No abstract

We present a multi-view stereo reconstruction technique that directly produces a complete high-fidelity head model with consistent facial mesh topology. While existing techniques decouple shape estimation and facial tracking, our framework jointly optimizes for stereo constraints and consistent mesh parameterization. Our method is therefore free from drift and fully parallelizable for dynamic facial performance capture. We produce highly detailed facial geometries with artist-quality UV parameterization, including secondary elements such as eyeballs, mouth pockets, nostrils, and the back of the head. Our approach consists of deforming a common template model to match multi-view input images of the subject, while satisfying cross-view, cross-subject, and cross-pose consistencies using a combination of 2D landmark detection, optical flow, and surface and volumetric Laplacian regularization. Since the flow is never computed between frames, our method is trivially parallelized by processing each frame independently. Accurate rigid head pose is extracted using a PCA-based dimension reduction and denoising scheme. We demonstrate high-fidelity performance capture results with challenging head motion and complex facial expressions around eye and mouth regions. While the quality of our results is on par with the current state-of-the-art, our approach can be fully parallelized, does not suffer from drift, and produces face models with production-quality mesh topologies.virtual characters in high-end film and game production. While recent advances in facial tracking research are pushing the boundaries of real-time performance and robustness in unconstrained capture settings, professional studios still rely on computationally demanding offline solutions with high resolution imaging. To further avoid the uncanny valley, time-consuming and expensive artist input, such as tracking clean-up or key-framing, is often required to

We present an accurate video stabilization method on aerial videos using the epipolar geometry constraint. Most previous methods used 2D homography for stabilization, but failed to overcome the parallax problem. In this work, we propose to use dense correspondences for stabilization and the epipolar constraint to deal with the parallax effect. We start by estimating the dense correspondences between two frames. The dense correspondences are then used to estimate the epipolar geometry. The epipolar geometry has an implicit 3D constraint that can be used to improve the dense correspondences and handle the parallax. We evaluate our method on a real-life database containing three aerial image sequences. We also compare our method with the dominant 2D method for aerial video stabilization. The quantitative result demonstrates the effectiveness of our approach.

Handwriting character recognition is an important research topic which has various applications in surveillance, radar, robot technology... In this paper, we propose the implementation of the handwriting character recognition using off-line handwriting recognition. The approach consists of two steps: to make thin handwriting by keeping the skeleton of character and reject redundant points caused by humam’s stroke width and to modify direction method which provide high accuracy and simply structure analysis method to extract character’s features from its skeleton. In addition, we build neural network in order to help machine learn character specific features and create knowledge databases to help them have ability to classify character with other characters. The recognition accuracy of above 84% is reported on characters from real samples. Using this off-line system and other parts in handwriting text recognition, we can replace or cooperate with online recognition techniques which are ususally applied on mobile devices and extend our handwriting recognition technique on any surfaces such as papers, boards, and vehicle lisences as well as provide the reading ability for humanoid robot.