Detecting Iris Liveness with Batch Normalized Convolutional Neural Network

Aim to countermeasure the presentation attack for iris recognition system,an iris liveness detection scheme based on batch normalized convolutional neural network(BNCNN)is proposed to improve the reliability of the iris authentication system.The BNCNN architecture with eighteen layers is constructed to detect the genuine iris and fake iris,including convolutional layer,batch-normalized(BN)layer,Relu layer,pooling layer and full connected layer.The iris image is first preprocessed by iris segmentation and is normalized to 256×256 pixels,and then the iris features are extracted by BNCNN.With these features,the genuine iris and fake iris are determined by the decision-making layer.Batch normalization technique is used in BNCNN to avoid the problem of over fitting and gradient disappearing during training.Extensive experiments are conducted on three classical databases:the CASIA Iris Lamp database,the CASIA Iris Syn database and Ndcontact database.The results show that the proposed method can effectively extract micro texture features of the iris,and achieve higher detection accuracy compared with some typical iris liveness detection methods.

一种基于神经网络的太阳能电池板缺陷检测方法

研究一种基于神经网络的太阳能电池板缺陷检测方法,利用DenseNet网络模型对缺陷进行检测,在该模型中加入转换器保证相邻模块间的大小,融入L2正则化可以在一定程度上避免过拟合现象,调整Batch Normalization层在避免梯度消失的同时加快收敛速度,使用SELU激活函数可以提高模型的鲁棒性。

Effective Customer Review Analysis Using Combined Capsule Networks with Matrix Factorization Filtering

Nowadays,commercial transactions and customer reviews are part of human life and various business applications.The technologies create a great impact on online user reviews and activities,affecting the business process.Customer reviews and ratings are more helpful to the new customer to purchase the product,but the fake reviews completely affect the business.The traditional systems consume maximum time and create complexity while analyzing a large volume of customer information.Therefore,in this work optimized recommendation system is developed for analyzing customer reviews with minimum complexity.Here,Amazon Product Kaggle dataset information is utilized for investigating the customer review.The collected information is analyzed and processed by batch normalized capsule networks(NCN).The network explores the user reviews according to product details,time,price purchasing factors,etc.,ensuring product quality and ratings.Then effective recommendation system is developed using a butterfly optimized matrix factorizationfiltering approach.Then the system’s efficiency is evaluated using the Rand Index,Dunn index,accuracy,and error rate.

COVID-19 Detection via a 6-Layer Deep Convolutional Neural Network

Many people around the world have lost their lives due to COVID-19.The symptoms of most COVID-19 patients are fever,tiredness and dry cough,and the disease can easily spread to those around them.If the infected people can be detected early,this will help local authorities control the speed of the virus,and the infected can also be treated in time.We proposed a six-layer convolutional neural network combined with max pooling,batch normalization and Adam algorithm to improve the detection effect of COVID-19 patients.In the 10-fold cross-validation methods,our method is superior to several state-of-the-art methods.In addition,we use Grad-CAM technology to realize heat map visualization to observe the process of model training and detection.

基于改进YOLOv3的钢卷端面缺陷检测应用研究

工业生产中,现有钢卷端面缺陷检测使用的主要方法仍未人工目视检测,少量使用机器视觉传统算法进行辅助识别,效果不尽人意。近些年,有研究使用深度学习的机器视觉方法应用于钢卷断面缺陷检测,但是很多算法实际应用中难以达到理想效果。针对现有钢卷端面缺陷检测方法中存在的检测精度低,实时检测速度慢,数据量不足等问题,提出一种改进YOLOv3算法模型。该算法改进了YOLOv3的Batch Normalization层,将Batch Normalization层的参数合并到卷积层,提升模型运算速度。其次使用GIoU度量损失替代IoU边界框回归损失,提供更加准确的边界框移动方向的数据信息,提高检测精度。实验分析可得出,改进后的YOLOv3算法检测速率可达55.1Fps,比原算法提高10.8%;检测精度指标mAP可达78.15%,比原算法提高6.89%。

Behavior recognition based on the fusion of 3D-BN-VGG and LSTM network

In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.

