Abstract
Convolutional Neural Network models represent a powerful tool that can be applied in image classification tasks. Convolutional Neural Networks have a wide variety of parameters and these can produce different results for the same tasks depending on the particular parameter settings. This paper presents an improved Convolutional Neural Networks model based on changing the number of layers and convolution filters weights with the aim of analyzing the impact in the image classification and recognition systems. The Handwritten digits (MNIST), the American Sign Language (ASL MNIST) and, the Mexican Sign Language (MSL) databases were selected to perform this study. The proposed approach achieved greater precision than the accuracy obtained without varying the parameters; therefore, the modification of the parameters in the convolution layer represents a significant impact on the results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Albawi, S., T. Mohammed, and S. Al-Zawi. 2017. Understanding of a convolutional neural network. In International Conference on Engineering and Technology (ICET).
Bantupalli, k., and Y. Xie. 2018. American sign language recognition using deep learning and computer vision. 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, 2018, pp. 4896–4899. https://doi.org/10.1109/bigdata.2018.8622141.
Bin, L.Y., G.Y. Huann, and L.K. Yun. 2019. Study of convolutional neural network in recognizing static american sign language. In 2019 IEEE international conference on signal and image processing applications (ICSIPA), pp. 41–45.
Castillo, O., and P. Melin. 1998. A new fuzzy-fractal-genetic method for automated mathematical modelling and simulation of robotic dynamic systems. 1998 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 1998) Proceedings. Volume 2, 1182–1187.
Castillo, O., and P. Melin. 2003. Intelligent adaptive model-based control of robotic dynamic systems with a hybrid fuzzy-neural approach. Applied Soft Computing 3 (4): 363–378.
El-Sayed, A., A.Y. Estaitia, and M. Khafagy. 1998. Automated edge detection using convolutional neural network. In International Journal of Advanced Computer Science and Applications, vol. 86, issue 11.
Gonzalez, C.I., P. Melin, J. Castro, and O. Castillo. 2017a. Edge detection methods based on generalized type-2 fuzzy logic. In SpringerBriefs in Applied Sciences and Technology.
Gonzalez, C.I., P. Melin, J.R. Castro, and O. Castillo. 2017b. Edge detection methods and filters used on digital image processing. Edge Detection Methods Based on Generalized Type-2 Fuzzy Logic, Published by Springer, pp. 11–16.
Gonzalez, C., P. Melin, J. Castro, O. Mendoza, and O. Castillo. General type-2 fuzzy edge detection in the preprocessing of a face recognition system. In Applied soft computing, vol. 9, issue 4, pp. 3–18.
Gulli, A., and S. Pal. 2017. Deep Learning with Keras, Published by Packt Publishing Ltd.
Heaton, I., J.I. Goodfellow, Y. Bengio, and A. Courville. 2017. Deep learning. Genetic Programming and Evolvable Machines, 19(1–2): 305–307.
INEGI, “Discapacidad”, Inegi.org.mx, 2020. [Online]. Available: https://www.inegi.org.mx/temas/discapacidad/. Accessed 03 Aug 2020.
Kim, P. 2017. MATLAB deep learning: With machine learning. Seoul, Korea: Neural Networks and Artificial Intelligence. Apress.
Krizhevsky, A., I. Sutskever, and G. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM 60 (6): 84–90.
Kokkinos, I., E.C. Paris, and G. Group, Introduction to deep learning convolutional networks. Dropout, Maxout 1, pp. 1–70.
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998a. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86: 2278–2324.
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998b. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86 (11): 2278–2324.
Mendoza, O., P. Melín, and O. Castillo. 2009. Interval type-2 fuzzy logic and modular neural networks for face recognition applications. Applied Soft Computing 9 (4): 1377–1387.
Ozbulak, G., and H. Ekenel. 2018. Initialization of convolutional neural networks by Gabor filters. In 2018 26th Signal Processing and Communications Applications Conference (SIU).
