Search

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Although high-quality and high-resolution depth maps can significantly improve the performance of computer vision tasks in various natural scenes, the limitations of depth camera hardware make the depth maps captured by consumer-level depth cameras have problems such as low resolution, poor quality, invalid holes, etc. Depth super-resolution reconstruction (DSR) is a kind of technology that can effectively improve the resolution and quality of depth maps, and DSR has become a research hot-spot in the field of computer vision. Firstly, this paper introduced the definition of DSR and the research progress of DSR algorithm at home and abroad in recent years, and then mainly stated and analyzed deep learning DSR reconstruction algorithms. Next, it introduced the depth image quality evaluation criteria. Finally, this paper prospected the application fields of DSR and the challenges as well as the opportunities in the future. [ABSTRACT FROM AUTHOR]

Copyright of Application Research of Computers / Jisuanji Yingyong Yanjiu is the property of Application Research of Computers Edition and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The image rain removal algorithm analyzes and processes rain images to remove rain streaks and restore clean background scenes, which helps to improve the recognition accuracy of computer vision task, so that it becomes a hot spot in current research. In order to systematically understand the current research status and development trends in this field. Firstly, this paper introduced some typical synthetic rain models. Secondly, it analyzed typical image rain removal algorithm models and methods from two aspects, such as model-driven and data-driven. Then it compared the algorithm evaluation metrics and public rain datasets respectively. Finally, this paper prospected the future development trend of single image rain removal algorithms. [ABSTRACT FROM AUTHOR]

In order to improve the training speed and certain classification accuracy of CNN in the image classification, this paper started from BN, adjusted the affine transform of BN by adding new parameters, and proposed an improved BN, called BNalpha. Except fo r the neural networks with some specific structures, compared with the original BN, BNalpha could improve the training speed and certain classification accuracy of general neural networks without increasing the computational complexity. By analyzing and comparing the parameters of BN affine transform, this paper tried to explain the operation mechanism of BN partially, and conducted contrast experiment which covering different periods during training to illustrate that BNalpha was superior to the original BN. Based on the CIFAR-10 and CIFAR-100 datasets, by using various types of CNN structures, it compared and analyzed BNalpha and BN, and the experimental results verify that BNalpha can further improve the training speed and certain classification accuracy. [ABSTRACT FROM AUTHOR]

Aiming at the traditional model parallel methods for accelerating convolution neural network (CNN) tend to have low utilization, this paper proposed PipeCNN, which accelerated CNN with software pipeline. Firstly, this paper studied the forward propagation and back propagation, and then explored data correlation during training. Secondly, it parallelized CNN with the support of software pipeline, and then analyzed two feasible gradient updating methods in PipeCNN. Finally, it used circular queue to realize communication between two layers and then proposed a task allocation algorithm to divide CNN into working parts. Experiments show that the method can obtain good speedup and utilization while ensuring the accuracy of the model. It shows that software pipeline can effectively solve the problem of low utilization in model parallel, and accelerate the training of CNN. [ABSTRACT FROM AUTHOR]

Expert recommendation is one of the research hotspots in the online Q&A community. However, the majority of the currently used algorithms concentrate on matching user's static interest and question information, ignoring the efficient capture of user' s dynamic interest representation information, which results in a lack of recommendation accuracy. In order to address the aforementioned issues, this paper proposed an expert recommendation algorithm for the Q&A community that incorporated multi-head self-attention. Firstly, this algorithm built out question encoders of convolutional neural networks and attention mechanisms to process target question and user' s historically answered questions, in order to extract the corresponding question representations. Secondly, it treated the sequence of user's historically answered questions as a time series and used the multi-head self-attention mechanism to learn the dynamic interest representations hidden in the sequence, and combined with the user' s static interest representations to obtain the user' s comprehensive interest representations. Finally, it calculated the similarity between the target question representation and the comprehensive user representation to generate recommendation results. Based on the real data from the Zhihu Q&A community, the experimental results show that the performance of this algorithm is significantly better than the current popular expert recommendation algorithm. [ABSTRACT FROM AUTHOR]

