Cascade CNN Framework for Low Resolution Image Classification
Low resolution images contain less visual information, so classifications of these images are difficult. For overcoming this problem, cascade CNN framework for low resolution image classification is proposed. In this framework, super resolution CNN (SRCNN) enlarges low resolution image into super resolution image. The convolutional features of these super resolution images are fused with low resolution convolutional features which are extracted by low resolution CNN (LRCNN) feature extractor. A deep neural network classifier is trained on these fused CNN features. This classifier classifies low resolution images using learned fused features. Proposed cascade framework has been evaluated on different benchmark image dataset MNIST, CIFAR10 and achieves competitive accuracy results.
Keywords: Low resolution, cascade CNN, super resolution, feature fusion, image classification
Cite this Article
Suresh Prasad Kannojia, Gaurav Jaiswal. Cascade CNN Framework for Low Resolution Image Classification. Journal of Artificial Intelligence Research & Advances. 2019; 6(1): 39–43p.
Mudunuri, Sivaram Prasad, and Soma Biswas. Low resolution face recognition across variations in pose and illumination. IEEE transactions on pattern analysis and machine intelligence 2016; 38(5): 1034-40p
Liu, Yun-Fu, Jing-Ming Guo, and Che-Hao Chang. Low resolution pedestrian detection using light robust features and hierarchical system. Pattern Recognition. 2014; 47(4): 1616-25p.
Wang, Zhangyang, Shiyu Chang, Yingzhen Yang, Ding Liu, and Thomas S. Huang. Studying very low resolution recognition using deep networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016; 4792-4800p.
Kannojia, Suresh Prasad, and Jaiswal, Gaurav. Effects of Varying Resolution on Performance of CNN based Image Classification: An Experimental Study. International Journal of Computer Sciences and Engineering. 2018; 6(9): 451-56p.
Ullman, Shimon, et al. Atoms of recognition in human and computer vision. Proceedings of the National Academy of Sciences. 2016; 113(10): 2744-49p.
M. Chevalier, N. Thome, M. Cord, J. Fournier, G. Henaff, E. Dusch, LR-CNN for fine-grained classification with varying resolution. IEEE International Conference of Image Processing. 2015; 3101–3105p.
Chevalier, Marion, Nicolas Thome, Gilles Hénaff, and Matthieu Cord. Classifying low-resolution images by integrating privileged information in deep CNNs. Pattern Recognition Letters. 2018; 116: 29-35p.
Cai D, Chen K, Qian Y, Kämäräinen JK, Convolutional low-resolution fine-grained classification, Pattern Recognition Letters. 2017.
Wei, Xian, Yuanxiang Li, Hao Shen, Weidong Xiang, and Yi Lu Murphey. Joint learning sparsifying linear transformation for low-resolution image synthesis and recognition. Pattern Recognition. 2017; 66: 412-424p.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998; 86(11): 2278-2324p.
Krizhevsky, Alex, and Geoffrey Hinton. Learning multiple layers of features from tiny images. Technical report, University of Toronto. 2009; 1(4).
Dong, Chao, Chen Change Loy, Kaiming He, and Xiaoou Tang. Learning a deep convolutional network for image super-resolution. In European conference on computer vision, Springer, Cham, 2014; 184-199p.
C. Dong, C. C. Loy, K. He, X. Tang, Image super-resolution using deep convolutional networks, IEEE transactions on Pattern Analysis and Machine Intelligence. 2016; 38 (2): 295–307p.
Gu, Shuhang, Wangmeng Zuo, Qi Xie, Deyu Meng, Xiangchu Feng, and Lei Zhang. Convolutional sparse coding for image super-resolution. In Proceedings of the IEEE International Conference on Computer Vision. 2015; 1823-1831p.
Osendorfer, Christian, Hubert Soyer, and Patrick Van Der Smagt. Image super-resolution with fast approximate convolutional sparse coding. In International Conference on Neural Information Processing. Springer, Cham, 2014; 250-257p.
Fu, Yun, Liangliang Cao, Guodong Guo, and Thomas S. Huang. Multiple feature fusion by subspace learning. In Proceedings of the 2008 international conference on Content-based image and video retrieval. ACM, 2008; 127-134p.
- There are currently no refbacks.