Resampling Factor Estimation via Dual-Stream Convolutional Neural Network

The estimation of image resampling factors is an important problem in image forensics. Among all the resampling factor estimation methods, spectrumbased methods are one of the most widely used methods and have attracted a lot of research interest. However, because of inherent ambiguity, spectrum-based methods fail to discriminate upscale and downscale operations without any prior information. In general, the application of resampling leaves detectable traces in both spatial domain and frequency domain of a resampled image. Firstly, the resampling process will introduce correlations between neighboring pixels. In this case, a set of periodic pixels that are correlated to their neighbors can be found in a resampled image. Secondly, the resampled image has distinct and strong peaks on spectrum while the spectrum of original image has no clear peaks. Hence, in this paper, we propose a dual-stream convolutional neural network for image resampling factors estimation. One of the two streams is gray stream whose purpose is to extract resampling traces features directly from the rescaled images. The other is frequency stream that discovers the differences of spectrum between rescaled and original images. The features from two streams are then fused to construct a feature representation including the resampling traces left in spatial and frequency domain, which is later fed into softmax layer for resampling factor estimation. Experimental results show that the proposed method is effective on resampling factor estimation and outperforms some CNN-based methods.     

基于卷积神经网络的印刷套准识别方法

目的 针对目前印刷套准识别方法依赖于经验人工设计特征提取的问题,提出一种不需要人工提取图像特征的卷积神经网络模型,实现印刷套准状态的识别.方法 采用图像增强技术实现不均衡训练集的均衡化,增加训练集图像的数量,提高模型的识别准确率.设计基于AlexNet网络结构的印刷套准识别模型的结构参数,分析批处理样本数量和基础学习率对模型性能的影响规律.结果 文中方法获得的总印刷套准识别准确率为0.9860,召回率为1.0000,分类准确率几何平均数为0.9869.结论 文中方法能自动提取图像特征,不依赖于人工设计的特征提取方法.在构造的数据集上,文中方法的分类性能优于实验中的支持向量机方法.     

Sentiment Classification Based on Piecewise Pooling Convolutional Neural Network

Recently, the effectiveness of neural networks, especially convolutional neural networks, has been validated in the field of natural language processing, in which, sentiment classification for online reviews is an important and challenging task. Existing convolutional neural networks extract important features of sentences without local features or the feature sequence. Thus, these models do not perform well, especially for transition sentences. To this end, we propose a Piecewise Pooling Convolutional Neural Network (PPCNN) for sentiment classification. Firstly, with a sentence presented by word vectors, convolution operation is introduced to obtain the convolution feature map vectors. Secondly, these vectors are segmented according to the positions of transition words in sentences. Thirdly, the most significant feature of each local segment is extracted using max pooling mechanism, and then the different aspects of features can be extracted. Specifically, the relative sequence of these features is preserved. Finally, after processed by the dropout algorithm, the softmax classifier is trained for sentiment classification. Experimental results show that the proposed method PPCNN is effective and superior to other baseline methods, especially for datasets with transition sentences.     

Identification of Weather Phenomena Based on Lightweight Convolutional Neural Networks

Weather phenomenon recognition plays an important role in the field of meteorology. Nowadays, weather radars and weathers sensor have been widely used for weather recognition. However, given the high cost in deploying and maintaining the devices, it is difficult to apply them to intensive weather phenomenon recognition. Moreover, advanced machine learning models such as Convolutional Neural Networks (CNNs) have shown a lot of promise in meteorology, but these models also require intensive computation and large memory, which make it difficult to use them in reality. In practice, lightweight models are often used to solve such problems. However, lightweight models often result in significant performance losses. To this end, after taking a deep dive into a large number of lightweight models and summarizing their shortcomings, we propose a novel lightweight CNNs model which is constructed based on new building blocks. The experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory consumption. Such memory reduction is even better than that of existing lightweight models.     