Traditional image inpainting algorithms cannot accurately capture high-level semantics when regions involve complex non-repetitive structures, such as faces. In the past three years, the method based on deep learning has been applied to image inpainting, and the structural similarity of the repair results had increased by more than 10% compared with the traditional methods. This paper firstly expounded the research and development process of facial completion technologies, mainly introduced the face repair algorithm based on deep learning, which was divided into unsupervised and supervised categories. In each category, it focused on the various facial completion algorithm ideas that had emerged in recent years. Then it summarized the six mainstream types of image datasets. Two evaluation indexes were summarized in this paper. Finally, it discussed the future research direction of facial completion technique. [ABSTRACT FROM AUTHOR]

To solve the problems that the objects with different semantic classes are identified as co-salient objects in current co-saliency detection methods, this paper proposed a CNN and semantic correction-based co-saliency detection method (CSCCD). The proposed method first adopted the guided super pixel filter to process the super pixels obtained by SLIC and the saliency results generated by DSS, which showed clear object boundaries. Then it utilized Mask R-CNN to extract semantic features. It proposed the definitions of image semantic feature and semantic consistency. It also defined the image group semantic correction to solve the problem that detected the objects with different pose belonging to a semantic class as different semantic classes. With the concept, this paper defined image group semantic correlation class, solving semantic correlation problem of multiple images. It generated the final co-saliency detection results by fusing the saliency detection regions with the image group semantic consistent regions. The experimental results on public benchmark datasets show that this algorithm can effectively highlight the whole and outline of the object, and its comprehensive performance in objective quantification is obviously improved. [ABSTRACT FROM AUTHOR]

At present, super-resolution method based on CNN can obtain excellent results in the evaluation metric of peak signal- to-noise ratio and the structural similarity index, but the visual perceptual quality of super- resolution image is poor, and the details of the facial features are lost. In order to solve these problem, this paper designed a new deep neural network to predict the super-resolution wavelet coefficients to get clear super-resolution face images . Firstly, it used the prior knowledge of face images to manually give the facial features more attention. Then it introduced linear low-rank convolution in the network, and finally used the idea of long-distance dependence to supplement the details of the super-resolution images. The experimental results show that the method in this paper has achieved competitive results in the evaluation metric of peak signal-to-noise ratio and structural similarity index, and the visual perceptual quality of its super-resolution face images are excellent. [ABSTRACT FROM AUTHOR]

Aiming at the problem of poor diagnosis ability and generalization ability of the trained model caused by serious imbalance of bearing fault data, this paper proposed a method of generative adversarial networks based on Wasserstein distance to balance dataset. Firstly, it trained a small number of fault samples for adversarial training. Then when the network reached the Nash equilibrium, it added the generated fault samples to the original small number of fault samples to balance the dataset. This paper proposed a diagnostic model based on global average pooled convolutional neural network. The balanced data set was input into the diagnostic model for training. The model was adaptively extracted layer by layer to achieve accurate classification diagnosis of faults. The experimental results show that the proposed diagnostic method is superior to other algorithms and models, and has strong generalization ability and robustness. [ABSTRACT FROM AUTHOR]

Traditional manually designed feature descriptors are prone to cause a large number of mismatches in the face of multi temporal remote sensing images with large geometric and radiation differences and obvious changes in ground features. This paper developed a convolutional neural network matching algorithm with double screening and proposed double constraints to extract the deep semantic feature map of the image through CNN, it selected the key points that satisfied both the priority maximum principle and the precise extreme value principle from the feature map, and extracted 512-dimension descriptors from the corresponding positions. In the feature matching stage, the strategy of combining the rough to fine reverse matching constraints and RANSAC constraints ensured that the false matching points were eliminated effectively, and retained a certain number of correct matching points, which improved the matching accuracy. The experimental results show that the number of matches is moderate, the correct matching rate is improved compared with other algorithms selected in the experiment, and the image registration error is reduced by about 2 pixels. The running time is obviously improved, matching effect is good, with certain adaptability and robustness. [ABSTRACT FROM AUTHOR]

