Optimization Method of IR Thermography Facial Image Registration

Abstract

So far, there have been many types of researches subject to technical requirements due to image registration. Using image registration can lower deviation from sequential images and make it possible to analyze the information variation of the particular area subsequently. This study provides a procedure creating fixed image based on the data of facial IR thermography, where its methods include the visual saliency map by detected image, as well as cluster algorithm. Comparison is also made here to solve the merits and demerits by affine parameter to reach the optimum measure among Genetic Algorithm, Particle Swarm Optimization, and Simulated Annealing Algorithm, where there are two control parameters concerning this experiment: one is the calculation of time confined each alignment, while the other one is to use parallel computing toolbox or not. The optimum method will be chosen by the values of the objective function based on the control parameters. Afterward, the optimal internal parameter is to be verified through the Taguchi experiment and the validity of this procedure in this study will be built following the parameter result as above. Therefore, the difference of images before and after alignment can be validated by overlapping the images before and after alignment as well as the image quality measurements, where its results reveal that the alignment procedure of IR thermography in this study is capable of performing human face alignment precisely, and subsequently, do help data statistics and analysis concerning temperature area interdependence.

End-to-end processing of passive thermography sequences from outdoor concrete infrastructure inspection

“…However, the acquisition and analysis of thermal sequences also have challenges, including the generation of a high volume of data, the particular choice of acquisition settings, the misalignment and changes in the field of view caused by camera movement, the presence of irrelevant and dynamic objects in the scene, and oscillating noise. Studies over the past two decades have provided significant information on the treatment of IRT image, 6 processing of sequential thermal images for dimension reduction, [7][8][9][10][11] image registration, [12][13][14] subsurface delamination detection in concrete structures using IRT inspection 5,[15][16][17] and infrared image sequence analysis. [18][19][20][21] For data acquisition, there is one ASTM standard 22 that provides recommendations for subsurface delamination detection using IRT cameras and single image acquisition, although the standard is framed solely for the inspection of bridge decks with a camera mounted on a car.…”

Analysis of the correlation between infrared thermal sequence images of nostril area and respiratory rate

“…To analyse the time variant temperature of specific areas of the body surface, many studies use thermal image pre‐processing techniques to resolve the deviation caused by the movement of objects. This can include calibration methods based on regional features and overall temperature [6, 7]. Both methods have advantages in different applications, but the information in a thermal colour image is different from that in a visible light image.…”

Biomedical Signal Acquisition Using Sensors under the Paradigm of Parallel Computing

“…The Parallel-Computing Toolbox allows working with all workers or CPU Cores on a local machine, limiting this to the number of cores and threads of the microprocessor (in our case, four). If there is an application requiring more than four CPU cores in a cluster, the Matlab Distributed Computing Sever toolbox must be used, allowing working with all those workers or Distributed CPU Cores [37].…”