基于卷积神经网络的光学遥感图像船只检测

目的研究无需进行复杂的图像预处理和人工特征提取,就能提高光学遥感图像的船只检测准确率和实现船只类型精细分类。方法对输入的检测图像,采用选择性搜索的方法产生船只候选区域,用已经标记好的训练样本对卷积神经网络进行监督训练,得到网络参数,然后使用经过监督训练的卷积神经网络提取抽象特征,并对候选区域进行分类,根据船只候选区域的分类概率同时确定船只的位置以及类型。结果与现有的2种检测方法进行对比,实验结果表明卷积神经网络能有效提高船只检测准确率,平均检测准确率达到了93.3%。结论该检测方法无需进行复杂的预处理,能同时对船只进行检测和分类,并能有效提高船只检测准确率。     

基于卷积神经网络的印刷品颜色缺陷检测

目的 提取样本图像颜色直方图特征对卷积神经网络进行训练,达到快速、高准确率检测图像颜色缺陷的目的.方法 将标准图像从RGB颜色空间转换至HSV颜色空间,通过改变图像H,S,V三分量值获取训练样本和测试样本;在HSV颜色空间中非均匀量化图像的颜色直方图,得到所有训练样本和测试样本的颜色直方图特征;利用样本图像颜色直方图特征训练卷积神经网络,然后对测试样本进行检测,研究检测的速度、准确率,并将该检测方法与逐像素、超像素、BP神经网络和支持向量机方法进行对比.结果 对于图片尺寸为512×512的彩色图像,卷积神经网络检测单幅图片的平均检测时间约为57.66 ms,训练样本图像为50000张时,卷积神经网络方法对10000张测试样本进行检测的准确率为99.77％.结论 卷积神经网络方法在保证高准确率的前提下大幅提高检测精度,对于印刷品色差缺陷在线检测具有良好的应用价值.     

A Rub-Impact Recognition Method Based on Improved Convolutional Neural Network

Based on the theory of modal acoustic emission (AE), when the convolutional neural network (CNN) is used to identify rotor rub-impact faults, the training data has a small sample size, and the AE sound segment belongs to a single channel signal with less pixel-level information and strong local correlation. Due to the convolutional pooling operations of CNN, coarse-grained and edge information are lost, and the top-level information dimension in CNN network is low, which can easily lead to overfitting. To solve the above problems, we first propose the use of sound spectrograms and their differential features to construct multi-channel image input features suitable for CNN and fully exploit the intrinsic characteristics of the sound spectra. Then, the traditional CNN network structure is improved, and the outputs of all convolutional layers are connected as one layer constitutes a fused feature that contains information at each layer, and is input into the network’s fully connected layer for classification and identification. Experiments indicate that the improved CNN recognition algorithm has significantly improved recognition rate compared with CNN and dynamical neural network (DNN) algorithms.     

Enhancing CNN for Forensics Age Estimation Using CGAN and Pseudo-Labelling

Age estimation using forensics odontology is an important process in identifying victims in criminal or mass disaster cases. Traditionally, this process is done manually by human expert. However, the speed and accuracy may vary depending on the expertise level of the human expert and other human factors such as level of fatigue and attentiveness. To improve the recognition speed and consistency, researchers have proposed automated age estimation using deep learning techniques such as Convolutional Neural Network (CNN). CNN requires many training images to obtain high percentage of recognition accuracy. Unfortunately, it is very difficult to get large number of samples of dental images for training the CNN due to the need to comply to privacy acts. A promising solution to this problem is a technique called Generative Adversarial Network (GAN). GAN is a technique that can generate synthetic images that has similar statistics as the training set. A variation of GAN called Conditional GAN (CGAN) enables the generation of the synthetic images to be controlled more precisely such that only the specified type of images will be generated. This paper proposes a CGAN for generating new dental images to increase the number of images available for training a CNN model to perform age estimation. We also propose a pseudo-labelling technique to label the generated images with proper age and gender. We used the combination of real and generated images to train Dental Age and Sex Net (DASNET), which is a CNN model for dental age estimation. Based on the experiment conducted, the accuracy, coefficient of determination (R2) and Absolute Error (AE) of DASNET have improved to 87%, 0.85 and 1.18 years respectively as opposed to 74%, 0.72 and 3.45 years when DASNET is trained using real, but smaller number of images.     

