International Journal of Pattern Recognition and Artificial Intelligence

The interpretation of handwritten sentences is carried out using a holistic approach in which both text image recognition and the interpretation itself are tightly integrated. Conventional approaches follow a serial, first-recognition then-interpretation scheme which cannot adequately use semantic–pragmatic knowledge to recover from recognition errors. Stochastic finite-sate transducers are shown to be suitable models for this integration, permitting a full exploitation of the final interpretation constraints. Continuous-density hidden Markov models are embedded in the edges of the transducer to account for lexical and morphological constraints. Robustness with respect to stroke vertical variability is achieved by integrating tangent vectors into the emission densities of these models. Experimental results are reported on a syntax-constrained interpretation task which show the effectiveness of the proposed approaches. These results are also shown to be comparatively better than those achieved with other conventional, N-gram-based techniques which do not take advantage of full integration.

Previous research efforts on optical font recognition have mostly limited applications since they deal with only a few types of font attributes and estimate them from a line or block of text. This paper proposes a word-level optical font recognition system for printed Korean and English documents. At the word-level, it has the advantages of obtaining more detailed font attributes including the following: script (Korean and English), font style (regular, bold, italic, and underlined), typeface (Myung-jo and Gothic), point size (10, 12, 14 pts), and word length (2, 3, 4, 5 for Korean, and 4 to 10 for English). A hierarchical classifier and several typographical features have been devised for the system, and their effectiveness are proven by an experiment with a database of 100 sets of 264 font categories.

Segmentation of ovarian ultrasound images using cellular neural networks (CNNs) is studied in this paper. The segmentation method consists of five successive steps where the first four uses CNNs. In the first step, only rough position of follicles is determined. In the second step, the results are improved by expansion of detected follicles. In the third step, previously undetected inexpressive follicles are determined, while the fourth step detects the position of ovary. All results are joined in the fifth step. The templates for CNNs were obtained by applying genetic algorithm. The segmentation method has been tested on 50 ovarian ultrasound images. The recognition rate of follicles was around 60% and misidentification rate was around 30%.

We present a novel interactive edge detection algorithm that combines A* search with low-level adaptive image processing. The algorithm models the semantically driven interpretation that we hypothesize to occur between the mind and visual cortex in the human brain. The basic idea is that oriented Gabor sub-bands are used to model grating cells in the mammalian visual system. These sub-bands are used during the search for a path to a marker in an image. A domain expert uses image markers to select edges of interest.

We demonstrate the system in several image domains. Examples are shown in the areas of photo-interpretation, medical imaging, path planning and general edge finding. The A* search finds a suboptimal result, but executes in a time that is typically 10 to 1,000 times faster than the dynamic programming approach currently used for this type of edge detection.

The search for the optimal ordering of a set of variables in order to solve a computational problem is a difficulty that can appear in several circumstances. One of these situations is the automatic learning of a network structure, for example, a Bayesian Network structure (BN) starting from a dataset. Searching in the space of structures is often unmanageable, especially if the number of variables is high. Popular heuristic approaches, like Cooper and Herskovits's K2 algorithm, depend on a given ordering of variables. Estimation of Distribution Algorithms (EDAs) are a new paradigm for Evolutionary Computation that have been used as a search engine in the BN structure learning problem. In this paper, we will use two different EDAs to obtain not the best structure, but the optimal ordering of variables for the K2 algorithm: UMDA and MIMIC, both of them in discrete and continuous domains. We will also check whether the individual representation and its relation to the corresponding ordering play important roles, and whether MIMIC outperforms the results of UMDA.

In this contribution we demonstrate how the task of visual scene exploration can be solved by a knowledge-based vision system. During scene exploration, the system searches for a fixed number of a priori known objects in a static scene. If not all objects are visible using the initial camera set-up, the camera parameters have to be adjusted and the camera has to be moved by the system. This problem is reduced to the choice of optimal camera actions. The information about the objects and the camera actions is uniformly represented in a semantic network. In addition, a control algorithm is provided that finds the optimal assignment from objects to parts of a scene based on a suitable analysis strategy. This strategy is acquired by the system itself using reinforcement learning methods. The paper focuses on aspects of knowledge representation concerning the integration of camera actions and on the integration of reinforcement learning methods in a semantic network formalism and applies them in a realistic setup. Experiments are shown for images of two office rooms.

In this paper, we describe a new evolutionary computation approach, called multiphase genetic programming (MPGP). The special features of this approach lie in its variable-granularity representations of chromosomes and their corresponding genetic operations. In the paper, we provide an overview of the MPGP approach as well as details on how the sumo maneuver evolution experiments are carried out and how the MPGP-based case study differs from others.

In this paper, a novel profile verification scheme based on the ear, contour lines and feature points from head profile images is proposed. From the side image of a human head taken by a CCD camera, the contour line of the image is extracted by the simple filling method and morphological filtering. Based on the reference coordinate set by using ear images enrolled in the database a priori, the features of the contour line such as the tip of the nose, bottom of the nose, eye point and so on are extracted. The contour of the given image is divided into segments by utilizing the extracted feature points. The directional code of each segment is proposed and the length of the segment is computed for generating the feature vector. The verification of the given profile is performed by matching these feature vectors with those of the enrolled database. The experimental results show validity of the developed method for feature extraction and profile verification.

In this paper, a color image segmentation algorithm and an approach to large-format image segmentation are presented, both focused on breaking down images to semantic objects for object-based multimedia applications. The proposed color image segmentation algorithm performs the segmentation in the combined intensity–texture–position feature space in order to produce connected regions that correspond to the real-life objects shown in the image. A preprocessing stage of conditional image filtering and a modified K-Means-with-connectivity-constraint pixel classification algorithm are used to allow for seamless integration of the different pixel features. Unsupervised operation of the segmentation algorithm is enabled by means of an initial clustering procedure. The large-format image segmentation scheme employs the aforementioned segmentation algorithm, providing an elegant framework for the fast segmentation of relatively large images. In this framework, the segmentation algorithm is applied to reduced versions of the original images, in order to speed-up the completion of the segmentation, resulting in a coarse-grained segmentation mask. The final fine-grained segmentation mask is produced with partial reclassification of the pixels of the original image to the already formed regions, using a Bayes classifier. As shown by experimental evaluation, this novel scheme provides fast segmentation with high perceptual segmentation quality.

Understanding is based on a large number of highly varied abilities called intelligence that can be measured. In this paper understanding abilities of the shape understanding system (SUS) are tested based on the adoption of the intelligence tests. The SUS tests are formulated as the tasks given to the system and performance of SUS is compared with the human performance of these tasks. The main novelty of the presented method is that the process of understanding is related to the visual concept represented as a symbolic name of the possible classes of shape. The visual concept is one of the ingredients of the concept of the visual object (the phantom concept) that makes it possible to perform different tasks that are characteristic for the visual understanding. The presented results are part of the research aimed at developing the shape understanding method able to perform the complex visual tasks connected with visual thinking. The shape understanding method is implemented as the shape understanding system (SUS).