Abstract
In this paper a method for response integration of Modular Neural Networks, based on Choquet Integral applied to face recognition is presented. Type-1 and Type-2 fuzzy systems for edge detections based on the Sobel, which is a pre-processing applied to the training data for better performance in the modular neural network. The Choquet integral is an aggregation operator that in this case is used as a method to integrate the outputs of the modules of the modular neural networks (MNN).
Access provided by Autonomous University of Puebla. Download chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
1 Introduction
A mechanism which takes as input a number n of data and combines them to result in a representative value of the information is called integration method. In the literature there exist methods which combine information from different sources. In a MNN it is common to use different methods for integrate the information, such as Type-1 and Type-2 fuzzy logic for Multimodal Biometrics [3], for Human Recognition Based on Iris, Ear and Voice Biometrics [16], for Pattern Recognition [17], the fuzzy Sugeno integral for Pattern Recognition of human face and fingerprint [10], Interval Type-2 Fuzzy Logic Sugeno Integral for Face Recognition [11], a probabilistic sum integrator in Classification using Redundant Mapping [9], a novel Bayesian learning method for information aggregation in modular neural networks [23], Self-Organizing Maps for Japanese Historical Character Recognition [4], Choquet Integral in a modular neural network [8], among others.
The Choquet integral was created by the French mathematician Gustave Choquet in 1953 [2]. The Choquet integral with respect to a fuzzy measure is a very popular data aggregation approach. The generalized Choquet integral with respect to a signed fuzzy measure can act as an aggregation tool, which is especially useful in many applications [6, 21, 24].
This paper is organized as follows: Sect. 2 shows the technique that is applied for the combination of the several information sources: the concepts of Fuzzy Measures and Choquet integral. Section 3 presents Edge detection based on Sobel with type-1 and type-2 fuzzy systems. Section 4 describes the architecture of the modular neural network proposed and in the Sect. 5 the simulation results are shown. And finally in Sect. 6 the Conclusions are presented.
2 Fuzzy Measures and Choquet Integral
In 1974 the concepts of “fuzzy measure and fuzzy integral” were defined by Sugeno [20] in order to define sets that do not have well-defined boundaries. A fuzzy measure is a nonnegative function monotone of values defined in “classical sets”. Currently, when referring to this topic, the term “fuzzy measures” has been replaced by the term “monotonic measures”, “non-additive measures” or “generalized measures” [14, 18, 22]. When fuzzy measures are defined on fuzzy sets, we speak of fuzzified monotonic measures [22].
2.1 Fuzzy Measures
A fuzzy measure can be defined as a fuzzy measure μ with respect to the dataset X, and must satisfy the following conditions:
-
1.
\( \mu \left( X \right) = 1;\;\mu ({\O} ) = 0 \; {\text{Boundary conditions}} \)
-
2.
\( Si \, A \subset B, \, then\;\mu \left( A \right) \le \left( B \right) \; {\text{Monotonicity}} \)
In condition two, A and B are subsets of X.
A fuzzy measure is a Sugeno measure or λ-fuzzy, if it satisfies the condition (1) of addition for some λ > −1.
where λ can be calculated with (2):
The value of the parameter λ is determined by the conditions of Theorem 1.
Theorem 1
Let \( \mu \left( {\left\{ x \right\}} \right) < 1 \) for each x ∈ X and let \( \mu \left( {\left\{ x \right\}} \right) > 0 \) for at least two elements of X, then (2) determines a unique parameter in the following way:
The fuzzy measure represents the importance or relevance of the information sources when computing the aggregation. The method to calculate Sugeno measures, carries out the calculation in a recursive way, using (3) and (4).
where \( A_{i} \) represents the fuzzy measure and \( M_{i} \) represents the fuzzy density determined by an expert, where \( 1 < M_{i} \le \cdots \le {\text{n}} \), should be permuted with respect to the descending order of their respective μ(A i ).
In the literature there are 2 types of Integral, the integral of Sugeno and the Choquet Integral.
2.2 Choquet Integral
The Choquet integral can be calculated using Eq. (5) or an equivalent expression (6)
Or also
In this case A i represents the fuzzy measurement associated with a data D i .
3 Edge Detection
Edge detection can be defined as a method consisting of identifying changes that exist in the light intensity, which can be used to determine certain properties or characteristics of the objects in the image. A number of edge detectors have been developed by various researchers. Amongst them, the most important operators are the Sobel Operator [19], Prewitt operator [15], Robert operator [15], Canny operator [1] and Kirsch operator [5]. The resultant images of the edge detectors preserve more details of the original images, which is a desirable feature for a pattern recognition system.
We used the Cropped Yale database to perform the training of the modular neural network, which has images of 38 people with 60 samples of each individual. To each of the images we applied a pre-processing by making use of Sobel edge detector with type-1 and type-2 fuzzy logic systems [7] in order to highlight features, some of the images can be displayed in Fig. 4a. Each image of the Cropped Yale database has a size of 168 × 192.
