This paper investigates the use of Euclidean invariant features in a generalization of iterative closest point registration of range images. Pointwise correspondences are chosen as the closest point with respect to a weighted linear combination of positional and feature distances. It is shown that under ideal noise-free conditions, correspondences formed using this distance function are correct more often than correspondences formed using the positional distance alone. In addition, monotonic convergence to at least a local minimum is shown to hold for this method. When noise is present, a method that automatically sets the optimal relative contribution of features and positions is described. This method trades o error in feature values due to noise against error in positions due to misalignment. Experimental results show that using invariant features decreases the probability of being trapped in a local minimum, and is most e ective for di cult registration problems where the scene is very small compared to the model.

This paper addresses the problem of large-scale multiview registration of range images captured from unknown viewing directions. To reduce the computational burden, we separate the local problem of pairwise registration on neighboring views from the global problem of distribution of accumulated errors. We define the global problem as an optimization over the graph of neighboring views, and we show how the graph can be decomposed into a set of cycles such that the optimal transformation parameters for each cycle can be solved in closed form. We then describe an iterative procedure that can be used to integrate the solutions for the set of cycles across the graph of views. This method for error distribution does not require point correspondences between views, and can be used to integrate any method of pairwise registration or robot odometry.

Facial expression recognition is one of the most important tasks in human-computer interaction, affective computing, computer vision, and related work. Feature additive pooling and progressive finetuning of the convolutional neural network (CNN) for facial expression recognition in a static image are introduced. Network is proposed that partially employs the visual geometry group (VGG)-face model pretrained on a VGG-face dataset. The characteristics and distribution of the facial expression images in each database are biased according to the purpose of the publicly available facial database used. To alleviate this problem, a CNN model is developed that merges progressively fine-tuned CNNs into a single network. Experiments were carried out to validate the presented method using facial expression images from the Cohn-Kanade + , Karolinska directed emotional face, and Japanese female facial expression databases, and cross-database evaluation results show that the method is superior to state-of-the-art methods.

Missing data are common in range images, due to geometric occlusions, limitations in the sensor field of view, poor reflectivity, depth discontinuities, and cast shadows. Using registration to align these data often fails, because points without valid correspondences can be incorrectly matched. This paper presents a maximum likelihood method for registration of scenes with unmatched or missing data. Using ray casting, correspondences are formed between valid and missing points in each view. These correspondences are used to classify points by their visibility properties, including occlusions, field of view, and shadow regions. The likelihood of each point match is then determined using statistical properties of the sensor, such as noise and outlier distributions. Experiments demonstrate a high rates of convergence on complex scenes with varying degrees of overlap.

No abstract