Based on the characteristics of the image, the traditional methods are improved based on the theory of convolutional networks and the research results at home and abroad. Firstly, the training algorithm of convolutional network is studied. By analysing the algorithm, debugging and finding the optimal initialization parameters and the most suitable network structure configuration. Then, for the calculation of the classification result, a multi-region test method is used, and the accuracy of image recognition can be improved by calculating a plurality of regions of the image during the test. Finally, a general dataset input interface is designed for the system, and the experimental results show that the improved convolutional neural network structure is more conducive to obtaining the diversity characteristics of the image. Under the same experimental conditions, the recognition rate is higher than that of the traditional network.

Zhiqiang Gao, Yuexin Li, Shijie Wang. An image recognition method using parallel deep CNN. Academic Journal of Computing & Information Science (2019), Vol. 2, Issue 3: 34-48. https://doi.org/10.25236/AJCIS.020305.

[1] Guo L, Li F, Liew W C(2016). Image Aesthetic Evaluation Using Parallel Deep Convolution Neural Network. International Conference on Digital Image Computing: Techniques & Applications.
[2] Lin B Y, Chen C S(2016). Two Parallel Deep Convolutional Neural Networks for pedestrian detection.International Conference on Image & Vision Computing New Zealand.
[3] Chen X, Xiang S, Liu C L, et al(2014). Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks.  Pattern Recognition.
[4] Gong T, Fan T, Guo J, et al(2016). Gpu-based parallel optimization and embedded system application of immune convolutional neural network. International Workshop on Artificial Immune Systems.
[5] Zhang P, Niu X, Dou Y, et al(2017). Airport Detection on Optical Satellite Images Using Deep Convolutional Neural Networks[J]. IEEE Geoscience & Remote Sensing Letters, vol. 14, no.8, pp.1183-1187.
[6] Yuan X, Pu Y(). Parallel lensless compressive imaging via deep convolutional neural networks[J]. Optics Express, vol. 26, no.2, pp.1962-1977.
[7] Pang S, Yu Z, Orgun M A(2017). A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images[J]. Computer Methods & Programs in Biomedicine, vol.140, pp.283-293.
[8] Li X, Zhang G, Huang H H, et al(2016). Performance Analysis of GPU-Based Convolutional Neural Networks. International Conference on Parallel Processing.
[9] Yang X, Liu C, Wang Z, et al(2017). Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI[J]. Medical Image Analysis, vol. 42, pp.212-227.
[10] Lee S, Jha D, Agrawal A, et al(2017). Parallel Deep Convolutional Neural Network Training by Exploiting the Overlapping of Computation and Communication. IEEE International Conference on High Performance Computing.
[11] Hou S, Liu X, Wang Z(2017). DualNet: Learn Complementary Features for Image Recognition. 2017 IEEE International Conference on Computer Vision (ICCV).
[12] Qin M, Xie F, Li W, et al(2018). Dehazing for Multispectral Remote Sensing Images Based on a Convolutional Neural Network with the Residual Architecture. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, vol.99, pp.1-11.
[13] Phan K T, Maul T H, Vu T T(2017). An Empirical Study on Improving the Speed and Generalization of Neural Networks Using a Parallel Circuit Approach[J]. International Journal of Parallel Programming, vol.45, no.4):780-796.
[14] Zhang H, Zhu Q, Jia X(2015). An Effective Method for Gender Classification with Convolutional Neural Networks. International Conference on Algorithms & Architectures for Parallel Processing..
[15] Yakopcic C, Alom M Z, Taha T M(2017). Extremely parallel memristor crossbar architecture for convolutional neural network implementation. International Joint Conference on Neural Networks.
[16] Chu J L, Krzyżak A(2014). Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks. Canadian Conference on Artificial Intelligence.
[17] Du L, Du Y, Li Y, et al(2018). A Reconfigurable Streaming Deep Convolutional Neural Network Accelerator for Internet of Things[J]. Circuits & Systems I Regular Papers IEEE Transactions on, vol. 65, no.1, pp. 198-208.
[18] Anthimopoulos M, Christodoulidis S, Ebner L, et al(2016). Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network [J]. IEEE Transactions on Medical Imaging, vol.35, no. 5, pp. 1207-1216.