Aiming at the knowledge overload in the process of online learning and the problems of data sparsity and cold start in the traditional recommendation algorithm, this paper proposed an improved learning resource recommendation algorithm based on MLP. The algorithm used the advantage of MLP in nonlinear data processing, converted the prediction mode of vector multiplication of learner characteristics and learning resource characteristics into the input mode of MLP, and improved the DN-CBR neural network recommendation model. In order to verify the effectiveness of the model, this paper built a dataset with the online learning platform data of iCourse as the sample. Compared with DN-CBR model, the improved model improves the normalized cumulative loss gain and hit rate by 1. 2 % and 3 % respectively on the dataset, which effectively improves the recommendation performance of the model. [ABSTRACT FROM AUTHOR]

Firstly, this paper reviewed the development of computer vision, presented the elementary knowledge of neurons, multi-layer perceptron, back-propagation algorithm, and the development of convolutional neural network (CNN) and its basic operation of convolution and pooled etc. Secondly, it discussed the structures of typical convolutional neural networks such as AlexNet, VGGNet, GoogLeNet and ResNet etc., and mainly introduced CapsNet. And then it summaried the research progress of the application of CNN in image classification, image semantic segmentation, image target detection and image generation. At last, this paper presented the research challenge of CNN and the future next work for CapsNet. [ABSTRACT FROM AUTHOR]

A variety of Chinese characters is an important Chinese cultural symbol. Its design and operation are a hard work requiring a lot of professional knowledge. Therefore, for this work, this paper proposed a new method of Chinese fonts style transfer based on generative adversarial networks. In the experiment, it used a generative model based on the residual network structure and performed the adversarial training between the generative model and the discriminative model under the constraint of mean square error. At last, the trained generative model could be used to implement one-to-one and many-to-many style transfer between different Chinese fonts. Experiments show that,compared with the usual l1regularization method used before, the method in this paper has better performance in fonts detail generation, simplifies Chinese fonts modeling, improves the fidelity of generated images, and has better flexibility and versatility. [ABSTRACT FROM AUTHOR]

For the traditional objective function based on the minimum classification error criterion ( MCE ), there exists the problem of gradient inversion in the network when the sample is misclassified. This paper introduced the minimum classification error criterion and defined the FMCE objective function with correction term. This paper used the higher precision cross entropy as a basis function and FMCE as a correction function, and proposed an improved cross entropy objective function CE-FMCE, which made the network increase the probability of label class output in the reverse propagation process. CE-FMCE not only overcame the gradient inversion problem of the traditional MCE objective function, but also compensated for the lack of differentiation of the cross entropy function for non-label set gradients. This paper compared CE-FMCE with MSE, cross entropy, MCE, and M3 CE on self-built typhoon image dataset and general dataset MNIST. The experimental results show that CE-FM CE is superior to other objective functions. [ABSTRACT FROM AUTHOR]

Due to the low randomness of character distribution and high randomness of word combination in word-based DGA domain names, the traditional detection methods are difficult to identify them. The method based on deep learning such as LSTM can capture domain's sequence features, but it lacks the word combination features and has low detection accuracy. In order to solve above problems, this paper proposed a new DGA domain name detection method based on fusion embedding layer. In domain embedding stage, it carried out a fusion vector representation based on characters and word segmentation technology . Then, it constructed a hybrid deep learning model based on CNN and BiGRU. The experimental results show that the proposed model has increased by 3 . 1 % and 4. 3% respectively in accuracy compared with the models based on CNN or LSTM alone. When dealing with the matsnu, suppobox and ngioweb DGAs, the proposed model is more effective. [ABSTRACT FROM AUTHOR]

Aiming at the problem of time-consuming,complex feature extraction and low recognition rate,this paper introduced the convolution neural network method based on deep learning. This method was widely used in the field of image recognition because of its good robustness, strong generalization ability and high recognition rate. In classification experiments of the 4 main vehicle types (bus, microbus, car, truck) on road, the improved convolution neural network LeNet-5 achieved vehicle type training and test accuracy both over 98% , which outperformed traditional SIFT -I- SVM algorithm. In addition, this paper also studied the effect of the Dropout layer in improved network on the vehicle type recognition. Compared with the traditional algorithm, the improved convolution neural network LeNet-5 has a significant improvement in reducing the detection time and improving the recognition rate,and has obvious advantages in vehicle type recognition. [ABSTRACT FROM AUTHOR]

