Research on the Pedestrian Re-Identification Method Based on Local Features and Gait Energy Images

The appearance of pedestrians can vary greatly from image to image, and different pedestrians may look similar in a given image. Such similarities and variabilities in the appearance and clothing of individuals make the task of pedestrian re-identification very challenging. Here, a pedestrian re-identification method based on the fusion of local features and gait energy image (GEI) features is proposed. In this method, the human body is divided into four regions according to joint points. The color and texture of each region of the human body are extracted as local features, and GEI features of the pedestrian gait are also obtained. These features are then fused with the local and GEI features of the person. Independent distance measure learning using the cross-view quadratic discriminant analysis (XQDA) method is used to obtain the similarity of the metric function of the image pairs, and the final similarity is acquired by weight matching. Evaluation of experimental results by cumulative matching characteristic (CMC) curves reveals that, after fusion of local and GEI features, the pedestrian reidentification effect is improved compared with existing methods and is notably better than the recognition rate of pedestrian re-identification with a single feature.     

基于多特征和多核学习的行人检测方法的研究

行人检测系统涉及交通安全问题,需要很高的鲁棒性,基于单特征结合单核支持向量机的方法效果有限,为解决这一问题,提出采用多特征和多核学习的方法来提升系统的鲁棒性,通过将积分信道特征、多层次导向边缘能量特征和CENTRIST特征分别与直方图交叉核、高斯核和多项式核进行线性组合,采用简单多核学习（Simple MKL）来分别计算核函数的权重系数,将多核学习方法与经典的梯度直方图特征/支持向量机、多尺度梯度直方图特征/直方图交叉核支持向量机和特征融合/直方图交叉核支持向量机的行人检测方法进行比较,实验表明所提出的行人检测算法的鲁棒性有明显提升。     

基于机器视觉的VVT发动机转子缺陷检测系统设计

针对目前工业生产线上的VVT（variable valve timing,可变气门正时）发动机转子存在尺寸误差和外观缺陷等问题,大多数工厂采用人工方式来测量尺寸和检测缺陷,但人工测量和检测的精度易受外部环境和主观意识的影响,从而产生过检和漏检。为此,设计了一种基于机器视觉的VVT发动机转子缺陷检测系统。首先,针对VVT发动机转子凸台外边缘磕碰点对外径测量的干扰,提出一种基于梯度特征和位置序列的磕碰点检测算法,先通过分析轮廓点的距离-位置序列、梯度-位置序列曲线来筛选并去除凸台外边缘的磕碰点,再采用最小二乘法对筛选后的轮廓点进行圆弧拟合以实现外径测量。然后,针对VVT发动机转子端面上的划痕、划伤等缺陷,提出一种基于改进HOG（histogram of oriented gradient,方向梯度直方图）特征的SVM（support vector machines,支持向量机）分类算法,先采用连通域分析方法得到待检测的目标区域,再提取目标区域的改进HOG特征,并利用SVM进行分类,以实现端面缺陷的检测。实验结果表明,所设计的缺陷检测系统在测量VVT发动机转子外径时的绝对精度可达到0.01 mm,且能够准确地筛选出凸台外边缘的磕碰点;因改进的HOG特征优于传统的HOG特征,所设计的缺陷检测系统在检测转子端面缺陷时具有较低的过检率和漏检率。综上可知,基于机器视觉的VVT发动机转子缺陷检测系统可实现外径的精确测量和外观缺陷的有效检测,基本满足工业检测要求,具有较高的实用价值。     

Providing an efficient intelligent transportation system through detection,tracking and recognition of the region of interest in traffic signs by using non-linear SVM classifier in line with histogram oriented gradient and Kalman filter approach

With a focus on new researches in the area of intelligent transportation systems (ITS), an efficient approach has been investigated here. Based on the present view point, analysis of traffic signs are first considered via intelligence based approach, which is carried out through three main stages including detection, tracking and recognition, respectively, in this research. The key role of detection is to identify traffic signs by classification of road sign shapes in accordance with their signatures. This classification consists of four different shapes of circle, semicircle, triangle and square, as well. The linear classification of traffic sign is also carried out via support vector machine (SVM) by using one against all (OAA), since the present SVMs classifiers realized via linear kernel. The next step is to track traffic sign. It should be noted that this technique is now developed to reduce the searching mode in case of the whole area to be optimized its computational processing, consequently. This research work is investigated by realizing Kalman filter approach, where, finally, in recognition step, a feature of the region of interest (ROI) has been extracted for SVM classification. Histogram of oriented gradient (HOG) is realized in organizing the approach, as long as Gaussian kernel is also developed for non-linear SVM classifier.     

