nach oben

2009 | Buch

Kapitel lesen Erstes Kapitel lesen

Bio-inspired Hybrid Intelligent Systems for Image Analysis and Pattern Recognition

herausgegeben von: Patricia Melin, Janusz Kacprzyk, Witold Pedrycz

Verlag: Springer Berlin Heidelberg

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

Bio-Inspired Hybrid Intelligent Systems for Image Analysis and Pattern Recognition comprises papers on diverse aspects of bio-inspired models, soft computing and hybrid intelligent systems.

The articles are divided into four main parts. The first one consists of papers that propose new fuzzy and bio-inspired models to solve general problems. The second part deals with the main theme of modular neural networks in pattern recognition, which are basically papers using bio-inspired techniques. The third part contains papers that apply hybrid intelligent systems to the problem of time series analysis and prediction, while the fourth one shows papers dealing with bio-inspired models in optimization and robotics applications. An edited book in which both theoretical and application aspects are covered.

Inhaltsverzeichnis

Frontmatter

Introductory Concepts and Models

Frontmatter

A Survey of Applications of the Extensions of Fuzzy Sets to Image Processing

Abstract

In this chapter a revision of different image processing applications developed with different extensions of fuzzy sets is presented. The way extensions of fuzzy sets try to modelize some aspects of the uncertainty existing in different processes of image processing and how this extensions handle in a better way than fuzzy sets such uncertainty is explained.

Humberto Bustince, Miguel Pagola, Aranzazu Jurio, Edurne Barrenechea, Javier Fernández, Pedro Couto, Pedro Melo-Pinto

Interval Type-2 Fuzzy Cellular Model Applied to the Dynamics of a Uni-specific Population Induced by Environment Variations

Abstract

As part of the research about the applicability of the Fuzzy Cellular Models (FCM) to simulate complex dynamics ecological systems, this paper presents an Interval Type-2 Fuzzy Cellular Model (IT2-FCM) applied to the dynamics of a uni-specific population. In ecology is known that in the dynamics of all population, the reproduction, mortality and emigration rates are not constants, and its variability is induced by a combination of environment factors. All kind of populations that are living together in a determinate place, and the physical factors which they interact with, compose a community. Each population o physical factor inside has its own dynamics, which also presents uncertainty given by combined effects among other environment factors inside the same community. In our model this uncertainty is represented by interval type-2 fuzzy sets, with the goal of show whether the trajectories described by the dynamics of the population present a better stability in the time and space. The validation of the model was made within a comparative frame using the results of another research where a FCM were used to describe the dynamics of a population.

Cecilia Leal-Ramirez, Oscar Castillo, Antonio Rodriguez-Diaz

A Genetic Programming Approach to the Design of Interest Point Operators

Abstract

Recently, the detection of local image feature has become an indispensable process for many image analysis or computer vision systems. In this chapter, we discuss how Genetic Programming (GP), a form of evolutionary search, can be used to automatically synthesize image operators that detect such features on digital images. The experimental results we review, confirm that artificial evolution can produce solutions that outperform many man-made designs. Moreover, we argue that GP is able to discover, and reuse, small code fragments, or building blocks, that facilitate the synthesis of image operators for point detection. Another noteworthy result is that the GP did not produce operators that rely on the auto-correlation matrix, a mathematical concept that some have considered to be the most appropriate to solve the point detection task. Hence, the GP generates operators that are conceptually simple and can still achieve a high performance on standard tests.

Gustavo Olague, Leonardo Trujillo

Modular Neural Networks in Pattern Recognition

Frontmatter

Face, Fingerprint and Voice Recognition with Modular Neural Networks and Fuzzy Integration

Abstract

In this paper we describe a Modular Neural Network (MNN) with fuzzy integration for face, fingerprint and voice recognition. The proposed MNN architecture defined in this paper consists of three modules; face, fingerprint and voice. Each of the mentioned modules is divided again into three sub modules. The same information is used as input to train the sub modules. Once we have trained and tested the MNN modules, we proceed to integrate these modules with a fuzzy integrator. In this paper we demonstrate that using MNNs for face, fingerprint and voice recognition integrated with a fuzzy integrator is a good option to solve pattern recognition problems.

