Hand operation action scoring device and method and computer readable storage medium

Abstract

The invention discloses a hand operation action scoring device and method and a computer readable storage medium, and the method comprises the steps of converting an obtained hand operation image frame into an HSV image, so as to obtain a binary image of a region where skin is located and a plurality of rectangular frames of the region where a hand is located from the HSV image; segmenting a firsthand image from the binarized image according to the plurality of rectangular frames and inputting the first hand image into a first preset model; constructing tracking data accumulated along with tracking time based on an analysis result of the first preset model; if the hand key point coordinates analyzed by the first preset model are unreliable, calling a preset hand series detection model todetect the hand operation image frame; utilizing a second preset model to configure a hand label for each hand part in the tracking data so as to perform data classification; preprocessing the classified tracking data to obtain refined data of each hand; and scoring the operation action of each hand according to the fine data and the reference fine data. According to the invention, the hand operation actions of the testee can be scored.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a handwork movement scoring device, method and computer-readable storage medium. Background technique [0002] In recent years, with the development of deep learning technology, the existing hand recognition technology generally uses hand detection models based on various architectures of convolutional neural networks for hand recognition. These models generally require only one hand in the input picture, which has certain limitations. [0003] In modern factories, the accuracy of workers' hand movements can have a certain impact on the yield and production efficiency of the production line. Existing evaluation methods for workers' hand movements generally involve real-time observation and scoring of workers' hand movements directly by evaluators. The accuracy of the evaluation is affected by the human factors of the evaluators, and the accuracy cannot be guarant...

AI Technical Summary

Problems solved by technology

The existing evaluation methods for workers' hand movements are generally observed and scored by the evaluators directly on the workers' hand movements in real time. The accuracy of the evaluation is affected by the human factors of the evaluators, and the accuracy cannot be guaranteed.

Images