Synthesis of a Cellular Nonlinear Network for a Fuzzy Associative Memory in Stereoscopic Vision
نویسندگان
چکیده
In this paper a Cellular Fuzzy Associative Memory containing fuzzy rules for gray image fuzzification is designed, considered as a subsystem of a CNN-based architecture able to store bidimensional patterns. After establishing the fuzzy rules which characterize the required FAM, these rules are properly codified and stored in a Cellular Nonlinear Network behaving as a memory. A numerical example concerning with the stereoscopic vision of a mobile robot is reported to show how the synthesized memory can process bidimensional patterns for robotic vision purposes.
منابع مشابه
Synthesis of Neural Associative Memories for Artificial Vision Systems by Fuzzy Image Segmentations
A design procedure of neural associative memories to be used for robot vision systems is developed, which fits in the capabilities both of discrete-time cellular neural networks (DTCNNs) and fuzzy logic. The choice of this kind of neural networks is motivated by their architecture, suitable for storing images, and their locally connected structure, which is effective for the hardware implementa...
متن کاملA Cellular Fuzzy Associative Memory for Image Fuzzification in Robot Vision Systems
In this paper a Cellular Fuzzy Associative Memory containing fuzzy rules for bidimensional image fuzzification in robot vision systems is developed. This cellular processor constitutes a subsystem of a CNNbased architecture which can store both bidimensional patterns and the rules to process them. After establishing the fuzzy rules characterizing the Fuzzy Associative Memory, a CNN behaving as ...
متن کاملFuzzy Associative Memories for Bidimensional Pattern Segmentation in CNN-based Systems
In this paper a design procedure of Fuzzy Associative Memories containing fuzzy rules for bidimensional pattern segmentation in CNN-based systems is developed. A Fuzzy Necessity/Possibility Technique is considered for these memories to provide binary segmented images adequate to be stored into cellular neural networks for object matching analysis. Simulation results are reported to show the cap...
متن کاملFuzzy Associative Memories and Their Relationship to Mathematical Morphology
Fuzzy associative memories (FAMs) belong to the class of fuzzy neural networks (FNNs). A FNN is an artificial neural network (ANN) whose input patterns, output patterns, and/or connection weights are fuzzy-valued [19, 11]. Research on FAM models originated in the early 1990’s with the advent of Kosko’s FAM [35, 37]. Like many other associative memory models, Kosko’s FAM consists of a single-lay...
متن کاملCellular Neural Networks in Active Vision System
In this paper, the application of CNN associative memories for 3D object recognition is presented. The main idea is to analyse the optical flow in an image sequence of an object. Several features of the optical flow between two succeeding images are calculated and merged to a time series of features for the whole image sequence. These features show several object specific characteristics and ar...
متن کامل