A novel algorithm for reconstruction of infrared thermographic sequence based on image segmentation

Abstract

It is demanding to develop a fast and precise data processing technique for high resolution infrared thermal images. In this paper, a novel algorithm is proposed, which provides an effective way to improve the precision and computing speed for processing of thermal image data, in this paper. Firstly, the algorithm will sort the thermographic sequence data in space by using image segmentation method. Secondly, the algorithm will employ classical fitting calculation to fit all the temperature decay curves. At last, the algorithm will use the fitting parameters of the curves as the parameters for compression and reconstruction of thermographic sequences. The proposed algorithm manages to compress thermographic sequences in time and space simultaneously. To validate the proposed algorithm, the authors used one defective specimen to conduct the experiment. The experimental results showed that the proposed infrared thermographic sequence reconstruction algorithm is an effective solution with high speed and high precision. Compared to the conventional method, this algorithm is not only noise resistant in time domain but also can increase the computing speed by hundreds of times.