An Optimized Convolutional Neural Network with Combination Blocks for Chinese Sign Language Identification

(Aim)Chinese sign language is an essential tool for hearing-impaired to live,learn and communicate in deaf communities.Moreover,Chinese sign language plays a significant role in speech therapy and rehabilitation.Chinese sign language identification can provide convenience for those hearing impaired people and eliminate the communication barrier between the deaf community and the rest of society.Similar to the research of many biomedical image processing(such as automatic chest radiograph processing,diagnosis of chest radiological images,etc.),with the rapid development of artificial intelligence,especially deep learning technologies and algorithms,sign language image recognition ushered in the spring.This study aims to propose a novel sign language image recognition method based on an optimized convolutional neural network.(Method)Three different combinations of blocks:Conv-BN-ReLU-Pooling,Conv-BN-ReLU,Conv-BN-ReLU-BN were employed,including some advanced technologies such as batch normalization,dropout,and Leaky ReLU.We proposed an optimized convolutional neural network to identify 1320 sign language images,which was called as CNN-CB method.Totally ten runs were implemented with the hold-out randomly set for each run.(Results)The results indicate that our CNN-CB method gained an overall accuracy of 94.88±0.99%.(Conclusion)Our CNN-CB method is superior to thirteen state-of-the-art methods:eight traditional machine learning approaches and five modern convolutional neural network approaches.

基于微型激光雷达的输电线路导线缺陷识别

在输电线路识别过程中,存在着训练模型耗时,数据集有偏差、冗余的缺陷,从而导致网络识别检测准确度低,且相互重叠的目标识别较弱的问题,提出基于改进SSD网络的结构,对其进行特征提取和Batch Normalization网络调整和参数调优。实验证明,通过改进SSD网络可以使模型训练加快收敛,降低计算冗余量,能够显著减少硬件体系内显存资源的运行效率,提升训练时间效率,说明改进SSD网络于输电线路缺陷识别具有实用性。

基于GoogLeNet的手写体汉字识别

近年来基于深度学习的方法识别手写体汉字取得了很多突破,但现有的一些方法存在计算参数多、模型收敛慢、训练时间长的缺点。针对以上问题,提出了基于GoogLeNet的脱机手写体汉字识别模型HCCR-IncBN,模型使用了5个Inception-v2模块,训练参数较少,模型收敛更快,存储整个模型只需要26MB的存储空间。实验利用HCCR-IncBN模型在ICDAR2013数据集获得了95.94%的识别准确率,表明模型在没有使用任何手写体汉字的特定领域知识和无需人工提取其他特征的前提下能够获得较高的识别效果。

Behavior recognition algorithm based on the improved R3D and LSTM network fusion

Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.

An Enhanced Deep Learning Method for Skin Cancer Detection and Classification

The prevalence of melanoma skin cancer has increased in recent decades.The greatest risk from melanoma is its ability to broadly spread throughout the body by means of lymphatic vessels and veins.Thus,the early diagnosis of melanoma is a key factor in improving the prognosis of the disease.Deep learning makes it possible to design and develop intelligent systems that can be used in detecting and classifying skin lesions from visible-light images.Such systems can provide early and accurate diagnoses of melanoma and other types of skin diseases.This paper proposes a new method which can be used for both skin lesion segmentation and classification problems.This solution makes use of Convolutional neural networks(CNN)with the architecture two-dimensional(Conv2D)using three phases:feature extraction,classification and detection.The proposed method is mainly designed for skin cancer detection and diagnosis.Using the public dataset International Skin Imaging Collaboration(ISIC),the impact of the proposed segmentation method on the performance of the classification accuracy was investigated.The obtained results showed that the proposed skin cancer detection and classification method had a good performance with an accuracy of 94%,sensitivity of 92%and specificity of 96%.Also comparing with the related work using the same dataset,i.e.,ISIC,showed a better performance of the proposed method.

