International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

An Improved Method of Clothing Image Classification Based on CNN


Affiliations
1 College of Computer and Communication, Hunan Institute of Engineering, China
 

In recent years, with the increasing demand for high-precision clothing image classification, people has attached great importance on the clothing image classification method based on CNN. In this paper, we discussed how to improve the accuracy of image classification by preprocessing the data set, combining the data set with CNN structure and improving the loss function. The comparative experiments between different structures of CNN and loss functions have been done. The experimental results show that the method we used can better improve the effect of classification and classification accuracy.

Keywords

CNN, Image classification, Image feature, Loss function
User
Notifications
Font Size

  • Harris C G, Stephens M. A combined corner and edge detector[C]//Alvey vision conference. 1988, 15(50): 10-5244.

  • Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, 60(2): 91-110.

  • Bay H, Ess A, Tuytelaars T, et al. Speeded-up robust features (SURF)[J]. Computer vision and image understanding, 2008, 110(3): 346-359.

  • Rublee E, Rabaud V, Konolige K, et al. ORB: An efficient alternative to SIFT or SURF[C]//2011 International conference on computer vision. Ieee, 2011: 2564-2571.

  • Chen L L, Han R P, Meng Q C. Clothing image feature extraction based on SURF[C]//IOP Conference Series: Materials Science and Engineering. IOP Publishing, 2018, 439(3): 032104.

  • ZHANG Yong, WU Yujian. Improved SIFT image feature matching algorithm. Computer Engineering and Applications, 2014, 50（9）：167-169.

  • LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

  • Zhou W, Shao Z, Diao C, et al. High-resolution remote-sensing imagery retrieval using sparse features by auto-encoder[J]. Remote Sensing Letters, 2015, 6(10):775-783.

  • Pan R, Gao W, Liu J, et al. Automatic recognition of woven fabric pattern based on image processing and BP neural network[J]. The Journal of the Textile Institute, 2011, 102(1): 19-30.

  • Razavian A S，Azizpour H，Sullivan J，et al.CNN features off-the-shelf：An astounding baseline for recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops，2014：512-519.

  • Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.

  • Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-resnet and the impact of residual connections on learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2017, 31(1).

  • Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.

  • Prakash K, Saravanamoorthi P, Sathishkumar R, et al. A study of image processing in agriculture[J]. International Journal of Advanced Networking and Applications, 2017, 9(1): 3311.

  • Qureshi I. Glaucoma detection in retinal images using image processing techniques: a survey[J]. International Journal of Advanced Networking and Applications, 2015, 7(2): 2705.

  • Gnanambal S, Thangaraj M, Meenatchi V T, et al. Classification algorithms with attribute selection: an evaluation study using WEKA[J]. International Journal of Advanced Networking and Applications, 2018, 9(6): 3640-3644.


Abstract Views: 255

PDF Views: 1




  • An Improved Method of Clothing Image Classification Based on CNN

Abstract Views: 255  |  PDF Views: 1

Authors

Zhang Xuan-yu
College of Computer and Communication, Hunan Institute of Engineering, China
Deng Zuo-jie
College of Computer and Communication, Hunan Institute of Engineering, China

Abstract


In recent years, with the increasing demand for high-precision clothing image classification, people has attached great importance on the clothing image classification method based on CNN. In this paper, we discussed how to improve the accuracy of image classification by preprocessing the data set, combining the data set with CNN structure and improving the loss function. The comparative experiments between different structures of CNN and loss functions have been done. The experimental results show that the method we used can better improve the effect of classification and classification accuracy.

Keywords


CNN, Image classification, Image feature, Loss function

References