Academic Journal of Engineering and Technology Science, 2023, 6(5); doi: 10.25236/AJETS.2023.060508.
Zhuojun Li, Yueyang Cao, Weikang Shi
College of Pharmacy, North China University of Science and Technology, Tangshan, 063210, China
At present, the world's major pharmaceutical companies often identify defective tablets by visual inspection, but because of the fatigue of staff and the human eye's recognition limit of tiny parts, so there are often missed inspection, inefficient inspection phenomenon.[1] How to effectively monitor and ensure more qualified inspection rate in the inspection activities, which is the current problems encountered by pharmaceutical companies. How to efficiently detect and maintain a high detection rate in the testing process, which is currently the difficulties faced by pharmaceutical companies. In order to improve the service quality of the company, the adoption of machine inspection and sorting technology to replace manual inspection and sorting has become a trend. [2]Therefore, after systematic research, we obtained a method for monitoring surface defects of tablet products based on convolutional neural network. Using this method, we developed a tablet screening technique for surface defects, which significantly improved the accuracy and efficiency of surface defect detection.
tablet drugs; deep learning; sorting system
Zhuojun Li, Yueyang Cao, Weikang Shi. Deep learning algorithm based tablet drug screening system. Academic Journal of Engineering and Technology Science (2023) Vol. 6, Issue 5: 50-54. https://doi.org/10.25236/AJETS.2023.060508.
[1] Wang Xianbao, Li Jie, Yao Minghai, et al. A deep learning-based method for solar cell surface defect detection [J]. Pattern Recognition and Artificial Intelligence, 2014(6):517-523.
[2] Zhu M.Y., Zhou W.N. Application of image processing in pill defect detection [J]. Computer Engineering and Design, 2010, 31(23):5151-5154.
[3] Sun Jizheng. Research on online detection technology of float glass defects based on FPGA and DSP [J]. Science Technology and Engineering, 2014, 1:260-264.
[4] Jing Junfeng, Fan Xiaoting, Li Pengfei, et al. Application of deep convolutional neural network for color fabric defect detection [J]. Journal of Textile, 2017, 38(02):68-74.
[5] Hui D. The Design of APP Content Guiding System Based on Deep Learning Algorithm[J]. IOP Conference Series: Earth and Environmental Science, 2019, 252(4):042110 (4pp).