faces and Caltech Faces 1999 (CF). Good result on these dataset has encouraged us to conduct tests on Labeled Faces in the Wild (LFW), where the images were taken from real-world condition. Mean average precision (MAP) was used for measuring the performance of the system. We carry out the experiments in two main stages indexing and searching with the use of k-fold cross-validation. We further boost the system by using Locality Sensitive Hashing (LSH). Furthermore, we also evaluate the impact of LSH on the searching stage. The experimental results have shown that LSH is effective for face searching as well as LBP is robust feature in fontal face retrieval.
Recognizing human action is valuable for many real world applications such as video surveillance, human computer interaction, smart home and gaming. In this paper, we present a method of action recognition based on hypothesizing that the classification of action can be boosted by motion information using optical flow. Emergence of automatic RGBD video analysis, we propose fusing optical flow is extracted from both RGB and depth channels for action representation. Firstly, we extract optical flow from RGB and depth data. Secondly, motion descriptor with spatial pyramid is computed from histogram of optical flow of RGB and depth. Then, feature pooling technique is used in order to accumulate RGB and depth feature into set of feature vectors for each action. Finally, we use the Multiple Kernel Learning (MKL) technique at the kernel level for action classification from RGB and depth feature pooling. To demonstrate generalizability, our proposed method has been systematically evaluated on two benchmark datasets shown to be more effective and accurate for action recognition compared to the previous work. We obtain overall accuracies of: 97.5 % and 92.8 % with our proposed method on the 3D ActionPairs and MSR-Daily Activity 3D dataset, respectively.
Abstract-Static hand gesture recognition is an interesting and challenging problem in computer vision. It is considered a significant component of Human Computer Interaction and it has attracted many research efforts from the computer vision community in recent decades for its high potential applications, such as game interaction and sign language recognition. With the recent advent of the cost-effective Kinect, depth cameras have received a great deal of attention from researchers. It promoted interest within the vision and robotics community for its broad applications. In this paper, we propose the effective hand segmentation from the full depth image that is important step before extracting the features to represent for hand gesture. We also represent the novel hand descriptor explicitly encodes the shape and appearance information from depth maps that are significant characteristics for static hand gestures. We propose hand descriptor based on Polar Transformation coordinate is called Histogram of Polar Transformation (HPT) in order to capture both shape and appearance. Beside a robust hand descriptor, a robust classification model also plays a very important role in the hand recognition model. In order to have a high performance in recognition rate, we propose hybrid model for classification based on Sparse Auto-encoder and Deep Neural Network. We demonstrate large improvements over the state-ofthe-art methods on two challenging benchmark datasets are NTU Hand Digits and ASL Finger Spelling and achieve the overall accuracy as 97.7% and 84.58%, respectively. Our experiments show that the proposed method significantly outperforms stateof-the-art techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.