With the increase of training data and the improvement of the performance of computers, the CNN-based object detection breaks the bottleneck of traditional object detection and has been the main method of current object detection. Therefore, it is a significant research that how to effectively utilize CNN for object detection. Firstly, this paper reviewed how to solve the problems of traditional object detection by CNN. Secondly, it introduced the basic architecture of CNN and described the current research development and widely-used CNN. Thirdly, this paper mainly analyzed and discussed two kinds of ideas and methods of the CNN-based object detection and pointed out the present deficiency. Finally, it concluded the CNN-based object detection and the future direction. [ABSTRACT FROM AUTHOR]

Because convolutional neural networks( CNN) mostly focus on global feature learning and ignore local feature information containing more details, it is difficult to improve the accuracy of indoor scene recognition. To solve this problem, this paper proposed an indoor scene recognition method based on improved global-local attention network ( GLANet). Firstly, it used GIAN et to capture the global and local features of the scene image to increase the detail information of the image features. Then, it introduced a non-local attention module into the local network to further preserve the detail features of the image through the convolution of attention diagram and feature graph. Finally, it used various features of different stages of the network for classification. Through training and verification on the MIT lndoor67 and the SUN397 dataset, the recognition accuracy of the proposed method was increased by l. 98% and 3. 07% respectively compared with the LGN method. Experimental results show that the algorithm can effectively capture global semantic information and fine spatial details, and significantly improves the recognition accuracy. [ABSTRACT FROM AUTHOR]

Most of the current fake face detection technologies use deep learning to identify the feature differences between real videos and fake videos, and have achieved good results on uncompressed videos. But the detection performance on compressed video will be severely reduced. Therefore, this paper proposed a fake face video detection method based on improved triplet loss to tackle the above problem. Firstly, it used an artifact map generated by the artifact map generator to deepen the feature difference between the fake face and the real face. Secondly, it used improved triplet loss to solve the problem of hard samples that were difficult to detect correctly. Finally, it chose a deep learning network that was more suitable for fake face detection to extract convolutional features. Experiments on the FaceForensics++ dataset show that proposed method is better than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In order to ensure the normal operation of the equipment and to predict the remaining life of the bearing, this paper proposed a life prediction model based on the combination of two-dimensional convolutional neural network and an improved WaveNet. To overcome the gradient vanishing problem of the unoptimized recurrent networks in the process of prediction training, the WaveNet time-series networks structure was introduced into the model. Aiming at the situation that the original WaveNet structure was not suitable for rolling bearing vibration data, the improved WaveNet structure combined with two-dimensional convolutional neural networks was applied to the life prediction of rolling bearing. The model extracted the features of one-dimensional vibration sequence using two-dimensional convolutional networks, and then input the features to the WaveNet to predict the remaining life of the rolling bearing. Compared with the deep recurrent networks, the combined model has higher computational efficiency and more accurate results. Compared with the CNN-WaveNet-0 model, the improved model has more accurate prediction results. Compared with the deep long short-term memory networks model, the root mean square error of the prediction results of this model is reduced by 11.04%, and the scoring function of the prediction results is reduced by 11.34% . [ABSTRACT FROM AUTHOR]

This paper tried to propose a method to solve the problem of sentiment classification by integrating word embedding and convolutional neural network (CNN). First of all, the method accomplished a training process with skip-gram model to generate word embedding of each word in the dataset. Then, it created a two-dimensional feature matrix which was the combination of word embedding of each word in a training sample as the input of CNN model. Each iteration process of training, entries of feature matrix would also update as part of model parameters. Secondly, this paper proposed a CNN structure which was mainly composed of three different sizes of convolution kernels so as to complete the automatic extraction process of a variety of local abstract features. Compared with traditional machine learning algorithms, the proposed word embedding and CNN based sentiment classification model has successfully improved classification accuracy by 5.04%. [ABSTRACT FROM AUTHOR]

