Sorry, you need to enable JavaScript to visit this website.

In this paper, we presented an automatic method for BVS struts detection in IVOCT images based on Haar-like features and Adaboost algorithm. Then, DP algorithm was used for struts segmentation. Based on the detection and segmentation results, apposed and malapposed struts were distinguished automatically. The qualitative and quantitative evaluation shows that our method is effective and robust for BVS struts detection and segmentation, and is capable of malapposition analysis.

We present an image-based approach to generate truly random numbers from the surface of water bodies such as oceanic bays. As a natural phenomenon, wind-generated gravity waves have non-deterministic behavior. We use the randomness of the angular relation between pairs of estimated surface normals to generate uniformly distributed random binary digits and build random numbers from those digits. Our approach produces compelling geometric models of water surfaces and generates random numbers with high entropy.

Depth maps captured by RGB-D cameras are often noisy and incomplete at edge regions. Most existing methods assume that there is a co-occurrence of edges in depth map and its corresponding color image, and improve the quality of depth map guided by the color image. However, when the color image is noisy or richly detailed, the high frequency artifacts will be introduced into depth map. In this paper, we propose a deep residual network based on deep fusion and local linear regularization for guided depth enhancement.

Visual context has formed a robust stimulation for visual perception. Spatio-temporal context in existing trackers sometimes shows weak reliability in visible light videos with poor quality. Supplemented by the infrared perception, this work exploits the role of visual context in tracking in a spatial-sequential-spectral view, by which to excavate dominance of different contexts in various scenarios.

In motion compensated frame interpolation, a repetition
pattern in an image makes it difficult to derive an accurate
motion vector because multiple similar local minima exist in
the search space of the matching cost for motion estimation.
In order to improve the accuracy of motion estimation in a
repetition region, this paper attempts a semi-global approach
that exploits both local and global characteristics of a
repetition region. Experimental results demonstrate that the
proposed method significantly outperforms the previous local

The topological derivative (TD) for shape analysis has been employed
in image segmentation, and machine learning schemes based on
convolutional neural network (CNN) provide the high performance in
the image processing. The supervised and unsupervised approaches
have different roles and advantages according to their concepts. To
maximize the benefits of two approaches, we propose CNN-TD based
segmentation approach. A CNN-based segmentation scheme is employed
to faithfully consider the characteristics of an object to be