基于直方图均衡化和卷积神经网络的轴承故障诊断方法

针对传统的滚动轴承故障诊断方法依赖人工特征提取和专家经验,难以自适应提取强噪声信号微弱故障特征的问题,提出一种直方图均衡化和卷积神经网络(CNN)相结合的智能诊断方法。首先,将传感器采集到的一维振动信号通过横向插值法转换为便于模型识别的二维振动图像,利用直方图均衡化技术拉伸像素之间灰度值差别的动态范围,突出纹理细节和对比度,以增强周期性故障特征;然后构建深层CNN模型,采用优化技术降低模型参数量,逐层学习监测数据与故障状态之间的复杂映射关系。实验结果表明该方法具有高达99%以上的准确率,对不同负载下的故障信号仍具有较高的识别精度和泛化能力。     

DDoS Attack Detection via Multi-Scale Convolutional Neural Network

Distributed Denial-of-Service (DDoS) has caused great damage to the network in the big data environment. Existing methods are characterized by low computational efficiency, high false alarm rate and high false alarm rate. In this paper, we propose a DDoS attack detection method based on network flow grayscale matrix feature via multiscale convolutional neural network (CNN). According to the different characteristics of the attack flow and the normal flow in the IP protocol, the seven-tuple is defined to describe the network flow characteristics and converted into a grayscale feature by binary. Based on the network flow grayscale matrix feature (GMF), the convolution kernel of different spatial scales is used to improve the accuracy of feature segmentation, global features and local features of the network flow are extracted. A DDoS attack classifier based on multi-scale convolution neural network is constructed. Experiments show that compared with correlation methods, this method can improve the robustness of the classifier, reduce the false alarm rate and the missing alarm rate.     

基于卷积神经网络的ZPW-2000R轨道电路智能故障诊断方法

为解决ZPW-2000R型轨道电路故障智能自诊断问题,提出一种基于深度卷积神经网络的ZPW-2000R轨道电路故障诊断模型,输入微机存储的38个实时监测变量数据,可自动诊断包括轨道电路室内及室外设备的共29种故障类型,且故障诊断准确率可达96%。为轨道电路故障诊断提供了有效的智能化解决方案。     

基于卷积神经网络的热轧薄板力学性能建模

目的 为了提高热轧薄板力学性能的预测精度,采用大数据与卷积神经网络相结合的方式建立高精度的预测模型.方法 建模前,对工业大数据进行预处理,包括去除异常值、聚类、均衡数据以及归一化,以得到高质量的数据集.同时,采用贡献权重法对输入参数进行筛选,去除弱相关的变量以降低模型的复杂程度.在此基础上,采用LeNet-5结构建立卷...     

卷积神经网络在喷码字符识别中的应用

为实现易拉罐灌装过程中喷码字符实时检测,提出了一种基于卷积神经网络的实时检测方法。该方法首先对采集的图像进行直方图均衡化和OSTU处理,然后对图像进行形态学膨胀操作,通过连通域面积法提取出喷码字符区域并进行旋转矫正,再采用投影法将字符区域分割为单个字符,在离线状态下采用卷积神经网络对字符进行训练,从而在在线检测时进行识别。实验表明,该方法检测一帧图像平均时间为46 ms,准确率达98.97%,实时性和准确性较高,可以满足工业易拉罐喷码字符在线实时检测要求。     

Digital Forensics for Recoloring via Convolutional Neural Network

As a common medium in our daily life, images are important for most people to gather information. There are also people who edit or even tamper images to deliberately deliver false information under different purposes. Thus, in digital forensics, it is necessary to understand the manipulating history of images. That requires to verify all possible manipulations applied to images. Among all the image editing manipulations, recoloring is widely used to adjust or repaint the colors in images. The color information is an important visual information that image can deliver. Thus, it is necessary to guarantee the correctness of color in digital forensics. On the other hand, many image retouching or editing applications or software are equipped with recoloring function. This enables ordinary people without expertise of image processing to apply recoloring for images. Hence, in order to secure the color information of images, in this paper, a recoloring detection method is proposed. The method is based on convolutional neural network which is quite popular in recent years. Unlike the traditional linear classifier, the proposed method can be employed for binary classification as well as multiple labels classification. The classification performance of different structure for the proposed architecture is also investigated in this paper.     

基于声信号和一维卷积神经网络的电机故障诊断研究

针对电机故障诊断问题,设计一种新型的一维卷积神经网络结构(1D-CNN),提出一种基于声信号和1D-CNN的电机故障诊断方法.为了验证1D-CNN算法在电机故障识别领域的有效性,以一组空调故障电机作为实验对象,搭建电机故障诊断平台,对4种状态的空调电机进行声信号采集实验,制作电机故障声信号数据集,并运用1D-CNN算法...     

