Network point door opening and closing state recognition method and device, electronic equipment and storage medium

Abstract

The invention relates to the image detection technology, and discloses a network point door opening and closing state identification method comprising the following steps: obtaining door images of a plurality of network points and a network point identification code corresponding to each door image; converting the dot identification code into a dot marking field, and marking the door image corresponding to the dot identification code by using the dot marking field to obtain a marked door image set; performing image standardization and feature extraction on the marking door image set to obtainan image feature set; performing double full connection processing on the image feature set to obtain a connection feature set; calculating a probability result of each connection feature in the connection feature set, and generating a plurality of website door opening and closing states according to the probability result. In addition, the invention also relates to a blockchain technology, and the door image can be stored in a node of a blockchain. The invention further provides a website door opening and closing state recognition device, electronic equipment and a computer readable storage medium. The method can solve a problem that the convolutional neural network is low in recognition accuracy of the opening and closing states of the website.

Description

technical field [0001] The present invention relates to the technical field of image detection, in particular to a method, device, electronic equipment and computer-readable storage medium for recognizing the opening and closing state of a network point. Background technique [0002] Generally, large companies or enterprises will set up multiple outlets across the country to handle business, but for the needs of operation and management, the company or enterprise needs to know the daily business start and end time of each outlet established. [0003] The traditional method of counting the opening and closing time of outlets is to use the images taken when the existing outlets open and close the doors to train the convolutional neural network, so that the trained convolutional neural network can analyze the status of the outlets’ opening and closing doors in the image according to the input image. recognition, but the existing convolutional neural network mostly uses binary c...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method, device and computer-readable storage medium for identifying the state of opening and closing of outlets, the main purpose of which is to solve the problem of low accuracy in identifying the state of opening and closing of outlets by convolutional neural networks

Images