good paper-computer interfaces are necessary to transform paper documents into an electronic form, which allows the use of a filing and retrieval system. An electronic document page is an optically scanned and digitized representation of a printed page. Document analysis is the problem of interpreting and labeling the constitutents of the document. Although there are very reliable optical character recognition (OCR) methods, the process could be very inefficient. To prune the search space and to become more efficient, some search supporting methods have to be developed. This article proposes an approach to identify the layout of a document page by dividing it recursively into nested rectangular areas. The procedure is used as a basis for a document layout model, which is able to control an automatic interpretation mechanism for deriving a high level representation of the contents of a document. We have implemented our method in Common Lisp on a Symbolies 3640 Workstation and have run it for a large population of office documents. The results obtained have been very encouraging and have convincingly confirmed the soundness of our approach.

This paper surveys the applications of vision to fish sorting, fish fillet sorting and detection of surface and sub-surface defects (such as worms and bones). It stresses the specific implementation context, needed performances, illumination, detection principle, as well as vision algorithms. Also analyzed are the optical properties of fish. Examples of results are given.

A new method recognizing and locating partially occluded two-dimensional parts is presented. The objects are described by a set of segments derived form the polygonal coding of their contours, and by the geometrical relationships between the segments. Rewriting rules are used to improve the stability of the polygonal coding. The identification process utilizes a robust hypothesis generator, from which the segment research assisted by the spatial relationship is propagated into the scene. The originality of this method relies mainly on the use of structural relationships between the segments to select the robust initialization hypotheses, and the use of structural research to achieve hypothesis propagation. These last two points with the use of a hash-coding technique to improve the location of predicted segments, greatly reduce the combinatories and make the algorithm particularly rapid and effective. This approach is integrated within a vision system of a Flexible Assembly Workcell to accomplish the automatic assembly of partially overlapping parts.

An original knowledge representation scheme named KRP based on Petri net theory is proposed. The formal description of the scheme, and the inference procedure similar to "intersection search" in semantic networks, are given.