两层级联卷积神经网络的人脸检测

目的 传统人脸检测方法因人脸多姿态变化和人脸面部特征不完整等问题,导致检测效果不佳。为解决上述问题,提出一种两层级联卷积神经网络（TC_CNN）人脸检测方法。方法 首先,构建两层卷积神经网络模型,利用前端卷积神经网络模型对人脸图像进行特征粗略提取,再利用最大值池化方法对粗提取得到的人脸特征进行降维操作,输出多个疑似人脸窗口;其次,将前端粗提取得到的人脸窗口作为后端卷积神经网络模型的输入进行特征精细提取,并通过池化操作得到新的特征图;最后,通过全连接层判别输出最佳检测窗口,完成人脸检测全过程。结果 实验选取FDDB人脸检测数据集中包含人脸多姿态变化以及人脸面部特征信息不完整等情况的图像进行测试,TC_CNN方法人脸检测率达到96.39%,误检率低至3.78%,相比当前流行方法在保证算法效率的同时检测率均有提高。结论 两层级联卷积神经网络人脸检测方法能够在人脸多姿态变化和面部特征信息不完整等情况下实现精准检测,保证较高的检测率,有效降低误检率,方法具有较好的鲁棒性和泛化能力。     

Automated emotion recognition employing a novel modified binary quantum‐behaved gravitational search algorithm with differential mutation

The present paper proposes a supervised learning based automated human facial emotion recognition strategy with a feature selection scheme employing a novel variation of the gravitational search algorithm (GSA). The initial feature set is generated from the facial images by using the 2‐D discrete cosine transform (DCT) and then the proposed modified binary quantum GSA with differential mutation (MBQGSA‐DM) is utilized to select a sub‐set of features with high discriminative power. This is achieved by minimising the cost function formulated as the ratio of the within class and interclass distances. The overall system performs its final classification task based on selected feature inputs, utilising a back propagation based artificial neural network (ANN). Extensive experimental evaluations are carried out utilising a standard, benchmark emotion database, that is, Japanese Female Facial Expresssion (JAFFE) database and the results clearly indicate that the proposed method outperforms several existing techniques, already known in literature for solving similar problems. Further validation has also been carried out on a facial expression database developed at Jadavpur University, Kolkata, India and the results obtained further strengthen the notion of superiority of the proposed method.     

基于主成分分析禁忌搜索和决策树分类的异常流量检测方法

真实网络流量包括大量特征属性,现有基于特征分析的异常流量检测方法无法满足高维特征分析要求。提出一种基于主成分分析和禁忌搜索(PCA-TS)的流量特征选择算法结合决策树分类的异常流量检测方法,通过PCA-TS对高维特征进行特征约减和近优特征子集选择,为决策树分类方法提供有效的低维特征属性,结合决策树分类精度和处理效率高的优点,采用半监督学习方式进行异常流量实时检测。实验表明,与传统异常检测方法相比,此方法具有更高的检测精度和更低的误检率,其检测性能受样本规模影响较小,且对未知异常可以进行有效检测     

基于本体特征的影评细粒度情感分类

针对中文影评情感分类中缺少特征属性及情感强度层面的粒度划分问题,提出一种基于本体特征的细粒度情感分类模型。首先,利用词频逆文档频率(TF-IDF)和TextRank算法提取电影特征,构建本体概念模型。其次,将电影特征属性和普鲁契克多维度情绪模型与双向长短时记忆网络(Bi-LSTM)融合,构建了在特征粒度层面和八分类情感强度下的细粒度情感分类模型。实验中,本体特征分析表明:观影人对故事属性关注度最高,继而是题材、人物、场景、导演等特征;模型性能分析表明:基于特征粒度和八分类情感强度,与应用情感词典、机器学习、Bi-LSTM网络算法在整体粒度和三分类情感强度层面的其他5个分类模型相比,该模型不仅有较高的F1值(0. 93),而且还能提供观影人对电影属性的情感偏好和情感强度参考,实现了中文影评更细粒度的情感分类。     