Micro-expression recognition algorithm based on the combination of spatial and temporal domains

Aiming at the problem of unsatisfactory effects of traditional micro-expression recognition algorithms,an efficient micro-expression recognition algorithm is proposed,which uses convolutional neural networks(CNN)to extract spatial features of micro-expressions,and long short-term memory network(LSTM)to extract time domain features.CNN and LSTM are combined as the basis of micro-expression recognition.In many CNN structures,the visual geometry group(VGG)using a small convolution kernel is finally selected as the pre-network through comparison.Due to the difficulty of deep learning training and over-fitting,the dropout method and batch normalization method are used to solve the problem in the VGG network.Two data sets CASME and CASME II are used for test comparison,in order to solve the problem of insufficient data sets,randomly determine the starting frame,and a fixedlength frame sequence is used as the standard,and repeatedly read all sample frames of the entire data set to achieve trayersal and data amplification.Finallv.a hieh recognition rate of 67.48% is achieved.

An improved micro-expression recognition algorithm of 3D convolutional neural network

The micro-expression lasts for a very short time and the intensity is very subtle.Aiming at the problem of its low recognition rate,this paper proposes a new micro-expression recognition algorithm based on a three-dimensional convolutional neural network(3D-CNN),which can extract two-di-mensional features in spatial domain and one-dimensional features in time domain,simultaneously.The network structure design is based on the deep learning framework Keras,and the discarding method and batch normalization(BN)algorithm are effectively combined with three-dimensional vis-ual geometry group block(3D-VGG-Block)to reduce the risk of overfitting while improving training speed.Aiming at the problem of the lack of samples in the data set,two methods of image flipping and small amplitude flipping are used for data amplification.Finally,the recognition rate on the data set is as high as 69.11%.Compared with the current international average micro-expression recog-nition rate of about 67%,the proposed algorithm has obvious advantages in recognition rate.

基于ResNet50-SSD的安全帽佩戴状态检测研究

针对现存的安全帽佩戴检测方法对尺寸大小不一、部分遮挡的目标检测难度大的问题。文章提出了一种基于Res-Net50-SSD的安全帽佩戴状态检测研究方法。该模型以SSD网络作为基础,采用ResNet-50代替传统的VGG-16作为SSD的主干网络提取特征,并在附加层中引入BN(Batch Normalization)层,加快网络的收敛速度,提高检测精确度。实验结果表明:ResNet50-SSD的在安全帽佩戴状态检测任务中mAP达80.4%,相对于传统的SSD提高了2.23%。在保证较高的检测准确率的情况下能达到了每秒35帧的检测速度,满足实时检测的要求。

Meta-BN Net for few-shot learning

In this paper, we propose a lightweight network with an adaptive batch normalization module, called Meta-BN Net, for few-shot classification. Unlike existing few-shot learning methods, which consist of complex models or algorithms, our approach extends batch normalization, an essential part of current deep neural network training, whose potential has not been fully explored. In particular, a meta-module is introduced to learn to generate more powerful affine transformation parameters, known as and , in the batch normalization layer adaptively so that the representation ability of batch normalization can be activated. The experimental results on miniImageNet demonstrate that Meta-BN Net not only outperforms the baseline methods at a large margin but also is competitive with recent state-of-the-art few-shot learning methods. We also conduct experiments on Fewshot-CIFAR100 and CUB datasets, and the results show that our approach is effective to boost the performance of weak baseline networks. We believe our findings can motivate to explore the undiscovered capacity of base components in a neural network as well as more efficient few-shot learning methods.