Poma, Y., P. Melin, C. González, and G.E. Martinez. 2020a. Optimal recognition model based on convolutional neural networks and fuzzy gravitational search algorithm method. Hybrid intelligent systems in control, pattern recognition and medicine 2020, vol. 827, pp. 71–81.
Poma, Y., P. Melin, C.I. González, and G.E. Martinez. 2020b. Filter size optimization on a convolutional neural network using FGSA. Intuitionistic and Type-2 Fuzzy Logic Enhancements in Neural and Optimization Algorithms 2020, pp. 391–403.
Poma, Y., P.Melin, C.I. González, and G.E. Martinez. 2020c. Optimization of convolutional neural networks using the fuzzy gravitational search algorithm. Journal of Automation, Mobile Robotics & Intelligent Systems 14(1).
Prewitt, J.M.S. 1970. Object enhancement and extraction. In Picture analysis and psychopictorics, ed. B.S. Lipkin and A. Rosenfeld, 75–149. New York, NY: Academic Press.
Rathi, D. 2018. Optimization of transfer learning for sign language recognition targeting mobile platform. International Journal on Recent and Innovation Trends in Computing and Communication, 6.
Sánchez, D., P. Melin, J. Carpio, and H. Puga. 2017. Comparison of optimization techniques for modular neural networks applied to human recognition. In Nature-inspired design of hybrid intelligent systems, pp. 225–241. Springer, Cham.
Sánchez, D., and P. Melin. 2014. Optimization of modular granular neural networks using hierarchical genetic algorithms for human recognition using the ear biometric measure. Engineering Applications of Artificial Intelligence 27: 41–56.
Sanchez, M.A., O. Castillo, J.R. Castro, and P. Melin. 2014. Fuzzy granular gravitational clustering algorithm for multivariate data. Information Sciences 279: 498–511.
Sánchez, D., P. Melin, and O. Castillo. 2017b. Optimization of modular granular neural networks using a firefly algorithm for human recognition. Engineering Applications of Artificial Intelligence 64: 172–186.
Sandve, G.K., A. Nekrutenko, J. Taylor, and E. Hovig. 2013. Ten simple rules for reproducible computational research. PLoS Comput Biol 9(10).
Sinha, T., B. Verma, & A. Haidar. 2017. Optimization of convolutional neural network parameters for image classification. In IEEE Symposium Series on Computational Intelligence (SSCI).
Sobel, I. 1970. Camera models and perception. Ph.D. thesis, Stanford University, Stanford, CA.
Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going deeper with convolutions. In The IEEE conference on computer vision and pattern recognition (CVPR), pp. 1–9.
Wang, X. 2007. Laplacian operator-based edge detectors. IEEE Transactions on Pattern Analysis and Machine Intelligence 29 (5): 886–890.
Xie, B., X. He, and Y. Li. 2018. GB-D static gesture recognition based on convolutional neural network. The Journal of Engineering 2018(16): 1515–1520. https://doi.org/10.1049/joe.2018.8327.
Xu, X., H. Ge, and S. Li. 2016. An improvement on recurrent neural network by combining convolution neural network and a simple initialization of the weights. 2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS), Chongqing, pp. 150–154. https://doi.org/10.1109/ICOACS.2016.7563068.
Zhao, Y., and L. Wang. 2018. The application of convolution neural networks in sign language recognition. 2018 ninth international conference on intelligent control and information processing (ICICIP), Wanzhou, pp. 269–272, https://doi.org/10.1109/icicip.2018.8606707.
Acknowledgements
We thank the Tijuana Institute of Technology, and the financial support provided by our sponsor CONACYT contract grant number: 701173.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Rodriguez, R., Gonzalez, C.I., Martinez, G.E., Melin, P. (2021). An Improved Convolutional Neural Network Based on a Parameter Modification of the Convolution Layer. In: Castillo, O., Melin, P. (eds) Fuzzy Logic Hybrid Extensions of Neural and Optimization Algorithms: Theory and Applications. Studies in Computational Intelligence, vol 940. Springer, Cham. https://doi.org/10.1007/978-3-030-68776-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-68776-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68775-5
Online ISBN: 978-3-030-68776-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)