2019 Vol.2 Oct. No.5

• Title: A new gesture recognition method using HOG features and deep neural network
• Name: Bing Hu, Xiang Wang, Liang Gong, Limin Zhu
• Company: College of Computer and Information, Anhui Polytechnic Universit
• Abstract:

  Aiming at the low recognition rate of existing hand gesture recognition methods in complex environment, a new hand gesture recognition method based on the combination of hog and deep neural network is proposed. Firstly, the input video is processed by frame difference, and the action information is extracted by identifying the region of interest (ROI). Then, the gradient direction histogram (HOG) is extracted as the feature. Finally, the extracted features are fed back to the deep neural network framework, and the gesture classification is realized by using support vector machine (SVM). The proposed method is evaluated by using the data set of Jochen Triesch. The experimental results show that the proposed new gesture recognition method has a high recognition accuracy.

• Keyword: Gesture Recognition; Frame Difference; Gradient Direction Histogram; Deep Neural Network; Roi Extraction; Support Vector Machine
• DOI: 10.12250/jpciams2019050560
• Citation form: Bing Hu, Xiang Wang, Liang Gong, Limin Zhu .A new gesture recognition method using HOG features and deep neural network[J]. Computer Informatization and Mechanical System, 2019, vol. 2, pp. 1-3.

[1] Mitra S, Acharya T. Gesture Recognition: A Survey[J]. IEEE Transactions on Systems Man & Cybernetics Part C, 2007, 37(3):311-324.

[2] Pei J, Hu H H, Tao L, et al. Head gesture recognition for hands‐free control of an intelligent wheelchair[J]. Industrial Robot An International Journal, 2007, 34(1):60-68.

[3] Wu J, Jian C. Bayesian Co-Boosting for Multi-modal Gesture Recognition[J]. Journal of Machine Learning Research, 2017, 15(1):3013-3036.

[4] Bakheet S, Alhamadi A. Hand Gesture Recognition Using Optimized Local Gabor Features[J]. Journal of Computational & Theoretical Nanoscience, 2017, 14(3):1380-1389.

[5] Qi J, Jiang G, Li G, et al. Surface EMG hand gesture recognition system based on PCA and GRNN[J]. Neural Computing and Applications, 2019, (4): 1-9.

[6] Li J, Huai H, Gao J, et al. Spatial-temporal dynamic hand gesture recognition via hybrid deep learning model[J]. Journal on Multimodal User Interfaces, 2019, (8): 1-9.

[7] Latorrecarmona P, Pla F. 3D human gesture recognition using integral imaging[J]. Spienewsroom, 2018, 12(1):15-20.

[8] Lu Z, Xiang C, Qiang L, et al. A Hand Gesture Recognition Framework and Wearable Gesture-Based Interaction Prototype for Mobile Devices[J]. IEEE Transactions on Human-Machine Systems, 2017, 44(2):293-299.

[9] Jebril N A, Al-Zoubi H R, Al-Haija Q A. Recognition of Handwritten Arabic Characters using Histograms of Oriented Gradient (HOG)[J]. Pattern Recognition & Image Analysis, 2018, 28(2):321-345.

[10] Judd P, Albericio J, Moshovos A. Stripes: Bit-Serial Deep Neural Network Computing[J]. IEEE Computer Architecture Letters, 2017, 16(1):80-83.

[11] Brooks J L, Zoumpoulaki A, Bowman H. Data‐driven region‐of‐interest selection without inflating Type I error rate[J]. Psychophysiology, 2017, 54(1):100-113.

[12] Chen C, Liang J, Zhao H, et al. Frame difference energy image for gait recognition with incomplete silhouettes[J]. Pattern Recognition Letters, 2009, 30(11):977-984.

[13] Kaur B, Joshi G, Vig R. Indian sign language recognition using Krawtchouk moment-based local features[J]. Journal of Photographic Science, 2017, 65(3):171-179.