Automatic detection and classification of dynamic hand gestures in real-world systems intended for human computer interaction is challenging as: 1) there is a large diversity in how people perform gestures, making detection and classification difficult, 2) the system must work online in order to avoid noticeable lag between performing a gesture and its classification, in fact, a negative lag (classification before the gesture is finished) is desirable, as feedback to the user can then be truly instantaneous. In this paper, we address these challenges with a recurrent three-dimensional convolutional neural network that performs simultaneous detection and classification of dynamic hand gestures from multi-modal data. We employ connectionist temporal classification to train the network to predict class labels from inprogress gestures in unsegmented input streams. In order to validate our method, we introduce a new challenging multimodal dynamic hand gesture dataset captured with depth, color and stereo-IR sensors. On this challenging dataset, our gesture recognition system achieves an accuracy of 83:8%, outperforms competing state-of-the-art algorithms, and approaches human accuracy of 88:4%. Moreover, our method achieves state-of-the-art performance on SKIG and ChaLearn2014 benchmarks.

Driver distraction is a serious threat to automotive safety. The visual-manual interfaces in cars are a source of distraction for drivers. Automotive touch-less hand gesture-based user interfaces can help to reduce driver distraction and enhance safety and comfort. The choice of hand gestures in automotive interfaces is central to their success and widespread adoption. In this work we evaluate the recognition accuracy of 25 different gestures for state-of-the-art computer vision-based gesture recognition algorithms and for human observers. We show that some gestures are consistently recognized more accurately than others by both vision-based algorithms and humans. We further identify similarities in the hand gesture recognition abilities of vision-based systems and humans. Lastly, by merging pairs of gestures with high miss-classification rates, we propose ten robust hand gestures for automotive interfaces, which are classified with high and equal accuracy by vision-based algorithms.

We introduce a method for accurate three dimensional head pose estimation using a commodity depth camera. We perform pose estimation by registering a morphable face model to the measured depth data, using a combination of particle swarm optimization (PSO) and the iterative closest point (ICP) algorithm, which minimizes a cost function that includes a 3D registration and a 2D overlap term. The pose is estimated on the fly without requiring an explicit initialization or training phase. Our method handles large pose angles and partial occlusions by dynamically adapting to the reliable visible parts of the face. It is robust and generalizes to different depth sensors without modification. On the Biwi Kinect dataset, we achieve best-in-class performance, with average angular errors of 2.1, 2.1 and 2.4 degrees for yaw, pitch, and roll, respectively, and an average translational error of 5.9 mm, while running at 6 fps on a graphics processing unit.

We introduce a new measure of image similarity called the complex wavelet structural similarity (CW-SSIM) index and show its applicability as a general purpose image similarity index. The key idea behind CW-SSIM is that certain image distortions lead to consistent phase changes in the local wavelet coefficients, and that a consistent phase shift of the coefficients does not change the structural content of the image. By conducting four case studies, we have demonstrated the superiority of the CW-SSIM index against other indices (e.g., Dice, Hausdorff distance) commonly used for assessing the similarity of a given pair of images. In addition, we show that the CW-SSIM index has a number of advantages. It is robust to small rotations and translations. It provides useful comparisons even without a preprocessing image registration step, which is essential for other indices. Moreover, it is computationally less expensive.

Assessment of classifier performance is critical for fair comparison of methods, including considering alternative models or parameters during system design. The assessment must not only provide meaningful data on the classifier efficacy, but it must do so in a concise and clear manner. For two-class classification problems, receiver operating characteristic analysis provides a clear and concise assessment methodology for reporting performance and comparing competing systems. However, many other important biomedical questions cannot be posed as "two-class" classification tasks and more than two classes are often necessary. While several methods have been proposed for assessing the performance of classifiers for such multiclass problems, none has been widely accepted. The purpose of this paper is to critically review methods that have been proposed for assessing multiclass classifiers. A number of these methods provide a classifier performance index called the volume under surface (VUS). Empirical comparisons are carried out using 4 three-class case studies, in which three popular classification techniques are evaluated with these methods. Since the same classifier was assessed using multiple performance indexes, it is possible to gain insight into the relative strengths and weakness of the measures. We conclude that: 1) the method proposed by Scurfield provides the most detailed description of classifier performance and insight about the sources of error in a given classification task and 2) the methods proposed by He and Nakas also have great practical utility as they provide both the VUS and an estimate of the variance of the VUS. These estimates can be used to statistically compare two classification algorithms.

We present a promising analysis on using the pattern of symmetry in the face to increase the accuracy of three-dimensional face recognition. We introduce the concept of the dasiaaverage-half-facepsila, motivated by the symmetry preserving singular value decomposition. We compare face recognition results using the eigenfaces face recognition algorithm with average-half-face data and full face data in several experiments on a 3D face data set of 1126 images. We show that the results from the eigenfaces face recognition system using the average-half-face is more accurate than using the full face, only the left or right half of the face or a random choice of half of the face.

We present a systematic procedure for selecting facial fiducial points associated with diverse structural characteristics of a human face. We identify such characteristics from the existing literature on anthropometric facial proportions. We also present three dimensional (3D) face recognition algorithms, which employ Euclidean/geodesic distances between these anthropometric fiducial points as features along with linear discriminant analysis classifiers. Furthermore, we show that in our algorithms, when anthropometric distances are replaced by distances between arbitrary regularly spaced facial points, their performances decrease substantially. This demonstrates that incorporating domain specific knowledge about the structural diversity of human faces significantly improves the performance of 3D human face recognition algorithms.

We propose a novel 3D face recognition algorithm based on facial range image matching using the complex wavelet structural similarity metric (CW-SSIM) metric. Compared with many existing 3D surface matching methods, CW-SSIM is computationally efficient and is robust to small geometrical distortions. Using a data set that contains 360 3D face models of 12 subjects, we tested the performance of the proposed method and compared it with existing 3D surface matching based face recognition algorithms. Verification and identification performance of each algorithm was evaluated by means of the receiver operating characteristic curve and the cumulative match characteristic curve. Among the algorithms tested, the proposed algorithm based on the CW-SSIM resulted in the best overall performance with an equal error rate of 9.13% and a rank 1 recognition rate of 98.6%, significantly better than all the other algorithms. Besides the introduction of a novel approach for 3D face recognition, this is also the first attempt to expand the application scope of complex wavelet domain similarity measure to range image matching in general