Fault diagnosis of bearings based on deep separable convolutional neural network and spatial dropout

Bearing pitting,one of the common faults in mechanical systems,is a research hotspot in both academia and industry.Traditional fault diagnosis methods for bearings are based on manual experience with low diagnostic efficiency.This study proposes a novel bearing fault diagnosis method based on deep separable convolution and spatial dropout regularization.Deep separable convolution extracts features from the raw bearing vibration signals,during which a 3×1 convolutional kernel with a one-step size selects effective features by adjusting its weights.The similarity pruning process of the channel convolution and point convolution can reduce the number of parameters and calculation quantities by evaluating the size of the weights and removing the feature maps of smaller weights.The spatial dropout regularization method focuses on bearing signal fault features,improving the independence between the bearing signal features and enhancing the robustness of the model.A batch normalization algorithm is added to the convolutional layer for gradient explosion control and network stability improvement.To validate the effectiveness of the proposed method,we collect raw vibration signals from bearings in eight different health states.The experimental results show that the proposed method can effectively distinguish different pitting faults in the bearings with a better accuracy than that of other typical deep learning methods.

Probability-Based Channel Pruning for Depthwise Separable Convolutional Networks

Channel pruning can reduce memory consumption and running time with least performance damage,and is one of the most important techniques in network compression.However,existing channel pruning methods mainly focus on the pruning of standard convolutional networks,and they rely intensively on time-consuming fine-tuning to achieve the performance improvement.To this end,we present a novel efficient probability-based channel pruning method for depthwise separable convolutional networks.Our method leverages a new simple yet effective probability-based channel pruning criterion by taking the scaling and shifting factors of batch normalization layers into consideration.A novel shifting factor fusion technique is further developed to improve the performance of the pruned networks without requiring extra time-consuming fine-tuning.We apply the proposed method to five representative deep learning networks,namely MobileNetV1,MobileNetV2,ShuffleNetV1,ShuffleNetV2,and GhostNet,to demonstrate the efficiency of our pruning method.Extensive experimental results and comparisons on publicly available CIFAR10,CIFAR100,and ImageNet datasets validate the feasibility of the proposed method.

Simultaneous determination of naphazoline and pyridoxine in eye drops using excitation–emission matrix fluorescence coupled with second-order calibration method based on alternating trilinear decomposition algorithm

A novel method is developed for the direct determination of naphazoline hydrochloride（NAP） and pyridoxine hydrochloride（VB6） in commercial eye drops. By using excitation–emission matrix（EEM）fluorescence coupled with second-order calibration method based on the alternating trilinear decomposition（ATLD） algorithm, the proposed approach can achieve quantitative analysis successfully even in the presence of unknown and uncalibrated interferences. The method shows good linearity for NAP and VB6 with correlation coefficients greater than 0.99. The results were in good agreement with the labeled contents. To further confirm the feasibility and reliability of the proposed method, the same batch samples were analyzed by multiple reaction monitoring（MRM） based on LC–MS/MS method.T-test demonstrated that there are no significant differences between the prediction results of the two methods. The satisfactory results obtained in this work indicate that the use of the second-order calibration method coupled with the EEM is a promising tool for industrial quality control and pharmaceutical analysis due to its advantages of high sensitivity, low-cost and simple implementation.

INCORPERATING ARTICULATORY VELOCITY INFORMATION IN ACOUSTIC-TO-ARTICULATORY INVERSION

Conventional acoustic-to-articulatory inversion methods usually train mappings by using maximum likelihood or least square criterion,which assume that all the articulatory channels are equally important.However,different articulatory channels play different roles in speech production.In this paper,to account for this in acoustic-to-articulatory inversion,the importance of each articulatory channel is modeled as an exponential function of its corresponding velocity profile,and incorporated into the conventional least square loss function.The proposed loss function is applied to optimize a batch normalized Deep Neural Network(DNN)for acoustic-to-articulatory inversion.The result indicates that the DNN trained with the proposed cost function outperforms the DNN trained with traditional cost function for most articulatory channels.