Ricardo Muñoz, Oscar Castillo, Patricia Melin

Modular Neural Networks with Fuzzy Response Integration for Signature Recognition

Abstract

This chapter describes a modular neural network (MNN) for the problem of signature recognition. Currently, biometric identification has gained a great deal of research interest within the pattern recognition community. For instance, many attempts have been made in order to automate the process of identifying a person’s handwritten signature, however this problem has proven to be a very difficult task. In this work, we propose a MNN that has three separate modules, each using different image features as input, these are: edges, wavelet coefficients, and the Hough transform matrix. Then, the outputs from each of these modules are combined using a Sugeno fuzzy integral. The experimental results obtained using a database of 30 individual’s shows that the modular architecture can achieve a very high 98% recognition accuracy with a test set of 150 images. Therefore, we conclude that the proposed architecture provides a suitable platform to build a signature recognition system.

Mónica Beltrán, Patricia Melin, Leonardo Trujillo

Intelligent Hybrid System for Person Identification Using Biometric Measures and Modular Neural Networks with Fuzzy Integration of Responses

Abstract

This paper presents an intelligent system for person identification with biometric measures such as signature, fingerprint and face. We describe the neural network architectures used to achieve person identification based on the biometrics measures. Simulation results show that the proposed method provides good recognition.

Magdalena Serrano, Erika Ayala, Patricia Melin

Optimization of Modular Neural Networks with Interval Type-2 Fuzzy Logic Integration Using an Evolutionary Method with Application to Multimodal Biometry

Abstract

In this paper we describe a new evolutionary method to perform the optimization of a modular neural network applied to the case of multimodal biometry. Integration of responses in the modular neural network is performed using type-1 and type-2 fuzzy inference systems.

The proposed evolutionary method produces the best architecture of the modular neural network.

Denisse Hidalgo, Patricia Melin, Guillermo Licea

Comparative Study of Fuzzy Methods for Response Integration in Ensemble Neural Networks for Pattern Recognition

Abstract

We describe in this paper a new method for response integration in ensemble neural networks with Type-1 Fuzzy Logic and Type-2 Fuzzy Logic using Genetic Algorithms (GA’s) for optimization. In this paper we consider pattern recognition with ensemble neural networks for the case of fingerprints to the test proposed method of response integration. An ensemble neural network of three modules is used. Each module is a local expert on person recognition based on their biometric measure (Pattern recognition for fingerprints). The Response Integration method of the ensemble neural networks has the goal of combining the responses of the modules to improve the recognition rate of the individual modules. First we use GA’s to optimize the fuzzy rules of The Type-1 Fuzzy System and Type-2 Fuzzy System to test the proposed method of response integration and after using GA’s to optimize the membership function of The Type-1 Fuzzy Logic and Type-2 Fuzzy logic to test the proposed method of response integration and finally show the comparison of the results between these methods. We show in this paper a comparative study of fuzzy methods for response integration and the optimization of the results of a type-2 approach for response integration that improves performance over the type-1 logic approaches.

Miguel Lopez, Patricia Melin, Oscar Castillo

Neural Network Models and Time Series Prediction

Frontmatter

Ensemble Neural Networks with Fuzzy Integration for Complex Time Series Prediction

Abstract

In this paper we describe the application of the architecture for an ensemble neural network for Complex Time Series Prediction. The time series we are considering is the Mackey-Glass, and we show the results of some simulations with the ensemble neural network, and its integration with the methods of average, weighted average and Fuzzy Integration. Simulation results show very good prediction of the ensemble neural network with fuzzy integration.

Martha Pulido, Alejandra Mancilla, Patricia Melin

Prediction of the MXNUSD Exchange Rate Using Hybrid IT2 FLS Forecaster

Abstract

This paper presents a novel application of the interval type-1 non-singleton type-2 fuzzy logic system (FLS) for one step ahead prediction of the daily exchange rate between Mexican Peso and US Dollar (MXNUSD) using the recursive least-squared (RLS)-back-propagation (BP) hybrid learning method. Experiments show that the exchange rate is predictable. A non-singleton type-1 FLS and an interval type-1 non-singleton type-2 FLS, both using only BP learning method, are used as a benchmarking systems to compare the results of the hybrid interval type-1 non-singleton type-2 FLS (RLS-BP) forecaster.

