Cellular associative neural networks for image interpretation
Christos Orovas1997, 6th International Conference on Image Processing and its Applications
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
This paper describes the architecture and the operation of a neural network based system for image interpretation. The system is based on the use of two models of associative neural networks, ADAM and AURA for image and symbolic processing respectively. Employing characteristics of cellular automata theory and applying ideas from syntactic and structural pattern recognition, it uses a hierarchical approach to learn the structure of images. The hardware implementation of this system is based on the C-NNAP hardware platform.
Related papers
Cellular associative neural networks for pattern recognition
… OF YORK DEPARTMENT OF COMPUTER SCIENCE- …, 1999
A common factor of many of the problems in shape recognition and, in extension, in image interpretation is the large dimensionality of the search space. One way to overcome this situation is to partition the problem into smaller ones and combine the local solutions towards global interpretations. Using this approach, the system presented in this thesis provides a novel combination of the descriptional power of symbolic representations of image data, the parallel and distributed processing model of cellular automata and the speed and robustness of connectionist symbolic processing.
The cellular neural network associative processor, C-NNAP
Image Processing and its Applications, 1995., Fifth …, 1995
This paper describes a novel associative processor that uses neural associative memories as its processing elements. The machine has been designed to tackle problems in AI and computer vision and using nodes that allow rapid search using inexact information over very large data sets. Each processing element is an advanced distributed associative memory (ADAM) which is capable of storing large numbers of pattern associations and allow rapid access. As a neural network, the memory performs associative match, not by conventional CAM approaches, but by forming a mapping between the patterns to be associated. The benefit of this is rapid access, fault tolerance and an ability to match on inexact data. These abilities arise due to the distributed storage used in the memory, which also allows for high capacity in the memory. The memory is designed to work on large data word sizes, i.e. matching can take place on data items as small as 64 bits or as large as 1Mb. The machine is ideally suited as a pattern processing machine, which is where most of the application work has been centered. This is because it is capable of taking large subsections of images and performing matching and comparisons on these.
Applications of Cellular Neural Networks to Image Understanding
The Cellular Neural Networks (CNN) model is now a paradigm of ceIlular analog programmable multidimensional processor array with distributed local logic and memory. CNNs consist of many paraIlel analogue processors computing in real time. One desirable feature is that these processors arranged in a two dimensional grid, only have local connections, which lend themselves easily to VLSI implementations. The connections between these processors are determined by a cIoning template, which describes the strength of nearest-neighbour interconnections. The cloning templates are spaceinvariant, meaning that a11 the processors have the same relative connections. In this paper first we describe the architecture of CNN. Next, a new application of CNN using them for the 3D scene analysis is studied. .
Study of Image Recognition Using Cellular Associated Artificial Neural Networks
—The non textual image recognition is one of the important aspects of the multimedia. The image recognition is also termed as the computer vision and is used in the various areas and devices such as robotics. The ANN (Artificial Neural Networks) is one of the great tools involved in the image recognition. So far, the ANN were used in applications involving the computer vision. Although the artificial neural networks based systems are distinguished for their ability to cope with problems in pattern recognition and computer vision in general, they are rather impotent when faced with the dimensionality of problems in the image understanding domain. That makes them unable to deal sufficiently with problems such as rotation, distortion, clutter and scale variances. In this paper, we are going to deal the image recognition with the technology known as the CANN (Cellular Associative Neural Networks).The main thing which makes the difference between the traditional neural networks and the CANN is the architecture, which resembles the cellular automata. It is used in the interconnection between the various networks. We are going to have a look at the CANN technology, with the learning process and the recognition of images and the process of analysis of one dimensional and two dimensional images.
Study of Image Recognition Using Cellular Associated Artificial Neural Networks.pdf
—The non textual image recognition is one of the important aspects of the multimedia. The image recognition is also termed as the computer vision and is used in the various areas and devices such as robotics. The ANN (Artificial Neural Networks) is one of the great tools involved in the image recognition. So far, the ANN were used in applications involving the computer vision. Although the artificial neural networks based systems are distinguished for their ability to cope with problems in pattern recognition and computer vision in general, they are rather impotent when faced with the dimensionality of problems in the image understanding domain. That makes them unable to deal sufficiently with problems such as rotation, distortion, clutter and scale variances. In this paper, we are going to deal the image recognition with the technology known as the CANN (Cellular Associative Neural Networks).The main thing which makes the difference between the traditional neural networks and the CANN is the architecture, which resembles the cellular automata. It is used in the interconnection between the various networks. We are going to have a look at the CANN technology, with the learning process and the recognition of images and the process of analysis of one dimensional and two dimensional images.
