Radial basis function neural networks (RBFNNs) are widely applied due to their rapid modeling capabilities and efficient learning performance. However, when dealing with high-dimensional data, RBFNNs encounter two critical limitations: the hidden layer responses using Gaussian kernels suffer from ineffective activation and numeric underflow; and the estimation of output layer weights typically involves tedious parameter tuning and inefficient loading of high-dimensional feature matrices. To overcome these challenges, we first propose a dimensionality-adaptive Gaussian kernel function (DAGKF) equipped with a novel width adjustment mechanism that flexibly mitigates the numerical difficulties inherent in high-dimensional spaces. Moreover, to avoid processing entire feature matrices simultaneously, we introduce a multioutput coordinate descent (MOCD) algorithm that enables parallel computation across multioutput systems. Building upon MOCD, we further develop the joint residual MOCD (JRMOCD) algorithm, which incorporates a joint residual criterion for more effective weight estimation. The convergence of the JRMOCD algorithm is rigorously proven. Extensive experiments demonstrate the superior performance of the proposed methods, particularly in high-dimensional settings.

Fuzzy systems have been employed in many fields and achieved remarkable results. However, due to the inherent characteristics, there is still a challenge for them to deal with high-dimensional data which includes a large number of features and becomes very common in the current era of Big Data. Most of the literature employ the product, minimum, softmin and its adaptive versions to compute the firing strengths in fuzzy system modeling, where only the first two are standard T-norms conforming to the theoretical basis of fuzzy logic reasoning. But easy to cause numeric underflow and nondifferentiability are their disadvantages, respectively. To comply with fuzzy theory basis and alleviate the aforementioned predicament of dimensionality, this article investigates how to design high-dimensional Takagi–Sugeno–Kang (TSK) fuzzy system based on Dombi T-norm, which has not been explored for fuzzy system modeling to the best of our knowledge. We first build Dombi T-norm based TSK (DombiTSK) model, then an adaptive strategy is designed for the index parameter of Dombi T-norm to enhance the performance of DombiTSK, which results in so-called adaptive DombiTSK (ADMTSK) fuzzy system. To further improve the design and performance of ADMTSK, we give a novel membership function with positive lower bound to match the use of adaptive Dombi T-norm, which is constructed based on Gaussian membership function (GMF) and named as composite GMF (CGMF). The experiments are conducted on high-dimensional classification datasets with feature dimensions varying from 1024 to 120 432 to evaluate the proposed methodologies. Experimental results verify the advantages of adaptive Dombi T-norm and CGMF. The comparison results and statistical tests among ADMTSK and other state-of-the-art fuzzy algorithms demonstrate that our proposed model outperforms its rivals.

Algorithm of magnetic structure extraction and analysis in ultra thin magnetic film images is proposed. This algorithm allows to gain successful results and calculates a large number of characteristics of structures on magneto-optical images. The algorithm consists of three parts: background correction, structure extraction and calculation of dendrite characteristics. For correction of magnetic image we use methods for magneto-optic contrast. One of the basic features of structure extraction part is a preservation of border properties. Therefore the basic processing of extraction is applied for binary image. Proposed characteristics allow to describe and to classify dendrites. For analysis of complex magnetics structures topological properties are calculated for three basic objects types: body, holes and gulf. The software system ldquoZubrrdquo has been realized for magnetic structure image analysis.

Pixel force field is a novel image representation where at each pixel a two-dimensional vector is defined for representing the circumstance of the pixel. The vector is oriented to the center of the region composed of vectors having the same qualitative property, such as color and gray-scale level. Using the pixel force field, that is, the orientation and the magnitude of the vector, many fundamental and specific image processing tasks can be solved. As examples of the tasks, the force field is applied to color image thinning, color image segmentation, and color map vectorisation.

