ICANN 2016: Artificial Neural Networks and Machine Learning – ICANN 2016 pp 283-290 | Cite as
Classification of Photo and Sketch Images Using Convolutional Neural Networks
Abstract
Content-Based Image Retrieval (CBIR) system enables us to access images using only images as queries, instead of keywords. Photorealistic images, and hand-drawn sketch image can be used as a queries as well. Recently, convolutional neural networks (CNNs) are used to discriminate images including sketches. However, the tasks are limited to classifying only one type of images, either photo or sketch images, due to the lack of a large dataset of sketch images and the large difference of their visual characteristics. In this paper, we introduce a simple way to prepare training datasets, which can enable the CNN model to classify both types of images by color transforming photo and illustration images. Through the training experiment, we show that the proposed method contributes to the improvement of classification accuracy.
Keywords
Content Based Image Retrieval Hand-drawn sketchNotes
Acknowledgments
The work has been supported by MEXT Grant-in-Aid for Scientific Research (A) 15H01710.
References
- 1.Liu, Y., Zang, D., Lu, G., Ma, W.: A survey of content-based image retrieval with high-level semantics. Pattern Recogn. 40, 262–282 (2007)CrossRefMATHGoogle Scholar
- 2.Eitz, M., Hildebrand, K., Boubekeur, T., Alexa, M.: Sketch-based image retrieval: benchmark and bag-of-features descriptors. IEEE Trans. Visual Comput. Graphics 17, 1624–1636 (2011)CrossRefGoogle Scholar
- 3.Cao, Y., Wang, H., Wang, C., Li, Z., Zhang, L., Zang, L.: MindFinder: interactive sketch-based image search. In: Proceedings of ACM Multimedia International Conference, pp. 1605–1608 (2010)Google Scholar
- 4.Cao, Y., Wang, C., Zhang, L., Zhang, L.: Edgel index for large-scale sketch-based image search. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 761–768 (2011)Google Scholar
- 5.Eitz, M., Hays, J., Alexa, M.: How do humans sketch objects? ACM Trans. Graph. 31, 1–10 (2012)Google Scholar
- 6.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1106–1114 (2012)Google Scholar
- 7.He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. arXiv:1512.03385 (2015)
- 8.Yang, Y., Hospedales, T.M.: Deep Neural Networks for Sketch Recognition. arXiv:1501.07873 (2015)
- 9.Yu, Q., Yang, Y., Song, Y., Xiang, T., Hospedales, T.: Sketch-a-Net that beats humans. In: Proceedings of the British Machine Vision Conference, pp. 7.1–7.12 (2015)Google Scholar
- 10.Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679–698 (1986)CrossRefGoogle Scholar
- 11.Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 421–436. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 12.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girchick, R., Guadarrama, S., Darrell, T.: Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv:1408.5093 (2014)