Due to the small amount of microscopic features image data of traditional Chinese medicinal materials powder, unbalanced distribution of sample classes and small difference between classes, it is difficult to achieve a satisfying classification effect through traditional image classification methods. To solve the above problems,this paper proposed an improved method of deep convolution neural network based on dynamic ReLU and attention mechanism model. Firstly, it used Xception as the basic network, which had an obvious effect on small sample data classification. Secondly, it replaced the static ReLU activation function in the network with the improved dynamic ReLU function, so that each sample had its own unique ReLU parameters. Finally, it embedded the improved SE module in the network to enable the network to learn the importance of each feature channel automatically. The proposed method can make the network pay more attention to the detailed information in the image, and can solve the problem of unbalanced distribution of sample classes and small differences between classes. The experimental results show that the image classification accuracy of 56 kinds of traditional Chinese medicinal materials powder vessel is increased by about 1.5% to 93.8%, which demonstrates that the proposed method is advantageous over other image classification methods. [ABSTRACT FROM AUTHOR]

Radar echo extrapolation has been widely used in short-term heavy precipitation nowcasting. Aiming at the problem that traditional radar echo extrapolation methods do not make full use of massive historical meteorological data, which leads to low forecast accuracy, this paper proposed a new radar echo extrapolation method based on DPCNN. With the addition of dynamic probability calculation layer, DPCNN was able to calculate the corresponding probability convolution kernel for different radar echo input sequences and used it in the subsequent extrapolation calculations. Dynamic probability calculation layer enabled the network to make corresponding probability adjustments according to different input sequences in the prediction stage and enhance the connection between extrapolation and input sequences. The extrapolation experiment of short-term heavy precipitation in a certain area verifies the validity of the model from four aspects: extrapolated image, CSI, FAR, and POD. [ABSTRACT FROM AUTHOR]

Face makeup transfer refers to the task of transferring reference makeup to people’s face while keeping the features of people’s face and showing the style of the reference makeup as much as possible. The current methods of transferring facial makeup do not fully consider the facial differences,it causes the problems such as insufficient extracted facial information. In order to avoid such problems and realize automatic transferring of face makeup,this paper proposed a face makeup transfer algorithm based on deep convolutional neural network. First,the algorithm automatically located the people’s face and features of reference makeup,and extracted the feature information of key parts. After the autonomous training of deep convolutional neural network,it automatically transferred the reference makeup to people’s face through the makeup transfer network and loss function. The simulation result shows that the algorithm takes less time,has more advantages in computing performance,and makeup transfer effect is more natural without changing the details of the original facial features. [ABSTRACT FROM AUTHOR]

Aiming at the problems that the existing human motion recognition methods based on deep learning have large parameters and the networks were too deep and heavy, this paper proposed a lightweight two-steam fusion deep neural network model and applied this model to human action recognition. This model combined a shallow multi-scale network with a deep network, and achieved a significant reduction in the amount of model parameters and avoided the problem that network was too deep. Experiments were performed on datasets UCFlOl and HMDB51, achieving 94.0% and 69.4% recognition accuracy in ImageNet pre-training mode, respectively. Experiments show that compared with the existing human motion recognition models based on deep learning, this model greatly reduces the parameter quantity and still has high motion recognition accuracy. [ABSTRACT FROM AUTHOR]

Considering the performance deterioration of OFDM system due to narrowband interference( NBI), this paper employed deep learning into NBI mitigation of OFDM systems and proposed two structures with CNN. These two structures firstly pre-processed the received data in receiver, then adopted CNN to exploit the interference estimation in time domain. Finally it removed the impact of NBI from received signal. The simulation results demonstrate that the two systems can learn the interference effectively and improve system performance. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing target detection framework based on big data and deep learning is difficult to realize real-time video target detection on low-power mobile and embedded devices, this paper improved the target detection framework SSD based on deep learning, and put forward an improved multi-target detection framework LSTM-SSD which was dedicated to multi-target detection of traffic scenes video. Combining single image detection frame with recursive neural network LSTM network to form an interleaved circular convolution structure, it realized the temporal association of network framelevel information by extracting the feature map between propagation frames by adopting a Bottleneck-LSTM layer, which greatly reduced the network calculation cost. Combining the time-aware information with the improved dynamic Kalman filtering algorithm, the tracking and identification of the targets which were influenced by strong interference such as light change and largearea occlusion in the video could be realized. Experimental results show that the improved LSTM-SSD can achieve good results when dealing with the difficult detection situations such as multi-targets, cluttered background, light changes, fuzziness and large-area occlusion. Compared with other target detection frameworks based on deep learning, the average accuracy rate of all kinds of target identification is increased by 5% - 16%, the average accuracy rate is increased by 4% - 10%, the multi-target detection rate is increased by 4% - 19%, and the detection frame rate reaches 43 fps, basically meeting the requirements of real-time . The balance between the accuracy of the algorithm and the running speed is achieved, and a good detection and identification effect is achieved. [ABSTRACT FROM AUTHOR]

