摘要
手势作为一种自然语义表达方式,在人机交互中发挥着重要的作用。针对手势图像复杂的背景影响识别准确性且传统方法中人工提取的图像特征难以适应手势多变性的问题,提出一种基于肤色阈值和卷积神经网络的手势识别算法。实验结果表明:该算法在两个数据集下对手势的平均识别率均达到96%以上,因此该算法是可行的。
As a very natural method of semantic expression, gesture plays an important role in human computer interaction. The complex background of gesture images affect the accuracy of recognition. It is difficult to adapt to the variability of hand gestures in traditional methods. In order to solve the problems, we proposed a gesture recognition algorithm based on skin color threshold and convolution neural network. The experimental results show that the average recognition rate of the algorithm is over 96% in both datasets. So the algorithm is feasible.
引文
[1] 朱雯文, 叶西宁. 基于卷积神经网络的手势识别算法[J]. 华东理工大学学报(自然科学版), 2018, 44(2): 260-269.
[2] Rossi M, Benatti S, Farella E, et al. Hybrid EMG classifier based on HMM and SVM for hand gesture recognition in prosthetics[C]//IEEE International Conference on Industrial Technology.IEEE, 2015:1700-1705.
[3] Prasuhn L, Oyamada Y, Mochizuki Y, et al. A HOG-based hand gesture recognition system on a mobile device[C]//IEEE International Conference on Image Processing. IEEE, 2015:3973-3977.
[4] Jimenez J, Martin A, Uc V, et al. Mexican sign language alphanumerical gestures recognition using 3D haar-like features[J].IEEE Latin America Transactions,2017,15(10):2000-2005.
[5] Flores C J L, Cutipa A E G, Enciso R L. Application of convolutional neural networks for static hand gestures recognition under different invariant features[C]//2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing(INTERCON),Cusco,Peru,2017.
[6] Shaik K B, Ganesan P, Kalist V, et al. Comparative study of skin color detection and segmentation in HSV and YCbCr color space[J]. Procedia Computer Science, 2015, 57: 41-48.
[7] Cheng X, Zhang Y H,Chen Y Q, et al. Pest identification via deep residual learning in complex background[J]. Computers and Electronics in Agriculture,2017,141:351-356.
[8] 顾郑平, 朱敏. 基于深度学习的鱼类分类算法研究[J]. 计算机应用与软件,2018,35(1):200-205.
[9] Sridevi K, Sundarambal M, Muralidharan K, et al. FPGA implementation of hand gesture recognition system using neural networks[C]//International Conference on Intelligent Systems and Control. IEEE, 2017:34-39.