Narrow Results

The neighborhood system based rough set is a generalization of Pawlak's rough set model since the former uses the neighborhood system instead of the partition for constructing target approximation. In this paper, the neighborhood system based rough set approach is employed to deal with the incomplete information system. By the coverings induced by the maximal consistent blocks and the support sets of the descriptors, respectively, two neighborhood systems based rough sets are explored. By comparing with the original maximal consistent block and descriptor based rough sets, the neighborhood system based rough sets hold the same lower approximations and the smaller upper approximations. Furthermore, the concept of attribute reduction is introduced into the neighborhood systems and the corresponding rough sets. The judgement theorems and discernibility functions to compute reducts are also presented. Some numerical examples are employed to substantiate the conceptual arguments.

Satellite imagery consists of highly complex spatial features that make it difficult for traditional image processing techniques to use them for classification tasks. In this paper, we propose a novel method to use these hidden fractal information that naturally exist in these satellite images. We have designed a fractal-based descriptor which generates a scale invariant fractal image for easier fractal-based pattern extraction and uses it as an added feature vector that is combined with the original image and fed into a VGG-16 deep learning architecture which successfully classifies even low-resolution satellite images with an f1-score of 0.78.

For estimating log P values of a group of organic compounds, a back-propagation neural network with a 9–6–1 architecture was developed with optimal learning rate (ε) and momentum (μ) of 0.24 and 0.82, respectively. A collection of 131 organic compounds was chosen as data set that consists of normal hydrocarbons, alcohols, ethers, amines, ketones, acids, benzene derivatives, phenols, and aldehydes. The data set was divided into a training set consisting of 118 molecules and a prediction set consisting of 18 molecules. The most important properties that affect the partition coefficients of organic compounds (surface/volume, dipole moment, and those which are related to electrostatic potentials such as the sum of charges on the carbon atoms) were used as descriptors. These descriptors were obtained using AM1 semiempirical MO method for the gas phase geometries. The descriptors were selected via developing a multiple linear regression analysis. The ANN calculated values of partition coefficients (log Ps) for molecules of the training and prediction sets are in good agreement with the experimental values.

In many image analysis applications, such as image retrieval, the shape of an object is of primary importance. In this paper, a new shape descriptor, namely the Normalized Wavelet Descriptor (NWD), which is a generalization and extension of the Wavelet Descriptor (WD), is introduced. The NWD is compared to the Fourier Descriptor (FD), which in image retrieval experiments conducted by Zhang and Lu, outperformed even the Curvature Scale Space Descriptor (CSSD). Image retrieval experiments have been conducted using a dataset containing 2D-contours of 1400 objects extracted from the standard MPEG7 database. For the chosen dataset, our experimental results show that the NWD outperforms the FD.

The historical development of the physiology and psychology of perception and the technical area of “computer vision” periodically overlap, and both areas are mutually enriched by conceptual and model representations. In particular, retina-like sensors appeared in computer vision, which, as it turned out, not only model the features of the structural organization of the organs of vision but are also effective for the technical description and recognition of fragments of visual scenes. On the other hand, models created as a result of the generalization and systematization of physiological and psychological knowledge, receive technical validation are implemented as computer vision algorithms. One of the concepts — active perception, which appeared in psychology, was effectively used in technical vision. Within the framework of this concept, perception is treated not as a passive act, conditioned by reaction to events in the environment, but as an active behavior initiated by the subject of perception, conditioned by internal motivation, and affected by the situational context. The use of such a concept in technical vision gives an effective, biologically-inspired solution to the issue of interpreting ambiguous sensory information when such ambiguity is reduced due to the actions of the observer. The implementation of the paradigm of active perception from a technical point of view leads to a certain structural organization of sensor models, as well as ways of processing and aggregating visual information. In this chapter, we consider models of active vision, models of visual sensors, algorithms for the lower and upper levels of visual information processing, as well as application of active vision models for various technical problems.