Search

Your search keyword '"Tavsanoglu, V."' showing total 12 results
Start Over Author "Tavsanoglu, V." Search Limiters Full Text
12 results on '"Tavsanoglu, V."'

3. A time-multiplexing simulator for cellular neural network (CNN)

Author

Tavsanoglu, V., El-Shafei, A.A.H., Sobhy, Mohammed, Tavsanoglu, V., El-Shafei, A.A.H., and Sobhy, Mohammed

Abstract

A CNN simulator and a Time-Multiplexing algorithm implementation are described. The model for the CNN cell is simulated by SIMULINK(R) but the multiplexing algorithm could be used with any other implementation. The CNN cell model was tested using several templates and the test results, using Connected Components Detection templates ( CCD) are given. This simulator provides a simple and user friendly environment for studying and analyzing CNN dynamics. The, Time-Multiplexing algorithm is tested using the edge detection and CCD templates and the results are attached.

Published
1998

11. Efficient Simulation of Time-Derivative Cellular Neural Networks.

Author

Polat, S. N. T., Yavuz, O., and Tavsanoglu, V.

Subjects
SIMULATION methods & models, OPERATIONS research, ARTIFICIAL neural networks, ARTIFICIAL intelligence, MULTILAYER perceptrons
Abstract

A fast simulation method for time-derivative cellular neural networks (TDCNN) is proposed. Using forward Euler approximation (FEA) for the derivative of the cell state and the backward Euler approximation (BEA) for the derivatives of the neighboring cell states enables the recursive computation of the cell state and provides a speed advantage of orders of magnitude. The state equations are then packed into a vector-matrix form which enables the previously empirically given time constraint to be expressed as a matrix condition. It is shown that using both FEA and BEA leads to a second-order difference equation whose corresponding second-order differential equation is derived and shown to yield the same simulation results. [ABSTRACT FROM PUBLISHER]

Published
2012
Full Text
View/download PDF

12. Fingerprint image enhancement using CNN filtering techniques.

Author

Saatci E and Tavsanoglu V

Subjects
Image Enhancement standards, Dermatoglyphics, Image Enhancement methods, Neural Networks, Computer
Abstract

Due to noisy acquisition devices and variation in impression conditions, the ridgelines of fingerprint images are mostly corrupted by various kinds of noise causing cracks, scratches and bridges in the ridges as well as blurs. These cause matching errors in fingerprint recognition. For an effective recognition the correct ridge pattern is essential which requires the enhancement of fingerprint images. Segment by segment analysis of the fingerprint pattern yields various ridge direction and frequencies. By selecting a directional filter with correct filter parameters to match ridge features at each point, we can effectively enhance fingerprint ridges. This paper proposes a fingerprint image enhancement based on CNN Gabor-Type filters.

Published
2003
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results