3.1 Sobel
The Sobel operator is applied to a digital image in gray scale, is a pair of 3 × 3 convolution masks, one estimating the gradient in the x-direction (columns) (7) and the other estimating the gradient in the y-direction (rows) (8) [12].
If we have Im,n as a matrix of m rows and r columns, where the original image is stored, then gx and gy are matrices having the same dimensions as I, which at each element contains the horizontal and vertical derivative approximations and are calculated by (9) and (10) [12].
In the Sobel method the gradient magnitude g is calculated by (11).
For the type-1 and type-2 fuzzy inference systems, 3 inputs can be used as can seen in Figs. 1 and 2, two of them are the gradients with respect to the x-axis and y-axis, calculated with (9) and (10), which we call DH and DV, respectively. The third variable M is the image after the application of a low-pass filter hMF in (12); this filter allows to detect image pixels belonging to regions of the input where the mean gray level is lower. These regions are proportionally affected more by noise, which is supposed to be uniformly distributed over the whole image [12].
After applying the edge detector of Type-1 with Sobel, the resulting image can be viewed in Fig. 3b.
The rules used for the tests in the Type-1 and Type-2 Sobel edge detectors are [12]:
-
1.
If (dh is LOW) and (dv is LOW) then (y1 is HIGH).
-
2.
If (dh is MIDDLE) and (dv is MIDDLE) then (y1 is LOW).
-
3.
If (dh is HIGH) and (dv is HIGH) then (y1 is LOW).
-
4.
If (dh is MIDDLE) and (hp is LOW) then (y1 is LOW).
-
5.
If (dv is MIDDLE) and (hp is LOW) then (y1 is LOW).
-
6.
If (m is LOW) and (dv is MIDDLE) then (y1 is HIGH).
-
7.
If (m is LOW) and (dh is MIDDLE) then (y1 is HIGH).
The images generated by the Type-2 Sobel edge detector are shown in Fig. 3c.
4 Modular Neural Networks
To each image of the Cropped Yale database we applied a preprocessing with the Type-1 and Type-2 Sobel edge detector, after this, each image is divided into 3 sections horizontal. Each section was used as training data in each one of the three modules of the modular neural network, as shown in Fig. 4. The integration of the simulation of each module is made with the Choquet integral.
The Training Parameters are:
Training method: gradient descendent with momentum and adaptive learning rate back-propagation (Traingdx).
Each module has two hidden layers [200 200].
Error goal: 0.0001
Epochs: 500
In Table 1 the distribution of the training data is shown.
4.1 The Experiment with a Modular Neural Network Recognition System and the Choquet Integral for the Modules Fusion
The experiment consist on applying each evaluated edge detector to obtain a data set of same well know benchmark data bases of images, like Cropped Yale database of faces and then train a neural network to compare the recognition rate using the k-fold cross-validation method [13].
5 Simulation Results
In the experiments we performed 27 tests in simulation of the trainings with each edge detectors making variations in the fuzzy densities with the values of 0.1, 0.5 and 0.9 and performing the calculation of the parameter λ with the bisection method, and these parameters can be find in Table 2.
In Table 3, the results obtained using preprocessing of the image, with the type-1 Sobel edge detector, are shown. The first column represents the number of tests performed for each simulation, of the column M1 to M5 the average obtained in each module for each training is displayed and finally the last three columns present the mean of the five trainings, the standard deviation and the maximum of each simulation.
In Table 4 we show the percentages of recognition of the Modular neural network using the Choquet integral as integration method with a preprocessing in the images with the Type 1 Sobel edge detector. Each result of the tests is the average of 27 simulations with different fuzzy densities, as seen in Table 3.
In Table 5 we can find the results of the simulations using the Type-2 Sobel edge detector as preprocessing method.
It can be noted that when using the Type-2 Sobel edge detector it was obtained 98.49 % of recognition whereas with type-2 Sobel edge detector a 98.68 % was obtained.
6 Conclusions
The use of the Choquet integral as an integration method of responses of a modular neural network applied to face recognition has yielded favorable results when performing the aggregation process of the preprocessed images with the detectors of Sobel edges. The resultant images of the edge detectors preserve more details of the original images, which is a desirable feature for a pattern recognition system. However it is still necessary to use a method that optimizes the values of the Sugeno measure assigned to each source of information because these were designated arbitrarily.