The purpose of target-specific affective analysis is to predict the sentiment of a text from the perspective of different target words. The key is to assign appropriate affective words to a given target. When there are more than one affective word describing multiple target sentiments in a sentence, it may lead to the mismatch between the affective word and the target. This paper proposed a hybrid neural network based on CRT mechanism for target-specific sentiment analysis. The model used CNN layer to extract features from the word representation after BiLSTM transformation. It generated the specific target representation of the word by CRT component and saved the original context information from BiLSTM layer. Experiments on three open datasets show that the proposed model can significantly improve the accuracy and stability of target-specific affective analysis tasks compared with previous models. It is proved that the CRT mechanism can integrate the advantages of CNN and LSTM well, which is of great significance to the task of sentiment analysis for specific targets. [ABSTRACT FROM AUTHOR]

The traditional sentence classification model has many disadvantages such as complex feature extraction process and low classification accuracy. This paper used the advantages of the popular deep learning model based convolutional neural network in feature extraction, combined with the traditional sentence classification method, proposed a sentence classification model based on convolutional neural network and Bayesian classifier. The model first used convolutional neural network to extract text features, and secondly used principal component analysis method to reduce the dimensionality of text features. Finally, Bayesian classifier were used to classify sentences. The experimental results show that on Cornell University's public film review dataset and Stanford Sentiment Treebank dataset, the proposed model is superior to the model using only deep learning or the traditional sentence classification model. [ABSTRACT FROM AUTHOR]

The problem that the recognition rate of handwritten Chinese characters is affected by random noise, this paper proposed a new algorithm based on deep learning and noise suppression. This algorithm was mainly aimed at handwritten Chinese character characters and pictures with random noise. It was a model that used Caffe platform to establish noise suppression and convolutional neural networks in the Python environment. It removed noise and correctly recognized handwritten Chinese characters. In addition, the new algorithm did not change the character while removing noise, and retained the original Chinese character information. As a result, the noise intensity of two different types of noise (Gaussian noise and salt-and-pepper noise) was gradually increased, it performed multiple experiments and compared them with other methods, the average recognition rate was 97. 05%. The experimental results show that the model and algorithm have the advantages of high efficiency and strong recognition ability. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing human motion recognition method needed to input a fixed length video segment and underutilized the spatio-temporal information, this paper proposed a deep neural network model based on the combination of space-time pyramid and attention mechanism. This improved architecture combined 3D-CNN including spatio-temporal pyramids with LSTM model with spatio-temporal attention mechanism, and realized multi-scale processing of video segments and full utilization of complex spatio-temporal information of actions. For the architecture, the inputs of spatial and temporal domain were RGB image and the optical flow, the input of the fusion domain was the fusion feature of the motion and appearance features of the pyramid pooling layer. Finally, it used the decision fusion strategy to obtain the final motion recognition result. Experiments were performed on the UCFlOl and HMDB51 datasets, it achieved 94. 2% and 70. 5% recognition accuracy, respectively. The experimental results show that the improved network model achieves high recognition accuracy in video based human motion recognition tasks. [ABSTRACT FROM AUTHOR]

Current salient object detection algorithms based on deep neural network ( DNN) are usually not able to be aware of the structure of instance, making the generated saliency maps fail to cover the entire salient object region, thus drag down the accuracy. To solve this problem, this paper introduced a novel multi-stream deep neural network, which integrated four components in a single framework, feature extractor, object skeleton sub-network, salient object sub-network and cross-domain connections. Firstly, during the learning and testing process, the salient object detection sub-network encoded the object structure which was extracted by using object skeleton detection sub-network through the cross-domain connections, so as to make the deep model be aware of the information of object structure and overcome the problem of incomplete detection of the target area. Then, to further improve the accuracy, it used a dense conditional random field based algorithm as the refinement post-process, so as to generate a more accurate saliency map as the final results. Experimental evaluations were conducted on three widely-used benchmarks. The results show that the proposed algorithm outperforms all existing DNN-based detection algorithms in accuracy and efficiency. It also indicates that integrating object structure information into deep neural network model is meaningful, which can help to improve the overall accuracy. [ABSTRACT FROM AUTHOR]

