Automatic gender detection is a process of determining the gender of a human according to the characteristic properties that represent the masculine and feminine attributes of a subject. Automatic gender detection is used in many areas such as customer behaviour analysis, robust security system construction, resource management, human-computer interaction, video games, mobile applications, neuro-marketing etc., in which manual gender detection may be not feasible. In this study, we have developed a fully automatic system that uses the 3D anthropometric measurements of human subjects for gender detection. A Kinect 3D camera was used to recognize the human posture, and body metrics are used as features for classification. To classify the gender, KNN, SVM classifiers and Neural Network were used with the parameters. A unique dataset gathered from 29 female and 31 male (a total of 60 people) participants was used in the experiment and the Leave One Out method was used as the cross-validation approach. The maximum accuracy achieved is 96.77% for SVM with an MLP kernel function.
This paper presents a comprehensive metrological analysis of the Microsoft Kinect motion sensor performed using a proprietary flat marker. The designed marker was used to estimate its position in the external coordinate system associated with the sensor. The study includes calibration of the RGB and IR cameras, parameter identification and image registration. The metrological analysis is based on the data corrected for sensor optical distortions. From the metrological point of view, localization errors are related to the distance of an object from the sensor. Therefore, the rotation angles were determined and an accuracy assessment of the depth maps was performed. The analysis was carried out for the distances from the marker in the range of 0.8−1.65 m. The maximum average error was equal to 23 mm for the distance of 1.6 m.