With the rapid development of the Internet of things and e-commerce, feature-based image retrieval and classification have become a serious challenge for shoppers searching websites for relevant product information. The last decade has witnessed great interest in research on content-based feature extraction techniques. Moreover, semantic attributes cannot fully express the rich image information. This paper designs and trains a deep convolutional neural network that the convolution kernel size and the order of network connection are based on the high efficiency of the filter capacity and coverage. To solve the problem of long training time and high resource share of deep convolutional neural network, this paper designed a shallow convolutional neural network to achieve the similar classification accuracy. The deep and shallow convolutional neural networks have data pre-processing, feature extraction and softmax classification. To evaluate the classification performance of the network, experiments were conducted using a public database Caltech256 and a homemade product image database containing 15 species of garment and 5 species of shoes on a total of 20,000 color images from shopping websites. Compared with the classification accuracy of combining content-based feature extraction techniques with traditional support vector machine techniques from 76.3% to 86.2%, the deep convolutional neural network obtains an impressive state-of-the-art classification accuracy of 92.1%, and the shallow convolutional neural network reached a classification accuracy of 90.6%. Moreover, the proposed convolutional neural networks can be integrated and implemented in other colour image database.
References
[1]
Zhou, X.S. and Huang, T.S. (2002) Unifying Keywords and Visual Contents in Image Retrieval. Multimedia IEEE, 9, 23-33.
[2]
He, R., Xiong, N., Yang, L.T., et al. (2011) Using Multi-Modal Semantic Association Rules to Fuse Keywords and Visual Features Automatically for Web Image Retrieval. Information Fusion, 12, 223-230.
[3]
Xu, J. and Shi, P.F. (2004) Active Learning with Labeled and Unlabeled Samples for Content-Based Image Retrieval. Journal of Shanghai Jiaotong University, 38, 2068-2072.
[4]
Jia, S.J., Kong, X.W., Fu, H., et al. (2010) Product Images Classification with Multiple Feature Combination. Proceedings of the 1st International Conference on E-Business Intelligence (ICEBI2010), Atlantis Press, 446-469.
[5]
Nilsback, M.E. (2009) An Automatic Visual Flora-Segmentation and Classification of Flower Images. Oxford University, Oxford.
[6]
Yao, B., Khosla, A., Li, F.F., et al. (2011) Combining Randomization and Discrimination for Fine-Grained Image Categorization. Computer Vision and Pattern Recognition IEEE, Colorado Springs, 20-25 June 2011, 1577-1584.
[7]
Yao, B. and Khosla, A. (2012) Codebook-Free and Annotation-Free Approach for Fine-Grained Image Categorization. Computer Vision and Pattern Recognition IEEE, Providence, 16-21 June 2012, 3466-3473.
[8]
Krause, J., Stark, M., Jia, D., et al. (2014) 3D Object Representations for Fine-Grained Categorization. International Conference on Computer Vision Workshops IEEE, Sydney, 2-8 December 2013, 554-561.
[9]
Dyrmann, M., Karstoft, H., Midtiby, H.S., et al. (2016) Plant Species Classification Using Deep Convolutional Neural Network. Biosystems Engineering, 151, 72-80.
[10]
Sun, Y., Liu, Y., Wang, G., et al. (2017) Deep Learning for Plant Identification in Natural Environment. Computational Intelligence and Neuroscience, 2017, Article ID: 7361042.
[11]
Krizhevsky, A., Sutskever, I., Hinton, G.E., et al. (2012) ImageNet Classification with Deep Convolutional Neural Networks. International Conference on Neural Information Processing Systems, Lake Tahoe, 3-6 December 2012, 1097-1105.
[12]
Russakovsky, O., Deng, J., Su, H., et al. (2015) ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115, 211-252.
[13]
Lecun, Y., Bengio, Y., Hinton, G., et al. (2015) Deep Learning. Nature, 521, 436.
[14]
Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al. (1986) Learning Representations by Back-Propagating Errors. Nature, 323, 533-536.
[15]
Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition.
[16]
He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Computer Vision and Pattern Recognition, Las Vegas, 770-778.
[17]
Ioffe, S. and Szegedy, C. (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Computer Science, 448-456.
[18]
Dieleman, S., De Fauw, J., Kavukcuoglu, K., et al. (2016) Exploiting Cyclic Symmetry in Convolutional Neural Networks. 1889-1898.
[19]
Mount, J. (2011) The Equivalence of Logistic Regression and Maximum Entropymodels. http://www.win-vector.com/dfiles/LogisticRegressionMaxEnt.pdf
[20]
Glorot, X., Bordes, A., Bengio, Y., et al. (2011) Deep Sparse Rectifier Neural Networks. International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, 315-323.
[21]
Cao, X. (2015) A Practical Theory for Designing Very Deep Convolutional Neural Networks Classifier Level. Technical Report.
[22]
Luo, W., Li, Y., Urtasun, R., et al. (2016) Understanding the Effective Receptive Field in Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, Barcelona, 5-10 December 2016, 4898-4906.
[23]
Girshick, R., Donahue, J., Darrel, T., et al. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 580-587.
[24]
Girshick, R. (2015) Fast-RCNN. Proceedings of the IEEE Conference on Computer Vision, Santiago, 7-13 December 2015, 1440-1448.
[25]
Ren, S., He, K., Girshick, R., et al. (2015) Faster-RCNN: Towards Real-Time Object Detection with Region Proposal Networks. Advances in Neural Information Processing Systems, Montreal, 7-12 December 2015, 91-99.
