Search

Face anti-spoofing has been attracting attention because of its prominent role in the security of face recognition systems. A face spoofing attack is launched on the authentication system by the attacker using the picture or video of the genuine user to get access to the services or information. This paper proposes local binary pattern (LBP) and convolutional neural network (CNN) based feature fusion model for classifying spoof face images. Initially, the images are pre-processed to remove the effect of the background in the feature extraction. The Viola-Jones algorithm is used for detecting and cropping the faces from the images. The color features of the pre-processed RGB images and LBP features are provided to the CNN. This feature combination reduces the requirement of a CNN-based deep learning architecture for providing a good classification performance. To validate the proposed model, it is trained and tested on NUAA and MSU-MFSD datasets. The experiment recorded the ACER of 0.21 and 0.20 on the MSU-MFSD and NUAA datasets, respectively. [ABSTRACT FROM AUTHOR]

In many machine learning applications and algorithms, the algorithm performance and accuracy are highly dependent on the metric used to measure the distance between different samples. Therefore, learning a distance metric specific to the data can improve these algorithms' performance. This paper proposes an unrestricted deep metric learning framework based on neural networks' interaction for learning metrics in latent space. The proposed method is inspired by generative neural nets (GANs), in which two neural nets are working together to learn true data distribution. In our method, one network plays the role of a supervisor for another network, a feature learning auto-encoder. Its task is to learn transformation to latent space in which data have more meaningful distance and separability. i.e., the supervisor gets the output of the auto-encoder and sends feedback to modify its weights. They interact with each other interleavingly. Several experiments were conducted on four datasets, such as MNIST, GISETTE, Winnipeg Cropland Classification (WCC), and swarm behavior, from different application domains, to evaluate the proposed method's performance. The results show that we can force auto-encoder to learn label information to project data into a latent space with better separability by using our approach. In addition to better class discrimination, the proposed method is far faster than normal auto-encoders during feature learning and has much less training time in the classification phase. [ABSTRACT FROM AUTHOR]

In this paper, an improved algorithm based on Yolo V3 is proposed, which can effectively improve the accuracy of small target detection. First of all, the feature map acquisition network is improved. The image double-segmentation and bilinear upsampling network are used to replace the 2-step downsampling convolution network in the original network architecture, and the feature values of large and small objects are amplified. Secondly, a size recognition module is added to the input image to reduce the loss of morpheme features caused by no-feature value filling and enhance the recognition ability of small objects. Thirdly, in order to avoid the gradient fading of the network, the residual network element of the output network layer is added to enhance the feature channel of small object detection. Compared with Yolo V3, our algorithm improves the detection accuracy of small objects from 82.4 to 88.5%, the recall rate from 84.6 to 91.3%, and the average accuracy from 95.5 to 97.3%, respectively. [ABSTRACT FROM AUTHOR]

In this paper an unsupervised on-line deep learning algorithm for action recognition in video sequences is proposed. Deep learning models capable of deriving spatio-temporal data have been proposed in the past with remarkable results, yet, they are mostly restricted to building features from a short window length. The model presented here, on the other hand, considers the entire sample sequence and extracts the description in a frame-by-frame manner. Each computational node of the proposed paradigm forms clusters and computes point representatives, respectively. Subsequently, a first-order transition matrix stores and continuously updates the successive transitions among the clusters. Both the spatial and temporal information are concurrently treated by the Viterbi Algorithm, which maximizes a criterion based upon (a) the temporal transitions and (b) the similarity of the respective input sequence with the cluster representatives. The derived Viterbi path is the node's output, whereas the concatenation of nine vicinal such paths constitute the input to the corresponding upper level node. The engagement of ART and the Viterbi Algorithm in a Deep learning architecture, here, for the first time, leads to a substantially different approach for action recognition. Compared with other deep learning methodologies, in most cases, it is shown to outperform them, in terms of classification accuracy. [ABSTRACT FROM AUTHOR]