Audio-visual emotion fusion (AVEF): A deep efficient weighted approach

The multi-modal emotion recognition lacks the explicit mapping relation between emotion state and audio and image features, so extracting the effective emotion information from the audio/visual data is always a challenging issue. In addition, the modeling of noise and data redundancy is not solved well, so that the emotion recognition model is often confronted with the problem of low efficiency. The deep neural network (DNN) performs excellently in the aspects of feature extraction and highly non-linear feature fusion, and the cross-modal noise modeling has great potential in solving the data pollution and data redundancy. Inspired by these, our paper proposes a deep weighted fusion method for audio-visual emotion recognition. Firstly, we conduct the cross-modal noise modeling for the audio and video data, which eliminates most of the data pollution in the audio channel and the data redundancy in visual channel. The noise modeling is implemented by the voice activity detection(VAD), and the data redundancy in the visual data is solved through aligning the speech area both in audio and visual data. Then, we extract the audio emotion features and visual expression features via two feature extractors. The audio emotion feature extractor, audio-net, is a 2D CNN, which accepting the image-based Mel-spectrograms as input data. On the other hand, the facial expression feature extractor, visual-net, is a 3D CNN to which facial expression image sequence is feeded. To train the two convolutional neural networks on the small data set efficiently, we adopt the strategy of transfer learning. Next, we employ the deep belief network(DBN) for highly non-linear fusion of multi-modal emotion features. We train the feature extractors and the fusion network synchronously. And finally the emotion classification is obtained by the support vector machine using the output of the fusion network. With consideration of cross-modal feature fusion, denoising and redundancy removing, our fusion method show excellent performance on the selected data set.     

Incremental Clustering-Based Facial Feature Tracking Using Bayesian ART

Person-independent, emotion specific facial feature tracking have been of interest in the machine vision society for decades. Among various methods, the constrained local model (CLM) has shown significant results in person-independent feature tracking. In 63this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. Considering a 17-point feature model on the frontal face region, the proposed tracking framework incorporates CLM with two incremental clustering algorithms to increase robustness and minimize tracking error during feature tracking. The Patch Clustering algorithm is applied to build an appearance model of face frames by organizing previously encountered similar patches into clusters while the shape Clustering algorithm is applied to build a structure model of face shapes by organizing previously encountered similar shapes into clusters followed by Bayesian adaptive resonance theory (ART). Both models are used to explore the similar features/shapes in the successive images. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed incremental clustering-based facial feature tracking (ICFFT) is evaluated using the FGnet database and the extended Cohn-Kanade (CK+) database. ICFFT demonstrates better results than baseline-method CLM and provides robust tracking as well as improved localization accuracy of emotion specific facial features tracking.     

基于多维特征及BP网络的高分辨雷达目标识别

高分辨雷达目标的识别性能取决于目标特征的提取以及分类器的设计。为解决雷达高分辨距离像（HRRP）的方位、平移和幅度敏感性问题,采用了序贯预处理方法,有效提高了HRRP的信噪比。通过提取能较好反映雷达目标散射点回波特性的多维特征向量,设计BP神经网络作为分类器,提出了一种基于目标多维特征向量以及BP神经网络的高分辨雷达目标识别方法。利用在微波暗室测量获得的三种国产飞机模型回波数据进行目标识别处理,实验结果表明,提出的方法能有效地完成三种目标识别任务,在虚警率低于3%的情况下正确识别率优于95%。     

Brain tumor diagnosis based on artificial neural network and a chaos whale optimization algorithm

Accurate and early detection of the brain tumor region has a great impact on the choice of treatment, its success rate, and the follow-up of the disease process over time. This study presents a new bioinspired technique for the early detection of the brain tumor area to improve the chance of completely healing. The study presents a multistep technique to detect the brain tumor area. Herein, after image preprocessing and image feature extraction, an artificial neural network is used to determine the tumor area in the image. The method is based on using an improved version of the whale optimization algorithm for optimal selection of the features and optimizing the artificial neural network weights for classification. Simulation results of the proposed method are applied to FLAIR, T1, and T2 datasets and are compared with different algorithms. Three performance indexes including correct detection rate, false acceptance rate, and false rejection rate are selected for the system performance analysis. Final results showed the superiority of the proposed method toward the other similar methods.     

