Traditional Chinese medicine infrared image human body segmentation algorithm based on deep learning

Abstract

The invention provides a deep learning-based traditional Chinese medicine infrared image human body segmentation algorithm. The algorithm comprises the following steps of 1, enabling a to-be-detected person to make a human body action conforming to a specification; 2, adopting an infrared temperature measurement camera to collect a human body infrared image; step 3, processing and preliminarily segmenting the acquired human body infrared image; step 4, segmenting the screened human body infrared image by using a convolutional neural network algorithm; and step 5, outputting the segmented human body infrared image. Through a traditional Chinese medicine infrared image segmentation algorithm adopting a convolutional neural network, a human body exposed area and a clothes shielding area can be accurately segmented, and a human body infrared image of the human body exposed area is used for health state evaluation and clinical disease diagnosis of a physician, so that the highest temperature and the lowest temperature are ensured to be on a human body in an analysis process; the interference of a background and a foreign object is avoided; and meanwhile, the accuracy of evaluation or diagnosis made by a physician is higher.

Description

technical field [0001] The invention relates to the field of infrared image human body segmentation algorithms, in particular to a deep learning-based infrared image human body segmentation algorithm of traditional Chinese medicine. Background technique [0002] Infrared imaging technology is a promising new technology. Electromagnetic waves longer than 0.78 microns lie outside the red of the visible light spectrum and are called infrared radiation, also known as infrared radiation. It refers to electromagnetic waves with a wavelength of 0.78-1000 microns, of which the part with a wavelength of 0.78-2.0 microns is called near-infrared, and the part with a wavelength of 2.0-1000 microns is called thermal infrared. In nature, all objects can radiate infrared rays, so using the detector to measure the infrared difference between the target itself and the background can obtain infrared images formed by different thermal infrared rays. [0003] Image segmentation is the technol...

AI Technical Summary

Problems solved by technology

[0005] In the use of medical digital infrared imaging, the collected infrared images of the human body are infrared images of the clothes of the person to be detected. Sending such infrared images directly to professional doctors for heat map and calorific value analysis may affect the doctor's understanding of the disease. Judgment, there is a certain impact on the assessment of health status and the diagnosis of clinical diseases. The present invention proposes a human body segmentation algorithm based on deep learning in traditional Chinese medicine infrared images. The infrared temperature measurement camera collects human body images that meet the prescribed actions, and proposes a convolution-based Neural network infrared image segmentation algorithm of traditional Chinese medicine, which can realize accurate segmentation of human body temperature area, and provide support for disease diagnosis based on infrared theory of traditional Chinese medicine

Images