Cellular neural networks: Implementation of a segmentation algorithm on a Bio-inspired hardware processor
2012 IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS), 2012
The Cellular Neural/Nonlinear Network (CNN) paradigm has recently led to a Bio-inspired (Bi-i) Cellular Vision system, which represents a computing platform consisting of sensing, array sensing-processing and digital signal processing. This paper illustrates the implementation of a novel CNN-based segmentation algorithm onto the Bi-i system. The experimental results, carried out for a benchmark video sequence, show the feasibility of the approach, which provides a frame rate of about 26 frame/sec. Finally, comparisons with existing CNN-based methods highlight that the proposed implementation represents a good trade-off between real-time requirements and accuracy.
Theory and Application of Cellular Automata For Pattern Classification
Fundamenta Informaticae, 2003
This paper presents the theory and application of a high speed, low cost pattern classifier. The proposed classifier is built around a special class of sparse network referred to as Cellular Automata (CA). A specific class of CA, termed as Multiple Attractor Cellular Automata (MACA), has been evolved through Genetic Algorithm (GA) formulation to perform the task of pattern classification. The versatility of the classification scheme is illustrated through its application in three diverse fields -data mining, image compression, and fault diagnosis. Extensive experimental results demonstrate better performance of the proposed scheme over popular classification algorithms in respect of memory overhead and retrieval time with comparable classification accuracy. Hardware architecture of the proposed classifier has been also reported.
Cellular Automata Algorithms for Digital Image Processing
Intelligent Analysis of Multimedia Information, 2000
In this paper are presented solutions to develop algorithms for digital image processing focusing particularly on edge detection. Edge detection is one of the most important phases used in computer vision and image processing applications and also in human image understanding. In this chapter, implementation of classical edge detection algorithms it is presented and also implementation of algorithms based on the theory of Cellular Automata (CA). This work is totally related to the idea of understanding the impact of the inherently local information processing of CA on their ability to perform a managed computation at the global level. If a suitable encoding of a digital image is used, in some cases, it is possible to achieve better results in comparison with the solutions obtained by means of conventional approaches. The software application which is able to process images in order to detect edges using both conventional algorithms and CA based ones is written in C# programming language and experimental results are presented for images with different sizes and backgrounds.
Evolving Cellular Automata Based Associative Memory for Pattern Recognition
2001
This paper reports a Cellular Automata (CA )model for pattern recognition.The special class of CA referred to as GMACA (Generalized Multiple Attractor Cellular Automata ),is employed to design the CA based associative memory for pattern recognition.The desired GMACA are evolved through the implementation of genetic algorithm (GA).An efficient scheme to ensure fast convergence of GA is also reported.Experimental results conform the fact that the GMACA based pattern recognizer is more powerful than the Hopfield network for memorizing arbitrary patterns.
VLSI Implementation of Cellular Neural Networks
The cellular neural nerwork (CNN) presented here is an example of very large scale analog processing or collective analog computation. The CNN architecture combines some features of fully connected analog neural networks [1,2,3] with the nearest neighbor interactions found in cellular automata [4,5,6]. A companion paper in this
Related papers
Cellular Automata for Pattern Recognition
Emerging Applications of Cellular Automata, 2013
Cellular Automata Machine for Pattern Recognition
Cellular Automata, 2002
This paper reports the design of a Cellular Automata Machine (CAM) to ad-dress the problem of Pattern Recognition. The design is based on an elegant computing model of a particular class of Cellular Automata (CA) referred to as Generalized Multiple Attractor CA (GMACA). The ...
Design of associative memories using cellular neural networks
Neurocomputing, 2009
Cellular neural networks (CNNs) have locally connected neurons. This characteristic makes CNNs adequate for hardware implementation and, consequently, for their employment on a variety of applications as real-time image processing and construction of efficient associative memories. Adjustments of CNN parameters is a complex problem involved in the configuration of CNN for associative memories. This paper reviews methods of associative memory design based on CNNs, and provides comparative performance analysis of these approaches.