It is widely accepted that automatic interpretation of drawings and documents are not achieved in the short to medium term and that manual digitisation is not an acceptable alternative. Despite this, there has been little systematic discussion of the role of the user in line drawing interpretation. We consider desirable properties of human interaction with line drawing interpretation systems, argue that descriptions are required of the inference structure of line drawing interpretation tasks and systems if appropriate and effective user involvement is to be achieved, and develop and compare the inference structures of two well-developed line drawing interpretation systems; one automatic, one interactive. Analysis of these representations highlights two areas in which interactivity could be improved. An interactive system addressing one of those areas is outlined and directions for future research are identified.

A novel algorithm for complexity reduction in binary image processing, namely for computation of correlation between image and object template is proposed. This algorithm is based on direct computation of vector-matrix multiplication with utilisation of binary matrix factorisation approach. Comparison with other algorithms is given and it is shown that our approach allows to reduce time and complexity of this task.

Two algorithms for segmentation of cell images are proposed. They have a unique part that contains computation of morphological gradient to extract object borders and thinning the obtained borders to get a line of one-pixel thickness. For this task, we propose the fast gray-scale thinning algorithm that is based on the idea of the analysis of binary image layers. Then, the obtained one-pixel lines are used to extract cells and compute their characteristics. The algorithms based on morphological and split/merge segmentation are developed and used for this task.

The paper describes the VEDI (Vectorization of Engineering Drawing Images) system developed for automatic recognition of main engineering drawing (ED) entities. The main principles of ED interpretation are introduced and the algorithms to recognize main ED entities are briefly described. In conclusion, some technical parameters and experimental results of the system performance are given.

One of areas where reverse engineering is used is integrated circuit (IC) production. Part of an existing IC topology can be utilised during design of a new IC. In this paper, we propose a method to automatically recognise IC elements and to obtain IC description from an IC layer image. The main distinguishing features of the proposed method are stability in respect to noise and low error percentage. To speed-up the processing, the special fast algorithms for edge detection, image vectorisation and reconstruction of vector representation have been developed.

The paper introduces the main principles of automatic interpretation of engineering drawing images. The technology of ED interpretation is proposed based on the introduced principles. The algorithms for automatic recognition of the main ED entities: line types, circular arcs, blocks, crosshatched areas and dimensions are proposed. They have been verified experimentally in the whole ED interpretation technology and show good results.

A binary pattern represented by means of its (d/sub 1/, d/sub 2/)-weighted skeleton is decomposed into elementary regions of given shape by selecting among its skeletal pixels those representing the considered regions. The selection is achieved by combining distance and directional information associated to each skeletal pixel with the notion of power of expansion of a pixel. A novel algorithm using these concepts to achieve a decomposition into possibly overlapping parts is presented and its performance in terms of naturalness and stability of the achieved decomposition is discussed.

The distance labeled skeleton of a two-dimensional digital object is hierarchically decomposed into loops, branches and concatenations of branches. Decomposition is obtained by using an iterated tracing-and-deleting process alternately applied to more and more internal skeleton subsets. Every skeleton subset is associated a feature, called the relevance, which is related to the spatial extension of the object region represented by that subset. The relevance is used to decide on how to perform concatenations, as well as to rank skeleton decomposition components ascribed to the same hierarchy level. The decomposition is stable under object rotation and can be used in a recognition process accomplished via graph matching.

The authors describe a system for automatic interpretation of map-drawings. To vectorize large-size 2-D line-drawing images, an effective pipeline-oriented scheme and special techniques have been developed on the basis of economic image representation. This allows processing large-size binary images on a personal computer and obtaining satisfactory time characteristics. This approach can be easily realized in a pipelined architecture using a simple transputer chain. The document object recognition techniques are described.>

The authors present a PC-based cartographical system to digitize maps. A memory restriction made us develop special technologies and techniques to digitize large-sized map-drawings. The combination of manual digitizing and labeling with automatic vectorization and recognition, and interactive editing allowed us to get satisfactory time characteristics for digitizing complex maps. To process automatically scanned maps in a restrictive computer memory, an effective pipeline oriented scheme and new techniques have been developed. A new process called object labeling has been introduced to speed up the interpretation process. An output database structure has been suggested to store all needed information about the map.>