| In the coal industry,coal preparation plants are mainly responsible for the separation of raw coal to maximize coal utilization,and the attendance management of coal preparation plants has a direct impact on the production efficiency of the coal preparation plant.Face recognition is often used in attendance due to its uniqueness and non-contact characteristics.Compared with traditional attendance methods,face attendance is more efficient and safe.Therefore,in order to strengthen the personnel management of the coal preparation plant,it is of great significance and value to study the face attendance system of the coal preparation plant.Since there is no open source face database for coal preparation plants,convolutional neural network requires a large number of samples during training,the paper uses mirroring,rotation,and translation to increase the number of samples.The employees’ faces are easily contaminated with coal ash during work,which affects face recognition effect On the basis of gaussian filtering of face images,the paper uses a combination of limited contrast adaptive histogram equalization and gamma correction to improve image features,making face details more prominent;AdaBoost algorithm based on Haar-like feature realizes face detection in coal preparation plant and extracts faces from complex background;in order to improve the accuracy of face recognition,the traditional AlexNet model is optimized,and the optimized model can extract more face features;according to the functional requirements of the attendance system,designed the face attendance system of the coal preparation plant,built the GUI interface of the attendance system using Python language,and designed the relevant database to realize the attendance management of the employees of the coal preparation plant.In this paper,through in-depth research on face recognition in coal preparation plant,the proposed optimized convolutional neural network has good robustness to face recognition in the environment of coal preparation plants.The designed attendance system is strengthened to a certain extent the attendance management of coal preparation plant employees.This subject has certain theoretical research significance and engineering application value. |