Abstract：To solve the positioning problem in toothbrush sorting, a method was proposed based on deep learning for toothbrush positioning and gesture recognition. The image of toothbrush was denoised and enhanced, and the interested region was extracted by threshold segmentation. The geometric moment of image was calculated to obtain the direction angle of toothbrush and the outer rectangle. The center of outer rectangle was taken as the center of toothbrush to determine the toothbrush position. The residual network model was trained with the toothbrush image in the rectangular box. When the accuracy of the model reached the requirement, the model was saved to judge the attitude of toothbrush in the image. The test results show that the method can quickly and accurately realize the position determination and gesture recognition of toothbrush, and provide the posture information for the robot operation.
LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis［J］. Medical Image Analysis, 2017, 42:60-88.
［2］
CHEN Y, LIN Z, ZHAO X, et al. Deep learning-based classification of hyperspectral data［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6):2094-2107.
WANG S K, ZHAO J Z, JIANG M, et al. Zhang′s camera calibration method based on circular array calibration board［J］. Journal of Beijing Institute of Technology, 2019,39(8):859-863.（in Chinese）
［5］
LEI B, FAN J L. Image thresholding segmentation method based on minimum square rough entropy［J］. Applied Soft Computing Journal,2019, doi： 10.1016/j.asoc.2019.105687.
［6］
HE K, ZHANG X, REN S, et al. Deep residual lear-ning for image recognition［J］. CVPR, 2016, doi:10.1109/CVPR.2016.90.
［7］
KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks［C］∥Proceedings of the Conference on Neural Information Processing Systems, 2012:1106-1114.
［8］
GRM K, ARTIGES A,CARON M, et al. Strengths and weaknesses of deep learning models for face recognition against image degradations［J］. IET Biometrics, 2018, 7(1):81-89.
［9］
ZHENG Y,WANG R, YANG J, et al. Principal characteristic networks for few-shot learning［J］.Journal of Visual Communication and Image Representation, 2019, 59:563-573.
2021, Vol. 42 
