Infrared Thermal Image Processing Method Based on Abnormal Area Location

Abstract

The invention discloses an infrared thermal image processing method based on abnormal area positioning, which collects the infrared thermal image video stream of the measured piece from the beginning of heating to the end of cooling, divides each frame of image into equal areas, and calculates each area according to the frame interval The Pearson correlation coefficient curve, the Pearson correlation coefficient sequence before and after the heating end time is subjected to a rough error test, when it is determined that there is a rough error, the area is judged to be an abnormal area; then the authenticity of the abnormal area is judged to obtain the real abnormal area; Calculate the skewness value of the infrared thermal response sequence of each pixel in the real abnormal area, enhance the infrared thermal response for the pixel with the skewness value greater than the threshold, and weaken the infrared thermal response for all other pixels, so as to obtain the abnormal area enhancement Infrared thermal image video stream. The invention analyzes from the angle of image area information extraction, realizes suppression of interference caused by uneven thermal emissivity on the material surface, and enhances defect features.

Description

technical field [0001] The invention belongs to the technical field of infrared thermal image processing, and more specifically relates to an infrared thermal image processing method based on abnormal region positioning. Background technique [0002] At present, infrared thermal imaging non-destructive testing technology has become an important branch of non-destructive testing. In the infrared thermal imaging non-destructive testing technology, the research on defect extraction and image enhancement has achieved certain results. However, in practical applications, the surface of the test material for non-destructive testing is not smooth or completely clean, and its surface layer is usually There are oil stains, paint coatings or oxide layers, which can seriously cause uneven thermal emissivity distribution on the surface of the material. The signal-to-noise ratio of directly extracted frame images is generally low due to the spurious temperature changes produced by the un...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the deficiencies of the prior art, provide an infrared thermal image processing method based on abnormal area positioning, analyze from the angle of image area information extraction, realize the suppression of interference caused by uneven thermal emissivity on the surface of materials, and enhance Defect characteristics, convenient for subsequent analysis and processing

Images