Abstract
Convolutional neural network (CNN) is a very popular deep learning structure. It has kinds of merits in the feature learning, such as local reception region, sharing weights, subsampling, etc. CNN can learn the image by pixel without previous feature extraction, and then discover some more characteristics of the input by the feature combination. In this paper, we study the effect of different combination rules in the CNN training. The simulation tests exhibit the different kinds of combination rules in the CNN learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rowley HA, Baluja S, Kanade T (1998) Neural network-based face detection. IEEE Trans Patt Anal Mach Intell 20(1):23–38
Feraud R, Bernier OJ, Viallet JE, Collobert M (2001) A fast and accurate face detector based on neural networks. IEEE Trans Pattern Anal Mach Intell 23(1):42–53
Jonsson K, Kittler J, Li YP, Matas J (2002) Support vector machines for face authentication. Image Vis Comput 20(5–6):369–375
Lawrence S, Giles CL, Tsoi AC, Back AD (1997) Face recognition: a convolutional neural network approach. IEEE Trans Neural Netw 8(1):98–113
LeCun Y, Jackel LD, Bottou LEO et al (1995) Learning algorithms for classification: a comparison on handwritten digit recognition. Neural Netw Stat Mech Perspect 261:276–291
Trinh H, Duranton M, Paindavoine M (2015) Efficient data encoding for convolutional neural network application. ACM Trans Archit Code Optim (TACO) 11(4):49(1–20)
Chen YN, Han CC, Wang CT et al (2010) A cnn-based face detector with a simple feature map and a coarse-to-fine classifier. IEEE Trans Pattern Anal Mach Intell 99:1–13
Huang L-L, Shimizu A, Kobatake H (2004) Classification-based face detection using Gabor filter features. In: Sixth IEEE international conference on automatic face and gesture recognition, pp 397–402
Acknowledgement
This work was supported in part by the National Natural Science Foundation of China under Grant No. 61174044, Natural Science Foundation of Shandong Province under Grant No. ZR2015PF009, and Independent Innovation Foundation of Shandong University under grant No. 2015ZQXM002.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xu, Q., Zhang, L. (2016). Different Feature Combination Rules in CNNs for Face Detection. In: Huang, B., Yao, Y. (eds) Proceedings of the 5th International Conference on Electrical Engineering and Automatic Control. Lecture Notes in Electrical Engineering, vol 367. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-48768-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-662-48768-6_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-48766-2
Online ISBN: 978-3-662-48768-6
eBook Packages: EngineeringEngineering (R0)