Classification of Arrhythmia Based on Convolutional Neural Networks and Encoder-Decoder Model

As a common and high-risk type of disease, heart disease seriously threatens people’s health. At the same time, in the era of the Internet of Thing (IoT), smart medical device has strong practical significance for medical workers and patients because of its ability to assist in the diagnosis of diseases. Therefore, the research of real-time diagnosis and classification algorithms for arrhythmia can help to improve the diagnostic efficiency of diseases. In this paper, we design an automatic arrhythmia classification algorithm model based on Convolutional Neural Network (CNN) and Encoder-Decoder model. The model uses Long Short-Term Memory (LSTM) to consider the influence of time series features on classification results. Simultaneously, it is trained and tested by the MIT-BIH arrhythmia database. Besides, Generative Adversarial Networks (GAN) is adopted as a method of data equalization for solving data imbalance problem. The simulation results show that for the inter-patient arrhythmia classification, the hybrid model combining CNN and Encoder-Decoder model has the best classification accuracy, of which the accuracy can reach 94.05%. Especially, it has a better advantage for the classification effect of supraventricular ectopic beats (class S) and fusion beats (class F).     

Importance of Adaptive Photometric Augmentation for Different Convolutional Neural Network

Existing segmentation and augmentation techniques on convolutional neural network (CNN) has produced remarkable progress in object detection. However, the nominal accuracy and performance might be downturned with the photometric variation of images that are directly ignored in the training process, along with the context of the individual CNN algorithm. In this paper, we investigate the effect of a photometric variation like brightness and sharpness on different CNN. We observe that random augmentation of images weakens the performance unless the augmentation combines the weak limits of photometric variation. Our approach has been justified by the experimental result obtained from the PASCAL VOC 2007 dataset, with object detection CNN algorithms such as YOLOv3 (You Only Look Once), Faster R-CNN (Region-based CNN), and SSD (Single Shot Multibox Detector). Each CNN model shows performance loss for varying sharpness and brightness, ranging between −80% to 80%. It was further shown that compared to random augmentation, the augmented dataset with weak photometric changes delivered high performance, but the photometric augmentation range differs for each model. Concurrently, we discuss some research questions that benefit the direction of the study. The results prove the importance of adaptive augmentation for individual CNN model, subjecting towards the robustness of object detection.     

基于VMD和卷积神经网络的变工况轴承故障诊断方法

针对变工况条件下轴承故障数据无法大量获取以及诊断困难的问题,提出了基于变分模态分解和卷积神经网络的轴承故障诊断方法,使用稳态工况获取的数据训练,能对变工况下的数据实现有效诊断.首先对轴承振动信号进行变分模态分解,以获得有限带宽的固有模态函数;然后构建卷积神经网络模型,采用优化技术提高模型适应性,实现对固有模态函数的自适...     

Melanoma Identification Through X-ray Modality Using Inception-v3 Based Convolutional Neural Network

Melanoma, also called malignant melanoma, is a form of skin cancer triggered by an abnormal proliferation of the pigment-producing cells, which give the skin its color. Melanoma is one of the skin diseases, which is exceptionally and globally dangerous, Skin lesions are considered to be a serious disease. Dermoscopy-based early recognition and detection procedure is fundamental for melanoma treatment. Early detection of melanoma using dermoscopy images improves survival rates significantly. At the same time, well-experienced dermatologists dominate the precision of diagnosis. However, precise melanoma recognition is incredibly hard due to several factors: low contrast between lesions and surrounding skin, visual similarity between melanoma and non-melanoma lesions, and so on. Thus, reliable automatic detection of skin tumors is critical for pathologists’ effectiveness and precision. To take care of this issue, numerous research centers around the world are creating autonomous image processing-oriented frameworks. We suggested deep learning methods in this article to address significant tasks that have emerged in the field of skin lesion image processing: we provided a Convolutional Neural Network (CNN) based framework using an Inception-v3 (INCP-v3) melanoma detection scheme and accomplished very high precision (98.96%) against melanoma detection. The classification framework of CNN is created utilizing TensorFlow and Keras in the backend (in Python). It likewise utilizes Transfer-Learning (TL) approach. It is prepared on the data gathered from the “International Skin Imaging Collaboration (ISIC)” repositories. The experiments show that the suggested technique outperforms state-of-the-art methods in terms of predictive performance.     

An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.