The goals, objectives, characteristics, prerequisites, and courses of an information technology curriculum developed at the University of Veszprem in Hungary are discussed. Basic, introductory, and core courses as wel...
详细信息
The goals, objectives, characteristics, prerequisites, and courses of an information technology curriculum developed at the University of Veszprem in Hungary are discussed. Basic, introductory, and core courses as well as special subjects are listed, and the program schedule of the five years is presented. The place and role of information engineering in a changing world is discussed, including some thoughts on the role of information technology in the general university curricula.< >
An effective new character recognition procedure implemented on a new type of hardware system is proposed. This procedure applied a new architecture, called CNND. This CNND contains one or more analog cellular neural ...
详细信息
An effective new character recognition procedure implemented on a new type of hardware system is proposed. This procedure applied a new architecture, called CNND. This CNND contains one or more analog cellular neural Networks (CNN) and some digital logic, incorporating the advantages of the fast analog CNN signal processing and the fast and easy decision capability of digital logics. This paper shows that this CNND system can be used for recognition of multifont printed or handwritten characters. Implemented in hardware, the system could hit the 100 000 char/s recognition speed with a recognition rate of more than 95 %. We show that the CNN results of pictures (maximum 40 * 40 pixels) of printed characters can be coded into about n * 20 bits (n = 2 ... 6) , so the coded results can be used to address memories of about 1 MB. The codes of CNN results of possible character pictures are used to address the memories while the memory contents are filled by the character categories. Prior to the hardware implementation the decision memories are filled by the results of recognition simulation for the possible pictures of each character-class in a filling procedure. In the memory filling procedure the simulated recognition uses a new random-type nearest neighbor (NN) method, which is ideal for the recent proposal of hardware applications. Recognition of handwritten characters is demonstrated in the same system with good recognition accuracy.
Cellular neural Networks (CNN's) with space-varying interconnections are considered here to implement associative memories, A fast learning method is presented to compute the interconnection weights. The algorithm...
详细信息
Cellular neural Networks (CNN's) with space-varying interconnections are considered here to implement associative memories, A fast learning method is presented to compute the interconnection weights. The algorithm was carefully tested and compared to other methods. Storage capacity, noise immunity, and spurious state avoidance capability of the proposed system are discussed.
A two-layer continuous-time cellular neural network for finding the Radon transform of a binary image is presented. The functionality of this cellular neural network follows from the functionality of the connected com...
详细信息
A two-layer continuous-time cellular neural network for finding the Radon transform of a binary image is presented. The functionality of this cellular neural network follows from the functionality of the connected component detector cellular neural network.
The Cellular neural Networks (CNN) providing for efficient analog array processing of images are used for revealing surface features hidden in different types of random-dot stereograms (RDS) coding 3D information in i...
详细信息
Recognition of small patterns covering only a few pixels in an image cannot be done by conventional recognition methods. A theoretically new pattern recognition method has been developed for undersampled objects which...
详细信息
Recognition of small patterns covering only a few pixels in an image cannot be done by conventional recognition methods. A theoretically new pattern recognition method has been developed for undersampled objects which are (much) smaller than the window-size of a picture element (pixel), i.e. these objects are of subpixel size. The proposed statistical technique compares the gray-level histogram of the patterns of a set of scanned objects to be examined with the (calculated) gray-level densities of different (in shape or size) possible objects, and the recognition is based on this comparison. This method does not need high-precision movement of scanning sensors or any additional hardware. Moreover, the examined patterns should be randomly distributed on the screen, or a random movement of camera is (or target or both are) needed. Effects of noise are analysed, and filtering processes are suggested in the histogram domain. Several examples of different object shapes (triangle, rectangle, square, circle, curving lines, etc.) are presented through simulations and experiments. A number of possible application areas are suggested, including astronomy, line-drawing analysis and industrial laser measurements.
Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image ...
详细信息
Markovian approaches to early vision processes need a huge amount of computing power. These algorithms can usually be implemented on parallel computing structures. with the Cellular neural Networks (CNN), a new image processing toot is coming into consideration, Its VLSI implementation takes place on a single analog chip containing several thousands of cells. Herein se use the CNN UM architecture for statistical image segmentation. The Modified Metropolis Dynamics (MMD) method can be implemented into the raw analog architecture of the CNN, We are able to implement a (pseudo) random held generator using one layer (one memory/cell) of the CNN. We can introduce the whole pseudostochastic segmentation process in the CNN architecture using 8 memories/cell, We use simple arithmetic functions (addition, multiplication), equality-test between neighboring pixels and very simple nonlinear output functions (step, jigsaw, With this architecture, a real VLSI CNN chip can execute a pseudostochastic relaxation algorithm of about 100 iterations in about 1 ms, In the proposed solution the segmentation is unsupervised. We have developed a pixel-level statistical estimation model. The CNN turns the original image into a smooth one. Then we have two gray-level values for every pixel: the original and the smoothed one. These two values are used for estimating the probability distribution of region label at a given pixel. Using the conventional first-order Markov Random Field (MRF) model, some misclassification errors remained at the region boundaries, because of the estimation difficulties in case of low SNR. By using a greater neighborhood, this problem has been avoided. In our CNN experiments, we used a simulation system with a fixed-point integer precision of 16 bits, Our results show that even in the case of the very constrained conditions of value-representations (the interval is (-64, +64), the accuracy is 0.002) can result in an effective and acceptable segmentation.
The programmability (as a stored program) of the CNN Universal Machine is discussed first. It is shown why and in which sense this machine is universal. A new type of algorithm, the analogic one, is introduced. The ap...
Various types of CNNs are summarized and the taxonomy of CNN is given according to the different types of grids, processors, interactions, and modes of operation. Next, the CNN Universal Machine is introduced. The arc...
A new statistical pattern recognition method has been developed for detection, recognition or measurement of patterns which are (much) smaller than the measure of the elementary pixel windows in the image screen. In t...
详细信息
A new statistical pattern recognition method has been developed for detection, recognition or measurement of patterns which are (much) smaller than the measure of the elementary pixel windows in the image screen. In this measurement the gray-level histogram of the objects examined is compared with the simulated histograms of different (in type or size) possible objects, and the recognition (of shape or measure) is taken on the basis of the comparison. This method does not need ultra-precise movement of the scanning sensors or any additional hardwares. Moreover, the examined pattern should be randomly distributed on the screen, or a random movement of camera (or target or both) is needed. Effect of noises are analyzed, and filtering processes are suggested in the histogram domain. Several examples of different shapes are presented through simulations and experiments.< >
暂无评论