基于SVM的高通量dPCR基因芯片荧光图像分类研究

目的 为了实现高通量dPCR基因芯片荧光图像的亮点分类与计数,提出一种基于支持向量机（SVM）的荧光图像分类与计数方法。方法 首先对荧光图像进行去噪、对比度增强等图像预处理,对预处理后荧光图像进行亮点区域提取标注,去除背景与暗点的冗余信息,利用方向梯度直方图（Histogram of Oriented Gradient, HOG）提取鉴别特征,计算合并所有样本的亮点特征得到HOG特征向量,根据已得到的HOG特征向量创建一个线性SVM分类器,利用训练好的SVM分类器对荧光图像亮点进行分类与计数。结果 对比传统算法,文中算法具有较高的分类识别精度,平均准确率高达98%以上,可以很好地实现荧光图像亮点分类与计数。结论 在有限的小样本标注数据下,文中算法具有良好的分类性能,能够有效识别荧光图像中的亮点,对其他荧光图像分类研究也具有一定参考价值。     

Vibration data-driven machine learning architecture for structural health monitoring of steel frame structures

A vibration data-based machine learning architecture is designed for structural health monitoring (SHM) of a steel plane frame structure. This architecture uses a Bag-of-Features algorithm that extracts the speeded-up robust features (SURF) from the time-frequency scalogram images of the registered vibration data. The discriminative image features are then quantised to a visual vocabulary using K-means clustering. Finally, a support vector machine (SVM) is trained to distinguish the undamaged and multiple damage cases of the frame structure based on the discriminative features. The potential of the machine learning architecture is tested for an unseen dataset that was not used in training as well as with some datasets from entirely new damages close to existing (i.e., trained) damage classes. The results are then compared with those obtained using three other combinations of features and learning algorithms—(i) histogram of oriented gradients (HOG) feature with SVM, (ii) SURF feature with k-nearest neighbours (KNN) and (iii) HOG feature with KNN. In order to examine the robustness of the approach, the study is further extended by considering environmental variabilities along with the localisation and quantification of damage. The experimental results show that the machine learning architecture can effectively classify the undamaged and different joint damage classes with high testing accuracy that indicates its SHM potential for such frame structures.     

Earlier detection of cancer regions from MR image features and SVM classifiers

In this article, we examine the use of several segmentation algorithms for medical image classification. This work detects the cancer region from magnetic resonance (MR) images in earlier stage. This is accomplished in three stages. In first stage, four kinds of region‐based segmentation techniques are used such as K‐means clustering algorithm, expectation–maximization algorithm, partial swarm optimization algorithm, and fuzzy c‐means algorithm. In second stage, 18 texture features are extracting using gray level co‐occurrence matrix (GLCM). In stage three, classification is based on multi‐class support vector machine (SVM) classifier. Finally, the performance analysis of SVM classifier is analyzed using the four types of segmentation algorithm for a group of 200 patients (32—Glioma, 32—Meningioma, 44—Metastasis, 8—Astrocytoma, 72—Normal). The experimental results indicate that EM is an efficient segmentation method with 100% accuracy. In SVM, quadratic and RBF (σ = 0.5) kernel methods provide the highest classification accuracy compared to all other SVM kernel methods. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 196–208, 2016     

基于时间序列数据和支持向量机的纳米加工AFM刀尖损伤监测

研究了基于支持向量机(SVM)的时间序列数据分析和模式识别,以监测基于AFM尖端的纳米加工过程在加工性能和尖端磨损方面的状态变化。具有瞬态、非线性和非静止特性的时间序列数据(即来自过程的加工力)由数据采集系统收集。提取3种状态检测特征,包括最大侧向加工力、侧向加工力值峰间距以及侧向加工力的方差,以对纳米加工过程的状态进行分类。构造具有(高斯)径向基核函数(RBF内核)的定向非循环图支持向量机(DAGSVM)以识别尖端状态。使用多元SVM分类机,将加工过程和刀尖磨损分为初始磨损、过渡区域磨损以及尖端失效(破裂/磨损严重的加工/不加工)3个区域。实验数据表明,二元和三元分类中SVM的准确率均超过94.73％。     

