Convolutional Neural Networks for Semantic Segmentation as a Tool for Multiclass Face Analysis in Thermal Infrared

Convolutional neural networks were used for multiclass segmentation in thermal infrared face analysis. The principle is based on existing image-to-image translation approaches, where each pixel in an image is assigned to a class label. We show that established networks architectures can be trained for the task of multiclass face analysis in thermal infrared. Created class annotations consisted of pixel-accurate locations of different face classes. Subsequently, the trained network can segment an acquired unknown infrared face image into the defined classes. Furthermore, face classification in live image acquisition is shown, in order to be able to display the relative temperature in real-time from the learned areas. This allows a pixel-accurate temperature face analysis e.g. for infection detection like Covid-19. At the same time our approach offers the advantage of concentrating on the relevant areas of the face. Areas of the face irrelevant for the relative temperature calculation or accessories such as glasses, masks and jewelry are not considered. A custom database was created to train the network. The results were quantitatively evaluated with the intersection over union (IoU) metric. The methodology shown can be transferred to similar problems for more quantitative thermography tasks like in materials characterization or quality control in production.

Applying a Two-Layer Quadrupole Model for Quantitative Thermography at Overload-Induced Delaminations in GFRP

The applicability of 1D-quadrupole-model on the depth estimation of overload-induced delaminations is tested in this contribution. While classical 1D-methods like Pulsed Phase Transformation and Thermographic Signal Reconstruction determine the depth of a defect by one parameter, a two-layer quadrupole model provides two parameters: depth and thermal resistance. In addition, the convectional losses at the surfaces may be considered. The defect investigated is a large-scale delamination in glass fibre reinforced polymer generated by tension overload.

The Importance of Moisture Content to the Emissivity of Ceramic Bricks

Emissivity is a key parameter if one intends to use quantitative thermography. The importance of temperature, surface characteristics, wavelength and the direction of the emitted radiation in the emissivity is well documented in the literature. However, no research was found concerning the effect of moisture content. In this research, an experimental campaign was carried out with two main objectives: compare the emissivity value measured with an emissometer with the value measured with infrared thermography; assess the importance of moisture content in the emissivity value measured with an emissometer. A ceramic brick was used as an example case.