References
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(2), 679–698 (1986)
Choquet, G.: Theory of capacities. Ann. Inst. Fourier, Grenoble 5, 131–295 (1953). doi:10.5802/aif.53
Hidalgo, D.: Fuzzy inference systems type 1 and type 2 as integration methods in neural networks for multimodal biometrics and Me-optimization by means of genetic algorithms. Master Thesis, Tijuana Institute of Technology (2008)
Horiuchi, T., Kato, S.: A study on Japanese historical character recognition using modular neural networks. In: IEEE Fourth International Conference on Innovative Computing, Information and Control, pp. 1507–1510 (2009)
Kirsch, R.: Computer determination of the constituent structure of biological images. Comput. Biomed. Res. 4, 315–328 (1971)
Kwak, K.C., Pedrycz, W.: Face recognition: a study in information fusion using fuzzy integral. Pattern Recogn. Lett. 26, 719–733 (2005)
Liu, H.C., Wu D.B., Jheng Y.D., Chen, C.C., Chien, M.F., Sheu, T.W.: Choquet integral with respect to sigma-fuzzy measure. In: International Conference on Mechatronics and Automation, Changchun, China 978-1-4244-2693-5/09. IEEE (2009)
Martínez, G.E., Melin, P., Olivia, M.D., Castillo, O.: Face recognition with Choquet integral in modular neural networks. In: Recent Advances on Hybrid Approaches for Designing Intelligent Systems. Springer International Publishing, Switzerland (2014). doi:10.1007/978-3-319-05170-3_30
Meena, Y.K., Arya, K.V., Kala, R.: Classification using redundant mapping in modular neural networks. In: Second World Congress on Nature and Biologically Inspired Computing, Kitakyushu, Fukuoka, Japan, 15–17 Dec 2010
Melin, P., Gonzalez, C., Bravo, D., Gonzalez, F., Martínez, G.: Modular neural networks and fuzzy Sugeno integral for pattern recognition: the case of human face and fingerprint. In: Hybrid Intelligent Systems: Design and Analysis. Springer, Heidelberg (2007)
Melin, P., Mendoza, O., Castillo O.: Face recognition with an improved interval type-2 fuzzy logic Sugeno integral and modular neural networks. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 41(5) (2011)
Mendoza, O., Melin, P., Castillo, O., Castro, J.: Comparison of fuzzy edge detectors based on the image recognition rate as performance index calculated with neural networks. In: Soft Computing for Recognition Based on Biometrics. Studies in Computational Intelligence, vol. 312, pp. 389–399 (2010)
Mendoza, O., Melin, P.: Quantitative evaluation of fuzzy edge detectors applied to neural networks or image recognition. In: Advances in Research and Developments in Digital Systems, pp. 324–335 (2011)
Murofushi, T., Sugeno, M.: Fuzzy measures and fuzzy integrals. Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan (2000)
Prewitt, J.M.S.: Object enhancement and extraction. In: Lipkin, B.S., Rosenfeld, A. (eds.) Picture Analysis and Psychopictorics, pp. 75–149. Academic Press, New York (1970)
Sánchez, D., Melin, P.: Modular neural network with fuzzy integration and its optimization using genetic algorithms for human recognition based on iris, ear and voice biometrics. In: Soft Computing for Recognition Based on Biometrics, pp. 85–102 (2010)
Sánchez, D., Melin, P., Castillo, O., Valdez, F.: Modular neural networks optimization with hierarchical genetic algorithms with fuzzy response integration for pattern recognition. MICAI, pp. 247–258 (2012)
Song, J., Li, J.: Lebesgue theorems in non-additive measure theory. Fuzzy Sets Syst. 149(3), 543–548 (2005)
Sobel, I.: Camera models and perception. Ph.D. Thesis, Stanford University, Stanford, CA (1970)
Sugeno, M.: Theory of fuzzy integrals and its applications. Thesis Doctoral, Tokyo Institute of Technology, Tokyo, Japan (1974)
Timonin, M.: Robust optimization of the Choquet integral. Fuzzy Sets Syst. 213, 27–46 (2013)
Wang, Z., Klir, G.: Generalized measure Theory. Springer, New York (2009)
Wanga, P., Xua, L., Zhou, S.M., Fan, Z., Li, Y., Feng, S.: A novel Bayesian learning method for information aggregation in modular neural networks. In: Expert Systems with Applications, vol. 37, pp. 1071–1074. Elsevier, New York (2010)
Yanga, W., Chen, Z.: New aggregation operators based on the Choquet integral and 2-tuple linguistic information. Expert Syst. Appl. 39, 2662–2668 (2012)
Acknowledgment
We thank the MyDCI program of the Division of Graduate Studies and Research, UABC, Tijuana Institute of Technology, and the financial support provided by our sponsor CONACYT contract grant number: 189350.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Martínez, G.E., Melin, P., Mendoza, O.D., Castillo, O. (2015). Face Recognition with a Sobel Edge Detector and the Choquet Integral as Integration Method in a Modular Neural Networks. In: Melin, P., Castillo, O., Kacprzyk, J. (eds) Design of Intelligent Systems Based on Fuzzy Logic, Neural Networks and Nature-Inspired Optimization. Studies in Computational Intelligence, vol 601. Springer, Cham. https://doi.org/10.1007/978-3-319-17747-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-17747-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-17746-5
Online ISBN: 978-3-319-17747-2
eBook Packages: EngineeringEngineering (R0)