To improve the accuracy of the pedestrian detection method. this paper proposed a rectangular input of convolution neural network enhance the new pedestrian detection method based on the depth residual network and YOLO object detection method. The rectangular input helped the model gain the pedestrian characteristics expression by analyzing the expression and distribution characteristics of pedestrians in the images. The depth residual network with pre-activation for YOLO object detection improved the feature extraction ability through more layers of convolution neural networks. Hybrid dataset training and cluster anchor boxes could also improve the pedestrian detection performance. Hie test results of INRIA dataset prove that the method has better detection performance than the popular pedestrian detection methods, the index of false positive per image can reduce to 13.86% .improving ranging from 1.51% to 58. 62% in varying degrees. [ABSTRACT FROM AUTHOR]

In order to further improve the performance of video image super-resolution reconstruction and study the reconstruction of spatial resolution of video images by using the characteristics of convolution neural network .this paper proposed a video image reconstruction model based on convolution neural network. Hie model adopted the pre-training strategy to initialize the parameters. And it carried out the training processing both on the spatial and temporal dimensions of the multi-frame video images at the same time. It extracted the characteristics of the main motion information, learnt and made full use of the information inter the frames for improved performance. And it used the adaptive motion compensation algorithm to optimize the output of the channel to obtain the reconstructed center frame image with high resolution. The experimental results show that the average of objective evaluation indexes for video image reconstruction improves with a rather clear margin (PSNR + 0. 4 dB/SSIM + 0.02) ,and the edge of the fuzzy phenomenon in video reconstruction image for the subjective visual effect is effectively reduced. Compared with other traditional algorithms,it both obviously improved the evaluation of the objective indexes and subjective visual effect of the reconstructed image. Providing a novel architecture based on convolution neural network for video image super-resolution, which provides an exploration for the further study of video image super-resolution reconstruction based on the deep learning method. [ABSTRACT FROM AUTHOR]

In order to further improve the accuracy of gender recognition, this paper proposed the convolution neural network model based on multi-layer feature fusion with adjustable supervisory function, L-MFCNN, then used it for face gender recognition. Unlike the traditional convolution neural network, L-MFCNN combined the output of multiple shallow convolution layers with the final convolution layer output. Fusion the characteristics of multi-layer convolutions, not only used the high-level semantic information, but also considered the bottom of the details of the texture information, making the face gender recognition more accuracy. While using the large-margin softmax loss could adjust the margin function, it could explicitly encourages the same gender intra-class compactness and the different gender inter-class separability to get better face gender recognition. The face gender recognition experiment data on multiple face data sets show that the accuracy of L-MFCNN is higher than that of traditional convolution network. Besides, L-MFCNN also provides the new ideas and directions for the future gender recognition of face. [ABSTRACT FROM AUTHOR]

Aiming at the problem of complex feature extraction and low accuracy in human action recognition, this paper proposed a network structure combining batch normalization algorithm with GoogLeNet network model. Applying batch normalization idea in the field of image classification to action recognition field, it improved the algorithm by normalizing the network input training sample by mini-batch. For convolutional network, RGB image was the spatial input, and stacked optical flows was the temporal input. Then, it fused the spatio-temporal networks to get the final action recognition result. It trained and evaluated the architecture on the standard video actions benchmarks of UCF101 and HMDB51, which achieved the accuracy of 93. 50%and 68. 32%. The results show that the improved convolutional neural network has a significant improvement in improving the recognition rate and has obvious advantages in action recognition. [ABSTRACT FROM AUTHOR]

With the continuous development of remote sensing technology and computer technology, the traditional remote sensing image classification method cannot meet the needs of remote sensing image classification. In recent years, with the continuous emergence of research results in deep learning, it provides a new way for the classification of remote sensing images. This paper first outlined the development of remote sensing image classification and the basic concepts of deep learning, and then focused on the research progress in the classification of remote sensing images based on the deep learning model such as deep belief network, convolutional neural network and stacked auto-encoder. Finally, it summarized the existing issues and the future directions of remote sensing image classification based on deep learning. [ABSTRACT FROM AUTHOR]

