Tool abnormal placement detection method and system based on double-index metric learning

• Main Authors: YAN XIAOWEI, LI LUYUAN, MA JINHUA, CHEN XI
• Format: Patent
• Language: Chinese; English
• Published: 30.10.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a tool abnormal placement detection method and system based on double-index metric learning, and the method comprises the steps: obtaining a tool box picture of a correct placement tool, marking the tool box picture, and obtaining marking information; according to the marking information, cutting tools in the tool box pictures into correct tool pictures independently, carrying out data expansion on the correct tool pictures, and obtaining a training set and a verification set; training and verifying a preset tool exception placement detection model based on double-indexmetric learning through the training set and the verification set, and adjusting parameters to obtain a final tool exception detection model; and obtaining a current toolbox picture, cutting each current tool picture from the current toolbox picture according to the marking information, inputting the current tool pictures into the final tool abnormality detection model, and judging whether placement is abnormal or not. T