Systematic skin segmentation: merging spatial and non-spatial data

Skin detection is used in applications ranging from face detection, tracking of body parts, hand gesture analysis, to retrieval and blocking objectionable content. We present a systematic approach for robust skin segmentation using graph cuts. The skin segmentation process starts by exploiting the local skin information of detected faces. The detected faces are used as foreground seeds for calculating the foreground weights of the graph. If local skin information is not available, we opt for the universal seed. To increase the robustness, the decision tree based classifier is used to augment the universal seed weights when no local information is available in the image. With this setup, we achieve robust skin segmentation, outperforming off-line trained classifiers. The setup also provides a generic skin detection system, using positive training data only. With face detection, we take advantage of the contextual information present in the scene. With the weight augmentation, we provide a setup for merging spatial and non-spatial data. Experiments on two datasets with annotated pixel-level ground truth show that the systematic skin segmentation approach outperforms other approaches and provides robust skin detection.     

Investigations of ductile damage during the process chains of toothed functional components manufactured by sheet-bulk metal forming

Sheet-bulk metal forming processes combine conventional sheet forming processes with bulk forming of sheet semi-finished parts. In these processes the sheets undergo complex forming histories. Due to in- and out-of-plane material flow and large accumulated plastic strains, the conventional failure prediction methods for sheet metal forming such as forming limit curve fall short. As a remedy, damage models can be applied to model damage evolution during those processes. In this study, damage evolution during the production of two different toothed components from DC04 steel is investigated. In both setups, a deep drawn cup is upset to form a circumferential gearing. However, the two final products have different dimensions and forming histories. Due to combined deep drawing and upsetting processes, the material flow on the cup walls is three-dimensional and non-proportional. In this study, the numerical and experimental investigations for those parts are presented and compared. Damage evolution in the process chains is simulated with a Lemaitre damage criterion. Microstructural analysis by scanning electron microscopy is performed in the regions with high mechanical loading. It is observed that the evolution of voids in terms of void volume fraction is strongly dependent on the deformation path. The comparison of simulation results with microstructural data shows that the void volume fraction decreases in the upsetting stage after an initial increase in the drawing stage. Moreover, the concurrent numerical and microstructural analysis provides evidence that the void volume fraction decreases during compression in sheet-bulk metal forming.     

Applying the Mahalanobis-Taguchi strategy for software defect diagnosis

The Mahalanobis-Taguchi (MT) strategy combines mathematical and statistical concepts like Mahalanobis distance, Gram-Schmidt orthogonalization and experimental designs to support diagnosis and decision-making based on multivariate data. The primary purpose is to develop a scale to measure the degree of abnormality of cases, compared to “normal” or “healthy” cases, i.e. a continuous scale from a set of binary classified cases. An optimal subset of variables for measuring abnormality is then selected and rules for future diagnosis are defined based on them and the measurement scale. This maps well to problems in software defect prediction based on a multivariate set of software metrics and attributes. In this paper, the MT strategy combined with a cluster analysis technique for determining the most appropriate training set, is described and applied to well-known datasets in order to evaluate the fault-proneness of software modules. The measurement scale resulting from the MT strategy is evaluated using ROC curves and shows that it is a promising technique for software defect diagnosis. It compares favorably to previously evaluated methods on a number of publically available data sets. The special characteristic of the MT strategy that it quantifies the level of abnormality can also stimulate and inform discussions with engineers and managers in different defect prediction situations.