The paper presents an analysis concerning the influence of selected psychophysical parameters on the quality of human gait recognition. The following factors have been taken into account: body height (BH), body weight (BW), the emotional condition of the respondent, the physical condition of the respondent, previous injuries or dysfunctions of the locomotive system. The study was based on data measuring the ground reaction forces (GRF) among 179 participants (3 315 gait cycles). Based on the classification, some kind of confusion matrix were established. On the basis of the data included in the matrix, it was concluded that the wrong classification was most affected by the similar weight of two confused people. It was also noted, that people of the same gender and similar BH were confused most often. On the other hand, previous body injuries and dysfunctions of the motor system were the factors facilitating the recognition of people. The results obtained will allow for the design of more accurate biometric systems in the future.
Mariusz Bogdan, Marcin Derlatka and Józef Błachnio
The article presents a multi-stage algorithm for automatic (without any human, user – diagnostician intervention) detection of vanes-blades (technical objects) and their surfaces on a digital image, combined with color analysis, aimed at determining the technical condition of the tested turbine elements. The images recorded with the use of a camera, containing previously dismantled from the turbine operated stator vanes, were used as the exemplary analysis material. The paper presents the algorithm for the detection of the vanes’ airfoil surfaces with the impact of the applied techniques and methods of image processing and analysis on the final result (software localization of the vane’s trailing and leading edge), Then, the obtained image data, including the structural changes of both the vane’s coating and material (metallographic testing) were correlated with the surface colour scheme (colour segmentation based on the YCbrCr colour space model). Thanks to this approach, areas on the surface of the blade were distinguished, characteristic for proper, overheated and transient condition.