Alzheimer disease classification using KPCA,LDA, and multi‐kernel learning SVM

Early diagnosis of Alzheimer disease (AD) and mild cognitive impairment (MCI) is always useful. Preventive measures might have an impact on reducing AD risk factors. Structural magnetic resonance (MR) imaging, one of the vital sensitive biomarkers for cerebral atrophy in the brain, is used to extract volumetric feature by FreeSurfer and the CIVET toolbox. All of the structural magnetic resonance imaging (s‐MRI) data that we used were downloaded from the Alzheimer's disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu) of imaging data. This novel approach is applied for the diagnosis of AD and MCI from healthy controls (HCs) combining extracted features with the MMSE (mini‐mental state examination) scores, applying a two sample t‐test to select a subset of features. The subset of features is fed to kernel principal component analysis (KPCA) module to project data onto the reduced principal component coefficients at higher dimensional kernel space to increase the linear separability. Then, the kernel PCA coefficients are projected into the more efficient linear discriminant space using linear discriminant analysis. A multi‐kernel learning support vector machine (SVM) is used on newly projected data for stratification of AD and MCI from HCs. Using this approach, we obtain 93.85% classification accuracy when detecting AD from HCs for segmented volumetric features (using FreeSurfer) with high sensitivity and specificity. When distinguishing MCI from HCs and AD using volumetric features after subcortical segmentation, the detection rate reaches 86.54% and 75.12%, respectively.     

时频图像特征用于声场景分类

为解决根据音频流识别声场景的问题,对音频信号进行恒Q变换,得到其时频表达图像,然后进行滤波平滑等处理,随之提取能够表述信号谱能量变化方向信息的梯度直方图特征,以及能够捕捉信号谱纹理信息的局部二值模式特征,输入具有线性核函数的支持向量机分类器,对不同声场景数据进行分类实验。结果表明,相对于传统的时频域特征和梅尔频率倒谱系数特征,所提出的特征基本能够捕捉到给定声场景具有区分度的信息,所得分类率更高,且两者的互补作用使得联合特征分类效果达到最优,该方法为声信号特征提取贡献了一种新思路。     

基于混沌理论和支持向量机的人脸识别方法

针对如何选定主成分分析(PCA)特征维数和如何选定支持向量机(SVM)的参数来进一步提高人脸识别系统性能的问题,提出了一种基于混沌理论和支持向量机的人脸识别方法.首先,在统一的目标函数下,在采用PCA方法对人脸图像进行降维和将得到的特征送入SVM中进行训练期间,使用具有可操作性的改进混沌优化算法同时对PCA图像特征维数和分类器参数进行优化选择,然后用得到的优化人脸特征和最佳参数的分类器对未知图像进行识别.基于该方法,对ORL和Yale人脸库进行实验,其识别率都高达99%以上,仿真结果表明,该方法极大地提高了人脸识别能力.     

Feature selection and fault‐severity classification–based machine health assessment methodology for point machine sliding‐chair degradation

In this paper, we propose an offline and online machine health assessment (MHA) methodology composed of feature extraction and selection, segmentation‐based fault severity evaluation, and classification steps. In the offline phase, the best representative feature of degradation is selected by a new filter‐based feature selection approach. The selected feature is further segmented by utilizing the bottom‐up time series segmentation to discriminate machine health states, ie, degradation levels. Then, the health state fault severity is extracted by a proposed segment evaluation approach based on within segment rate‐of‐change (RoC) and coefficient of variation (CV) statistics. To train supervised classifiers, a priori knowledge about the availability of the labeled data set is needed. To overcome this limitation, the health state fault‐severity information is used to label (eg, healthy, minor, medium, and severe) unlabeled raw condition monitoring (CM) data. In the online phase, the fault‐severity classification is carried out by kernel‐based support vector machine (SVM) classifier. Next to SVM, the k‐nearest neighbor (KNN) is also used in comparative analysis on the fault severity classification problem. Supervised classifiers are trained in the offline phase and tested in the online phase. Unlike to traditional supervised approaches, this proposed method does not require any a priori knowledge about the availability of the labeled data set. The proposed methodology is validated on infield point machine sliding‐chair degradation data to illustrate its effectiveness and applicability. The results show that the time series segmentation‐based failure severity detection and SVM‐based classification are promising.     

视觉自适应行人计数

基于视觉的行人计数技术因其广阔的应用前景逐步成为智能视觉监控领域的一个研究热点。本文提出了一种基于虚拟门上前景像素点个数的行人计数方法。该方法分为学习和计数两个过程。在学习过程中,本方法采用基于行人检测的方法获取场景中的若干行人模型,并利用线性拟合为虚拟门上的点赋予权重。在计数过程中,本方法在考虑虚拟门上前景像素的权重、运动矢量的大小和方向等信息的基础上,逐帧统计虚拟门上前景点个数,通过特定时间内累计的前景点数量来确定通过虚拟门的行人数量。实验表明,该方法能够在保证计数精度的前提下,有较好的实时性能。     

