Human posture recognition is widely used in intelligent monitoring, human-computer interaction, video retrieval, virtual reality and so on. So it has been an active research direction in the field of computer vision. Firstly, the edge of human posture is detected, and the key feature points of the target image are calibrated. Then the human posture image is mapped by convolution neural network. Experimental results show that the proposed method has some advantages in both recognition rate and recognition time.

Fangjuan Xie. Intelligent Recognition Method of Multitype Human Posture Based on Deep Learning. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 11: 68-72. https://doi.org/10.25236/AJCIS.2022.051110.

[1] Fasanmade A, He Y, Al-Bayatti A H, et al. A Fuzzy-Logic Approach to Dynamic Bayesian Severity Level Classification of Driver Distraction Using Image Recognition [J]. IEEE Access, 2020, PP (99):1-1.

[2] Velichko A. Neural network for low-memory IoT devices and MNIST image recognition using kernels based on logistic map [J]. Electronics, 2020, 9(9): 1432.

[3] Ye J, He J, Peng X, et al. Attention-driven dynamic graph convolutional network for multi-label image recognition[C]//European conference on computer vision. Springer, Cham, 2020: 649-665.

[4] Kumar R, Joshi S. Dwivedi A. CNN-SSPSO: a hybrid and optimized CNN approach for peripheral blood cell image recognition and classification [J]. International Journal of Pattern Recognition and Artificial Intelligence, 2021, 35(5): 2157004.

[5] Luo Y L. Multi‐feature data mining for CT image recognition [J]. Concurrency and Computation: Practice and Experience, 2020, 32(1): e4885.

[6] Fan T. Image Recognition and Simulation Based on Distributed Artificial Intelligence [J]. Complexity, 2021, 4(5): 1-12.