基于四元数局部编码和卷积网络的表情识别

为充分利用彩色图像的颜色信息和通道之间的关联性,提出一种联合四元数矩阵相位信息和幅值信息的特征提取方法,结合卷积神经网络(CNN)进行表情识别。将彩色表情图像表示为纯四元数矩阵并进行Clifford平移,对相位和幅值分别进行局部二值模式(LBP)编码,提取多尺度融合的图像特征,将特征输入CNN进行训练并分类。实验结果表明,该算法在RafD和MMI表情库上的识别率分别为79.42%和93.28%,相比其它表情识别算法,识别率更高且识别效果稳定。     

A new approach for oil tank detection using deep learning features with control false alarm rate in high-resolution satellite imagery

ABSTRACT

Oil tank detection is a challenging task, primarily due to high time-consumption. This paper aims at further investigating this challenge and proposes a new hierarchical approach to detect oil tanks, especially with respect to how false alarm rates are reduced. The proposed approach is divided into four stages: region of interest (ROI) extraction, circular object detection, feature extraction, and classification. The first stage, which is a key component of this approach to reduce false alarm and processing time, is applied by an improved faster region-based convolutional neural network (Faster R-CNN) to extract oil depots. In the second stage, a number of candidate objects of the target are selected from the extracted ROIs by a fast circle detection method. Afterwards, in the third stage, a robust feature extractor based on a combination of the output feature vectors from convolutional neural network (CNN), as a high-level feature extractor, and histogram of oriented gradients (HOG), as a low-level feature extractor, are used for representing features of various targets. Finally, the support vector machine (SVM) is employed for classification. The experimental results confirm that the proposed approach has good prediction accuracy and is able to reduce the false alarm rates.     

Quantum and impulse noise filtering from breast mammogram images

Recent advances in the field of image processing have shown that level of noise highly affect the quality and accuracy of classification when working with mammographic images. In this paper, we have proposed a method that consists of two major modules: noise detection and noise filtering. For detection purpose, neural network is used which effectively detect the noise from highly corrupted images. Pixel values of the window and some other features are used as feature for the training of neural network. For noise removal, three filters are used. The weighted average value of these three filters is filled on noisy pixels. The proposed technique has been tested on salt & pepper and quantum noise present in mammogram images. Peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) are used for comparison of proposed technique with different existing techniques. Experiments shows that proposed technique produce better results as compare to existing methods.     

基于EEG和DE-CNN-GRU的情绪识别

近年,情绪识别研究已经不再局限于面部和语音识别,基于脑电等生理信号的情绪识别日趋火热.但由于特征信息提取不完整或者分类模型不适应等问题,使得情绪识别分类效果不佳.基于此,本文提出一种微分熵(DE)、卷积神经网络(CNN)和门控循环单元(GRU)结合的混合模型(DE-CNN-GRU)进行基于脑电的情绪识别研究.将预处理后的脑电信号分成5个频带,分别提取它们的DE特征作为初步特征,输入到CNN-GRU模型中进行深度特征提取,并结合Softmax进行分类.在SEED数据集上进行验证,该混合模型得到的平均准确率比单独使用CNN或GRU算法的平均准确率分别高出5.57%与13.82%.     

基于K-L变换和神经网络分类的微钙化点检测新方法

目前一般的乳腺X光片微钙化点检测系统大致都包括:图像预处理和分割;病理图像的特征提取和分类;辅助诊断和分析等几个步骤,其中神经网络经常用于特征提取和分类阶段。为了提高神经网络的分类能力,需要采用最具代表性的特征作为分类系统的输入部分,而且采用的特征数目要有利于最有效的特征提取,否则会使分类的效率大打折扣。所以分类系统一个重要的任务是对神经网络的输入样本集进行训练和特征值的优化,本文采用K-L变换用于降低输入特征向量的维数,从而达到参数优化的目的。试验表明,该方法可以有效地提高系统的灵敏度,降低诊断的假阳性。     

