Size modification of binary pictures can be mapped onto the CNN array using space variant linear templates. However, if all the parameters have to be set for each cell individually, then one of the CNN's main adva...
详细信息
Size modification of binary pictures can be mapped onto the CNN array using space variant linear templates. However, if all the parameters have to be set for each cell individually, then one of the CNN's main advantages will be lost in practice, the simple and quick parallel reprogrammability. In this paper, a general methodology is presented to derive the space variant templates of the complete weighting matrix from control pictures applying a simple nonlinear space invariant template. The straightforward design method presumes a modified CNN architecture (multiple input and specific nonlinear voltage-controlled current sources in every cell) and can be extended for a large class of sparse weighting matrices. Following this strategy the diminishment and enlargement process has been investigated using constant cell current and various bias maps in the transformations.
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.
Cellular neural networks (CNNs) paradigm is applied in the paper to compute the transient response of mechanical vibrating systems. Based on previous theoretical results on this field we would like to show (i) how the...
详细信息
Cellular neural networks (CNNs) paradigm is applied in the paper to compute the transient response of mechanical vibrating systems. Based on previous theoretical results on this field we would like to show (i) how the CNN templates can be generated automatically by a subroutine from the COSMOS/M finite element analysis system; (ii) how we assign to each degree of freedom two coupled CNN layers and how the templates are derived. Some interesting examples are shown and analyzed.< >
In this paper we report on a fast, complex and efficient implementation of the Cellular neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 50...
详细信息
In this paper we report on a fast, complex and efficient implementation of the Cellular neural Network Universal Machine as an IC chip. The chip has continuous time analog dynamics, and has been designed to process 500,000 image frames per second.< >
Novel types of analogic algorithms, using spatio-temporal CNN (cellular nonlinear/neural networks) operations are introduced. These algorithms make complex decisions in images without reading out the CNN chip. This ma...
详细信息
Novel types of analogic algorithms, using spatio-temporal CNN (cellular nonlinear/neural networks) operations are introduced. These algorithms make complex decisions in images without reading out the CNN chip. This makes them extremely time, area, and power effective. Two crucial effects are emphasized: diffusion type templates are applied during a finite time interval and local logic operates within well defined parts (patches) in the image plane. Hence, a new type of pattern recognition algorithm is introduced. The technique is demonstrated on an example. In our example we are dealing with an actual problem: how to avoid the counterfeiting on color copiers.< >
暂无评论