Cellular automata in pattern recognition
Information Sciences, 1993
This paper is a review of recent published work in the application of automata networks as part of a pattern or image recognition system. The principal requirements were to integrate model-based and data-driven approaches within a connectionist framework and to allow full parallelism. In particular, we construct a network of probabilistic cellular automata (PCAs) for iteratively resolving ambiguities and conflicts in pattern recognition. A natural implementation of inductive inference rules in such a network results in a d~amics that is sensitive to nons~metric couplings (s~aptic weights), unlike that of the more common models inspired by statistical physics (e.g., the Boltzmann machine). This, along with full parallelism, means that object recognition must be achieved through the intermediate-time rather than "infinite''-time behavior of the system. Another, more technology-driven, feature includes using local inferences insofar as possible. The framework is translation-invariant, which is natural for image re~gnition. This leads to a different architecture for describing the model from that used in Bayesian inference networks. ' We discuss only bilinear couplings here. Inference rules are often in the form, for example, that feature Q occurs only in conjunction with both features y and 6 in appropriate positions. The most direct way lo incorporate that these would be with trilinear and higher order couplings. An alternative would bc to have hidden units but keep the couplings bilinear (see [281X
Spiking Cellular Associative Neural Networks for Pattern Recognition
2008
The Cellular Associative Neural Network (CANN) is a novel symbolic pattern matching system, currently used for both the identification of objects in noisy images and for graph similarity searching of chemical structures. Objects are defined by a set of symbolic rules, which iteratively combine low level features into higher level constructs, until object level definitions can be obtained. The flow of information follows a cellular automata based model to aid parallel implementation and rules are stored in AURA associative memories, which provide efficient storage, fast retrieval and the ability to identify partially matching rules in constant time.
Design and Characterization of Cellular Automata Based Associative Memory for Pattern Recognition
IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 2004
This paper reports a cellular automata (CA) based model of associative memory. The model has been evolved around a special class of CA referred to as generalized multiple attractor cellular automata (GMACA). The GMACA based associative memory is designed to address the problem of pattern recognition. Its storage capacity is found to be better than that of Hopfield network. The GMACA are configured with nonlinear CA rules that are evolved through genetic algorithm (GA). Successive generations of GA select the rules at the edge of chaos [1], [2]. The study confirms the potential of GMACA to perform complex computations like pattern recognition at the edge of chaos.
Object Recognition in Image Sequences with Cellular Neural Networks
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 are used for a classification step in an object recognition system. Therefore, the feature vectors of an object set are learnt and recalled by an associative memory based on the paradigm of Cellular Neural Networks, CNN.
Cellular Automata as a Tool for Image Processing
Series in Computer Vision, 2011
An overview is given on the use of cellular automata for image processing. We first consider the number of patterns that can exist in a neighbourhood, allowing for invariance to certain transformation. These patterns correspond to possible rules, and several schemes are described for automatically learning an appropriate rule set from training data. Two alternative schemes are given for coping with gray level (rather than binary) images without incurring a huge explosion in the number of possible rules. Finally, examples are provided of training various types of cellular automata with various rule identification schemes to perform several image processing tasks.
Image processing using 3-state cellular automata
Computer Vision and Image Understanding, 2010
This paper describes the application of cellular automata (CA) to various image processing tasks such as denoising and feature detection. Whereas our previous work mainly dealt with binary images, the current work operates on intensity images. The increased number of cell states (i.e. pixel intensities) leads to a vast increase in the number of possible rules. Therefore, a reduced intensity representation is used, leading to a three state CA that is more practical. In addition, a modified sequential floating forward search mechanism is developed in order to speed up the selection of good rule sets in the CA training stage. Results are compared with our previous method based on threshold decomposition, and are found to be generally superior. The results demonstrate that the CA is capable of being trained to perform many different tasks, and that the quality of these results is in many cases comparable or better than established specialised algorithms.
Associative cellular learning automata and its applications
Cellular learning automata (CLA) is a distributed computational model which was introduced in the last decade. This model combines the computational power of the cellular automata with the learning power of the learning automata. Cellular learning automata is composed from a lattice of cells working together to accomplish their computational task; in which each cell is equipped with some learning automata. Wide range of applications utilizes CLA such as image processing, wireless networks, evolutionary computation and cellular networks. However, the only input to this model is a reinforcement signal and so it cannot receive another input such as the state of the environment. In this paper, we introduce a new model of CLA such that each cell receives extra information from the environment in addition to the reinforcement signal. The ability of getting an extra input from the environment increases the computational power and flexibility of the model. We have designed some new algorithms for solving famous problems in pattern recognition and machine learning such as classification, clustering and image segmentation. All of them are based on the proposed CLA. We investigated performance of these algorithms through several computer simulations. Results of the new clustering algorithm shows acceptable performance on various data sets. CLA-based classification algorithm gets average precision 84% on eight data sets in comparison with SVM, KNN and Naive Bayes with average precision 88%, 84% and 75%, respectively. Similar results are obtained for semi-supervised classification based on the proposed CLA.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.