A Face Recognition Method of Thermal Infrared Image in Coal Mine

Abstract

The invention discloses a coal mine underground thermal infrared image face recognition method, which comprises the steps of acquiring miner face thermal infrared images of miners and conducting normalization processing, conducting steps such as anisotropic diffusion filtering, vessel network extraction, vessel network skeleton extraction and vessel crossing point characteristic extraction to obtain crossing point distribution characteristic vectors which reflect face vessel crossing point distribution, and saving the crossing point distribution characteristic vectors in a miner face characteristic library; and at a face online recognition stage, acquiring a face thermal infrared image of a miner to be recognized, conducting normalization and face image temperature compensation processing, calculating the crossing point distribution characteristic vector of the image and finally obtaining a recognition result according to the degree of matching between the crossing point distribution characteristic vector of the image to be recognized and the crossing point distribution characteristic vectors in the miner face characteristic library. By using thermal infrared images to recognize faces, the coal mine underground thermal infrared image face recognition method is suitable for face recognition under the situations that the lighting conditions are poor and the faces of the miners are frequently covered by coal ash, the recognition rate is high and reliable information is provided for the identification of personnel who get in and out of mines in mining areas.

Description

technical field [0001] The invention relates to a thermal infrared image face recognition method based on image morphology, and belongs to the technical field of image pattern recognition. Background technique [0002] Coal is one of the main energy sources in my country and an important guarantee for China's economic development. About 70% of my country's energy consumption comes from coal. Since miners violate regulations and illegal operations occur from time to time, it will affect the safe production of coal mines, so there are strict requirements and restrictions on the management of underground personnel in the underground production process. [0003] The identity detection of personnel entering and exiting the well is one of the important technical means to ensure safe production in mines. Currently existing detection methods include detection technologies based on RFID and fingerprints. These technologies can achieve a certain degree of effect, but there are also s...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the problems existing in the application of existing RFID identification card methods, fingerprint recognition methods, and visible light face recognition methods to underground uniqueness detection, the present invention proposes a thermal infrared face image based on image morphology suitable for special underground environments The recognition method, which can achieve a high recognition rate in the dark underground environment, has strong adaptability to the temperature change of the coal mine underground environment, can deal with the situation where miners wear glasses and miner's lamps, and effectively detect the areas of glasses and miner's lamps. The unique detection of personnel leaving and entering the well provides a guarantee

Images