Virtual group photography based on scene and person perception.

Group photos have become indispensable in various gathering scenarios, such as family reunions, friends' gatherings, competitions, conferences, store openings, and school graduation ceremonies. The researchers tried automatically adding people who could not participate in the group photo. However, the current research on generating the pose or position of the person by context prediction of the group photo ignores the individual attributes (such as height and body shape) of the target person and does not consider the pose and boundary of the person at the same time. To address these issues, we propose a virtual group photography model that combines the global context of a group photo and the individual attributes of the target person. The model is divided into two stages. The first stage is to predict the person's position, pose, and boundary in the new group photo based on the context of the input group photo and the person's characteristics. The second stage generates new group photos based on the first stage's pose and boundary results. The experimental results show that our method can significantly improve the harmony and authenticity of the synthesis of people in group photos and synthesize the characters that should exist in the group photo, which is very suitable for the field of group photos.

3D Intelligent Scissors for Dental Mesh Segmentation.

Teeth segmentation is a crucial technologic component of the digital dentistry system. The limitations of the live-wire segmentation include two aspects: (1) computing the wire as the segmentation boundary is time-consuming and (2) a great deal of interactions for dental mesh is inevitable. For overcoming these disadvantages, 3D intelligent scissors for dental mesh segmentation based on live-wire is presented. Two tensor-based anisotropic metrics for making wire lie at valleys and ridges are defined, and a timesaving anisotropic Dijkstra is adopted. Besides, to improve with the smoothness of the path tracking back by the traditional Dijkstra, a 3D midpoint smoothing algorithm is proposed. Experiments show that the method is effective for dental mesh segmentation and the proposed tool outperforms in time complexity and interactivity.

Exposing image forgery by detecting consistency of shadow.

We propose two tampered image detection methods based on consistency of shadow. The first method is based on texture consistency of shadow for the first kind of splicing image, in which the shadow as well as main body is copied and pasted from another image. The suspicious region including shadow and nonshadow is first selected. Then texture features of the shadow region and the nonshadow region are extracted. Last, correlation function is used to measure the similarity of the two texture features. By comparing the similarity, we can judge whether the image is tampered. Due to the failure in detecting the second kind of splicing image, in which main body, its shadow, and surrounding regions are copied and pasted from another image, another method based on strength of light source of shadows is proposed. The two suspicious shadow regions are first selected. Then an efficient method is used to estimate the strength of light source of shadow. Last, the similarity of strength of light source of two shadows is measured by correlation function. By combining the two methods, we can detect forged image with shadows. Experimental results demonstrate that the proposed methods are effective despite using simplified model compared with the existing methods.