Gerardo M. Mendez, Angeles Hernandez

Discovering Universal Polynomial Cellular Neural Networks through Genetic Algorithms

Abstract

There are different benchmarks to test the capabilities of artificial neural networks. The Game of Life is an algorithm that has a very interesting mathematical characterization because can realize universal computing in the sense of a Turing machine. In this paper a new model of Polynomial Cellular Neural Networks that simulates a semi-totalistic automata is presented with the learning design to compute the templates. In this case, the rules of the semi-totalistic automata used, "play" the Game of Life. With the simulations presented we show that the PCNN can realize universal computing.

Eduardo Gomez-Ramirez, Enrique Haro Sedeño, Giovanni Egidio Pazienza

EMG Hand Burst Activity Detection Study Based on Hard and Soft Thresholding

Abstract

Electric signal analysis from live organism is an old area that was documented by Francesco Redi dated from 1666, Walsh 1773, and Galvani 1792 [1]. Contraction of muscular fibers by electric impulses was recorded by Debois-Raymmod 1849 [1]. Electric impulses known as myolectric signal and their recording are named electromyographic signals or EMG [2-8]. The first clinical use of EMG signals was reported in 1966 by Harddyck. It is not until the 1980´s that clinical methods to monitor EMG of several muscles were achieved [1].

Mario I. Chacon Murguia, Leonardo Valencia Olvera, Alfonso Delgado Reyes

Optimization and Robotics

Frontmatter

Modular Neural Networks Architecture Optimization with a New Evolutionary Method Using a Fuzzy Combination Particle Swarm Optimization and Genetic Algorithms

Abstract

We describe in this paper a new hybrid approach for optimization combining Particle Swarm Optimization (PSO) and Genetic Algorithms (GAs) using Fuzzy Logic to integrate the results. The new evolutionary method combines the advantages of PSO and GA to give us an improved FPSO+FGA hybrid method. Fuzzy Logic is used to combine the results of the PSO and GA in the best way possible. Also fuzzy logic is used to adjust parameters in the FPSO and FGA. The new hybrid FPSO+FGA approach is compared with the PSO and GA methods for the optimization of modular neural networks. The new hybrid FPSO+FGA method is shown to be superior with respect to both the individual evolutionary methods.

Fevrier Valdez, Patricia Melin, Guillermo Licea

A Multi-agent Architecture for Controlling Autonomous Mobile Robots Using Fuzzy Logic and Obstacle Avoidance with Computer Vision

Abstract

This paper describes the development of a Multi-Agent System (MAS), which is supported with fuzzy logic (to control the robots movements in a reactive path) and computer vision, which controls an autonomous mobile robot to exit a maze. The research consists of two stages. In the first stage the problem is to be able to make the robot exit a maze, the mobile robot is positioned at the entrance (point A) and should reach an output (B), it should be noted that we are working with a NXT robot to Lego MINDSTORMS ®. In its second phase the problem is to make the robot search for a recognized object, for this purpose a camera is used to capture images, which will be processed with vision techniques for identification, and after that, the SMA takes the decision to evade or take the object as appropriate.

Cinthya Solano-Aragón, Arnulfo Alanis

Particle Swarm Optimization Applied to the Design of Type-1 and Type-2 Fuzzy Controllers for an Autonomous Mobile Robot

Abstract

In this paper we describe the application of a Particle Swarm Optimization (PSO) algorithm as a method of optimization for membership functions’ parameters of a fuzzy logic controller (FLC) in order to find the optimal intelligent controller for an Autonomous Wheeled Mobile Robot. Simulations results show that PSO is able to optimize the tipe-1 and type-2 FLCs for this application.

Ricardo Martínez-Marroquín, Oscar Castillo, José Soria

Backmatter

Titel: Bio-inspired Hybrid Intelligent Systems for Image Analysis and Pattern Recognition
herausgegeben von: Patricia Melin
Janusz Kacprzyk
Witold Pedrycz
Verlag: Springer Berlin Heidelberg
Electronic ISBN: 978-3-642-04516-5
Print ISBN: 978-3-642-04515-8
DOI: https://doi.org/10.1007/978-3-642-04516-5