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

     

A robust incremental clustering-based facial feature tracking

Emerging significance of person-independent, emotion specific facial feature tracking has been actively tracked in the machine vision society for decades. Among distinct methods, the Constrained Local Model (CLM) has shown significant results in person-independent feature tracking. In this paper, we propose an automatic, efficient, and robust method for emotion specific facial feature detection and tracking from image sequences. A novel tracking system along with 17-point feature model on the frontal face region has also been proposed to facilitate the tracking of human basic facial expressions. The proposed feature tracking system keeps patch images and face shapes till certain number of key frames incorporating CLM-based tracker. After that, incremental patch and shape clustering algorithms is applied to build appearance model and structure model of similar patches and similar shapes respectively. The clusters in each model are built and updated incrementally and online, controlled by amount of facial muscle movement. The overall performance of the proposed Robust Incremental Clustering-based Facial Feature Tracking (RICFFT) is evaluated on the FGnet database and the Extended Cohn-Kanade (CK+) database. RICFFT demonstrates mean tracking accuracy of 97.45% and 96.64% for FGnet and CK+ database respectively. Also, RICFFT is more robust by minimizing average shape distortion error of 0.20% and 1.86% for FGnet and CK+ (apex frame) database, as compared with classic method CLM.     

基于主元神经网络和SVM的入侵特征抽取和检测

目前基于机器学习的入侵检测研究都是从提高检测精度的分类器算法设计出发,大多未考虑对样本特征的分析。文章提出了一种基于特征抽取的异常检测方法,应用主元神经网络(PCNN)抽取入侵特征,再应用SVM检测入侵。采用广义Hebb学习规则训练线性主元神经网络,SVM采用基于网格粒度搜索获得最优参数。利用KDD99数据集,将线性PCNN-SVM与SVM进行比较,结果显示在不降低分类器性能的情况下,PCNN特征抽取方法能对输入数据有效降维。     

A new genetic feature selection with neural network ensemble

A neural network ensemble is a learning paradigm in which a finite collection of neural networks is trained for the same task. Ensembles generally show better classification and generalization performance than a single neural network does. In this paper, a new feature selection method for a neural network ensemble is proposed for pattern classification. The proposed method selects an adequate feature subset for each constituent neural network of the ensemble using a genetic algorithm. Unlike the conventional feature selection method, each neural network is only allowed to have some (not all) of the considered features. The proposed method can therefore be applied to huge-scale feature classification problems. Experiments are performed with four databases to illustrate the performance of the proposed method.     

An efficient deep learning technique for facial emotion recognition

Emotion recognition from facial images is considered as a challenging task due to the varying nature of facial expressions. The prior studies on emotion classification from facial images using deep learning models have focused on emotion recognition from facial images but face the issue of performance degradation due to poor selection of layers in the convolutional neural network model.To address this issue, we propose an efficient deep learning technique using a convolutional neural network model for classifying emotions from facial images and detecting age and gender from the facial expressions efficiently. Experimental results show that the proposed model outperformed baseline works by achieving an accuracy of 95.65% for emotion recognition, 98.5% for age recognition, and 99.14% for gender recognition.

     

Emotion recognition from geometric facial features using self-organizing map

This paper presents a novel emotion recognition model using the system identification approach. A comprehensive data driven model using an extended Kohonen self-organizing map (KSOM) has been developed whose input is a 26 dimensional facial geometric feature vector comprising eye, lip and eyebrow feature points. The analytical face model using this 26 dimensional geometric feature vector has been effectively used to describe the facial changes due to different expressions. This paper thus includes an automated generation scheme of this geometric facial feature vector. The proposed non-heuristic model has been developed using training data from MMI facial expression database. The emotion recognition accuracy of the proposed scheme has been compared with radial basis function network, multi-layered perceptron model and support vector machine based recognition schemes. The experimental results show that the proposed model is very efficient in recognizing six basic emotions while ensuring significant increase in average classification accuracy over radial basis function and multi-layered perceptron. It also shows that the average recognition rate of the proposed method is comparatively better than multi-class support vector machine.