With the arrival of the era of artificial intelligence and data, the "Internet +" education model has achieved a blowout development. At the beginning of 2020, the outbreak of COVID-19 further promoted the online teaching model. However, due to the separation of time and space and the way of single line teaching, online classes lack human communication; when students' learning mood and behavior turn away from the learning classroom, teachers can not correct and give reminders in time, resulting in poor learning effect of students. Therefore, how to use artificial intelligence methods to obtain students' learning behavior from online classes, analyze and judge their classroom status, and form an effective classroom status evaluation mechanism is an important foundation for achieving scientific online education and improving learning effects. In this paper, the following research has been carried out on the online classroom face recognition system based on convolutional neural network. The use of ghost module can effectively reduce the amount of parameters and computation, and still ensure the good face recognition effect of the network. 

Amar Singh. Convolutional Neural Network in Face Recognition in Online Classroom. International Journal of Neural Network (2021), Vol. 2, Issue 2: 47-54. https://doi.org/10.38007/NN.2021.020207.

[1] Acharya U R, Fujita H, Lih O S, et al. Automated Detection of Coronary Artery Disease Using Different Durations of ECG Segments with Convolutional Neural Network. Knowledge-Based Systems. (2017) 132(sep.15):62-71. https://doi.org/10.1016/j.knosys.2017.06.003

[2] Salehi S, Erdogmus D, Gholipour A. Auto-Context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging. IEEE Transactions on Medical Imaging. (2017) (11):1-1.

[3] Evo I, Avramovi A. Convolutional Neural Network Based Automatic Object Detection on Aerial Images. IEEE Geoscience & Remote Sensing Letters. (2017) 13(5):740-744. https://doi.org/10.1109/LGRS.2016.2542358

[4] Cheng G, Wang Y, Xu S, et al. Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network. IEEE Transactions on Geoscience and Remote Sensing. (2017) 55(6):3322-3337. https://doi.org/10.1109/TGRS.2017.2669341

[5] Alotaibi M, Mahmood A. Improved Gait Recognition Based on Specialized Deep Convolutional Neural Network. Computer Vision and Image Understanding. (2017) 164(NOV.):103-110. https://doi.org/10.1016/j.cviu.2017.10.004

[6] Chen F C, Jahanshahi R. NB-CNN: Deep Learning-based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion. IEEE Transactions on Industrial Electronics. (2018) 65(99):4392-4400. https://doi.org/10.1109/TIE.2017.2764844

[7] Mao L. Remote Classroom Action Recognition Based on Improved Neural Network and Face Recognition. Journal of Intelligent and Fuzzy Systems. (2021) (1):1-11. https://doi.org/10.3233/JIFS-189803

[8] Mansoora S, Sadineni G, Kauser S H. Attendance Management System Using Face Recognition Method. Journal of Physics: Conference Series. (2021) 2089(1):012078-. https://doi.org/10.1088/1742-6596/2089/1/012078

[9] Thampi S M, Krishnan S, Rodriguez J C, et al. [Advances in Intelligent Systems and Computing] Advances in Signal Processing and Intelligent Recognition Systems Volume 678 || A Combined Feature Extraction Method for Automated Face Recognition in Classroom Environment. (2018) 10.1007/978-3-319-67934-1:417-426. https://doi.org/10.1007/978-3-319-67934-1_38

[10] Granda L, LRB Guamán, Torres-Carrion P V, et al. Face Recognition Systems in Math Classroom through Computer Vision Traditional Techniques. Communications in Computer and Information Science. (2020) 1194:652-664. https://doi.org/10.1007/978-3-030-42520-3_51

[11] Mustafa H T, Yang J, Zareapoor M. Multi-Scale Convolutional Neural Network for Multi-Focus Image Fusion. Image and Vision Computing. (2019) 85(MAY):26-35. https://doi.org/10.1016/j.imavis.2019.03.001

[12] Griffiths D, Boehm J. Improving Public Data for Building Segmentation from Convolutional Neural Networks (Cnns) For Fused Airborne Lidar and Image Data Using Active Contours. ISPRS Journal of Photogrammetry and Remote Sensing. (2019) 154(AUG.):70-83. https://doi.org/10.1016/j.isprsjprs.2019.05.013

[13] Rashid M, Khan M A, Sharif M, et al. Object Detection and Classification: A Joint Selection and Fusion Strategy of Deep Convolutional Neural Network and SIFT Point Features. Multimedia Tools & Alications. (2019) 78(12):15 https://doi.org/10.1007/s11042-018-7031-0751-15777.

[14] Rai A K, Mandal N, Singh A, et al. Landsat 8 OLI Satellite Image Classification using Convolutional Neural Network. Procedia Computer Science, 2020, 167:987-993. https://doi.org/10.1016/j.procs.2020.03.398

[15] Akhtar Z, Rattani A. A Face in any Form: New Challenges and Oortunities for Face Recognition Technology. Computer. (2017) 50(4):80-90. https://doi.org/10.1109/MC.2017.119

[16] Sakulchit T, Kuzeljevic B, Goldman R D. Evaluation of Digital Face Recognition Technology for Pain Assessment in Young Children. The Clinical journal of pain. (2019) 35(1):18-22. https://doi.org/10.1097/AJP.0000000000000659

[17] Rui C, Lima S, Á Rocha. Alication of Face Recognition Technology Based on CA Algorithm in Intelligent Residential Property Management. Journal of Intelligent & Fuzzy Systems. (2018) 35(3):2909-2919. https://doi.org/10.3233/JIFS-169646

[18] Lonarevi Z, Saraevi M, Hadi M. Analysis of Some Techniques of Biometric Authentication Systems with Emphasis on 2D And 3D Face Recognition Technology. Ekonomski Izazovi. (2018) 7(13):119-139. https://doi.org/10.5937/EkoIzazov1813119L