Biblio

Due to the continuous improvement of deep learning, saliency object detection based on deep learning has been a hot topic in computational vision. The Fully Convolutional Neural Network (FCNS) has become the mainstream method in salient target measurement. In this article, we propose a new end-to-end multi-level feature fusion module(MCFB), success-fully achieving the goal of extracting rich multi-scale global information by integrating semantic and detailed information. In our module, we obtain different levels of feature maps through convolution, and then cascade the different levels of feature maps, fully considering our global information, and get a rough saliency image. We also propose an optimization module upon our base module to further optimize the feature map. To obtain a clearer boundary, we use a self-defined loss function to optimize the learning process, which includes the Intersection-over-Union (IoU) losses, Binary Cross-Entropy (BCE), and Structural Similarity (SSIM). The module can extract global information to a greater extent while obtaining clearer boundaries. Compared with some existing representative methods, this method has achieved good results.

Anomaly detection is one of the research hotspots in Bitcoin transaction data analysis. In view of the existing research that only considers the transaction as an isolated node when extracting features, but has not yet used the network structure to dig deep into the node information, a bitcoin abnormal transaction detection method that combines the node’s own features and the neighborhood features is proposed. Based on the formation mechanism of the interactive relationship in the transaction network, first of all, according to a certain path selection probability, the features of the neighbohood nodes are extracted by way of random walk, and then the node’s own features and the neighboring features are fused to use the network structure to mine potential node information. Finally, an unsupervised detection algorithm is used to rank the transaction points on the constructed feature set to find abnormal transactions. Experimental results show that, compared with the existing feature extraction methods, feature fusion improves the ability to detect abnormal transactions.

Human computer operations such as writing documents and playing games have become popular in our daily lives. These activities (especially if identified in a non-intrusive manner) can be used to facilitate context-aware services. In this paper, we propose to recognize human computer operations through keystroke sensing with a smartphone. Specifically, we first utilize the microphone embedded in a smartphone to sense the input audio from a computer keyboard. We then identify keystrokes using fingerprint identification techniques. The determined keystrokes are then corrected with a word recognition procedure, which utilizes the relations of adjacent letters in a word. Finally, by fusing both semantic and acoustic features, a classification model is constructed to recognize four typical human computer operations: 1) chatting; 2) coding; 3) writing documents; and 4) playing games. We recruited 15 volunteers to complete these operations, and evaluated the proposed approach from multiple aspects in realistic environments. Experimental results validated the effectiveness of our approach.

When a complex scene such as rotation within a plane is encountered, the recognition rate of facial expressions will decrease much. A facial expression recognition algorithm based on CNN and LBP feature fusion is proposed in this paper. Firstly, according to the problem of the lack of feature expression ability of CNN in the process of expression recognition, a CNN model was designed. The model is composed of structural units that have two successive convolutional layers followed by a pool layer, which can improve the expressive ability of CNN. Then, the designed CNN model was used to extract the facial expression features, and local binary pattern (LBP) features with rotation invariance were fused. To a certain extent, it makes up for the lack of CNN sensitivity to in-plane rotation changes. The experimental results show that the proposed method improves the expression recognition rate under the condition of plane rotation to a certain extent and has better robustness.

In order to improve the limitation of single-mode biometric identification technology, a bimodal biometric verification system based on deep learning is proposed in this paper. A modified CNN architecture is used to generate better facial feature for bimodal fusion. The obtained facial feature and acoustic feature extracted by the acoustic feature extraction model are fused together to form the fusion feature on feature layer level. The fusion feature obtained by this method are used to train a neural network of identifying the target person who have these corresponding features. Experimental results demonstrate the superiority and high performance of our bimodal biometric in comparison with single-mode biometrics for identity authentication, which are tested on a bimodal database consists of data coherent from TED-LIUM and CASIA-WebFace. Compared with using facial feature or acoustic feature alone, the classification accuracy of fusion feature obtained by our method is increased obviously.

The speech emotion recognition accuracy of prosody feature and voice quality feature declines with the decrease of SNR (Signal to Noise Ratio) of speech signals. In this paper, we propose novel sub-band spectral centroid weighted wavelet packet cepstral coefficients (W-WPCC) for robust speech emotion recognition. The W-WPCC feature is computed by combining the sub-band energies with sub-band spectral centroids via a weighting scheme to generate noise-robust acoustic features. And Deep Belief Networks (DBNs) are artificial neural networks having more than one hidden layer, which are first pre-trained layer by layer and then fine-tuned using back propagation algorithm. The well-trained deep neural networks are capable of modeling complex and non-linear features of input training data and can better predict the probability distribution over classification labels. We extracted prosody feature, voice quality features and wavelet packet cepstral coefficients (WPCC) from the speech signals to combine with W-WPCC and fused them by Deep Belief Networks (DBNs). Experimental results on Berlin emotional speech database show that the proposed fused feature with W-WPCC is more suitable in speech emotion recognition under noisy conditions than other acoustics features and proposed DBNs feature learning structure combined with W-WPCC improve emotion recognition performance over the conventional emotion recognition method.