In order to overcome the shortcomings that low detection accuracy and slow network training of the real-time object detection algorithm YOLO, this paper proposed an algorithm that added the batch re-normalization to the YOLO network structure. It combined the characteristic of batch re-normalization, which had the strength to deal with small or non-i. i. d. minibatches. The improved algorithm treated the feature maps, which generated from the convolutional layers, as activations, and then batched renormalize the activations, meanwhile it removed the dropout from the original network structure and increased learning rate. The experimental results show that the proposal algorithm has better detection accuracy and faster than before, and furthermore, it can decrease the model training time and the requirement of hardware equipment. [ABSTRACT FROM AUTHOR]

Deep learning method has very excellent ability of image feature extraction. In order to get rid of disadvantages of traditional methods require a priori knowledge, this paper proposed an image feature extraction algorithm based on the fusion AutoEncoder and convolutional neural network (CNN ). The method introduced a fast sparsity control technique to AutoEncod-er and utilized AutoEncoder to train the basic elements of image and initialized the convolution kernel of CNN. Meanwhile, the algorithm added filtering mechanism to the CNN to keep the sparsity of output characteristics. The results of experiments point out that this method achieves good performance on the Minist handwritten digital library and the Yale face database. Furthermore, the advanced experimental outcomes indicate that the feature extraction model included the filtering technique is more effective than the model without filtering mechanism by using cross-validation with T test. [ABSTRACT FROM AUTHOR]

To solve the problem that the loss of image feature information and improve the accuracy of image retrieval, when the convolutional neural network (CNN) was used to extract the feature information of the image, this paper proposed an image retrieval algorithm based on improved convolutional neural network LeNet-L. First, it improved LeNet-5 convolution neural network structure, increased depth of network structure. Then, it pre-trained the deep convolutional neural network LeNet-L to extract the high-level semantic features. At last, it obtained the similar images by distance function between the image being retrieved and the one in image database. In Corel dataset, compared with the original model method and the traditional image retrieval method based on SVM and active learning, the proposed method had a higher accuracy. The experimental results show that the improved convolutional neural network has a better retrieval effect. [ABSTRACT FROM AUTHOR]

The utilization of smart phone’ acceleration sensors to identify human behavior is a big topic in intelligence field. Traditional identification methods, such as Bayes, speed learning and decision tree, must first collected acquisition frequency domain features of acceleration sensor data and extracted preferred features. This paper utilized convolutional neural network algorithm to extract smart phone’ accelerate data in three dimensions, and then automatically found out patterns from the data. Finally it used decision tree to identify human behavior from the pattern. Experimental results show that recognition accuracy improves 1.1% to 5.2% in comparison with traditional machine learning methods, especially data set on the large -scale. [ABSTRACT FROM AUTHOR]

In order to reduce the loss of dimension reduction in high dimensional image dataset and improve the effect of data visualization, this paper proposed a new image dataset visualization method based on the combination of deep features and nonlinear dimension reduction. This method firstly designed and trained a convolutional neural network model,and the single model on the MNIST dataset achieved the highest recognition accuracy. Secondly,it used the high precision model to extract the deep middle layer features as an effective representation of the image dataset. Finally,it used nonlinear dimension reduction method to reduce the features into two-dimensional and realized data visualization. Experimental results show that this method can effectively avoid the loss of traditional dimension reduction in image dataset visualization, and the visualization result is very obvious. [ABSTRACT FROM AUTHOR]

The classification accuracy of the traditional visual features can not meet the requirements in the application of modern military affairs due to the extremely high similarity of the different objects in the battlefield and low recognition rate in complex conditions. This paper presented a new architecture of the convolutional neural network (CNN) based on PCA whitening for solving the classification problem of large-scale images which contained some specific military objects. It efficiently eliminated the relativity of sample data. enhanced the learning ability and improved the accuracy of the object recognition. It tested and evaluated the new CNN model with the large-scale data from military images and compared with the traditional methods. The experiment results show that the algorithm has higher recognition rate on military object recognition. [ABSTRACT FROM AUTHOR]