MRI brain image classification—a hybrid approach

The present article proposes a novel computer‐aided diagnosis (CAD) technique for the classification of the magnetic resonance brain images. The current method adopt color converted hybrid clustering segmentation algorithm with hybrid feature selection approach based on IGSFFS (Information gain and Sequential Forward Floating Search) and Multi‐Class Support Vector Machine (MC‐SVM) classifier technique to segregate the magnetic resonance brain images into three categories namely normal, benign and malignant. The proposed hybrid evolutionary segmentation algorithm which is the combination of WFF(weighted firefly) and K‐means algorithm called WFF‐K‐means and modified cuckoo search (MCS) and K‐means algorithm called MCS‐K‐means, which can find better cluster partition in brain tumor datasets and also overcome local optima problems in K‐means clustering algorithm. The experimental results show that the performance of the proposed algorithm is better than other algorithms such as PSO‐K‐means, color converted K‐means, FCM and other traditional approaches. The multiple feature set comprises color, texture and shape features derived from the segmented image. These features are then fed into a MC‐SVM classifier with hybrid feature selection algorithm, trained with data labeled by experts, enabling the detection of brain images at high accuracy levels. The performance of the method is evaluated using classification accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) curves. The proposed method provides highest classification accuracy of greater than 98% with high sensitivity and specificity rates of greater than 95% for the proposed diagnostic model and this shows the promise of the approach. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 226–244, 2015     

基于图像序列的运动目标检测识别的关键技术研究

为提高运动目标检测的识别效果,通过分析、综合比较各种运动目标检测算法的优劣性,提出了基于全局自适应帧差法和基于码本模型的背景减除法对同一运动目标进行检测。通过对运动目标检测提取运动目标的掩膜,对掩膜进行外接矩形分析,从而得到包围运动目标的矩形框;将矩形框内的图片截取出来,调整该矩形并提取图片的HOG特征,最后通过训练好的SVM进行分类。在训练过程中,针对难易情况应用自举法对训练器进行优化。实验表明,与传统HOG+SVM多尺度检测算法相比,该方法在速度和准确性上可提升20%左右,可作为运动目标检测与识别的参考方法。     

基于相空间重构和非线性流形的滚动轴承复合故障诊断

针对滚动轴承振动信号的非平稳以及非线性特点,提出了一种基于相空间重构和非线性流形的滚动轴承复合故障诊断方法。该方法首先将滚动轴承一维振动信号重构到高维相空间,然后计算重构信号协方差矩阵的特征值,以此组成轴承故障诊断原始特征集;采用局部切空间排列算法对原始特征集作特征压缩后,将获得的新的特征输入到K-means分类器中进行轴承故障的识别与聚类。实验结果表明,与经典的线性分析方法PCA相比,该方法的聚类效果更好。     

An Efficient Detection Approach of Content Aware Image Resizing

Content aware image resizing (CAIR) is an excellent technology used widely for image retarget. It can also be used to tamper with images and bring the trust crisis of image content to the public. Once an image is processed by CAIR, the correlation of local neighborhood pixels will be destructive. Although local binary patterns (LBP) can effectively describe the local texture, it however cannot describe the magnitude information of local neighborhood pixels and is also vulnerable to noise. Therefore, to deal with the detection of CAIR, a novel forensic method based on improved local ternary patterns (ILTP) feature and gradient energy feature (GEF) is proposed in this paper. Firstly, the adaptive threshold of the original local ternary patterns (LTP) operator is improved, and the ILTP operator is used to describe the change of correlation among local neighborhood pixels caused by CAIR. Secondly, the histogram features of ILTP and the gradient energy features are extracted from the candidate image for CAIR forgery detection. Then, the ILTP features and the gradient energy features are concatenated into the combined features, and the combined features are used to train classifier. Finally support vector machine (SVM) is exploited as a classifier to be trained and tested by the above features in order to distinguish whether an image is subjected to CAIR or not. The candidate images are extracted from uncompressed color image database (UCID), then the training and testing sets are created. The experimental results with many test images show that the proposed method can detect CAIR tampering effectively, and that its performance is improved compared with other methods. It can achieve a better performance than the state-of-the-art approaches.     

基于多级特征融合的体素三维目标检测网络

目的 为精确分析点云场景中待测目标的位置和类别信息,提出一种基于多级特征融合的体素三维目标检测网络。方法 以2阶段检测算法Voxel?RCNN作为基线模型,在检测一阶段,增加稀疏特征残差密集融合模块,由浅入深地对逐级特征进行传播和复用,实现三维特征充分的交互融合。在二维主干模块中增加残差轻量化高效通道注意力机制,显式增强通道特征。提出多级特征及多尺度核自适应融合模块,自适应地提取各级特征的关系权重,以加权方式实现特征的强融合。在检测二阶段,设计三重特征融合策略,基于曼哈顿距离搜索算法聚合邻域特征,并嵌入深度融合模块和CTFFM融合模块提升格点特征质量。结果 实验于自动驾驶数据集KITTI中进行模拟测试,相较于基线网络,在3种难度等级下,一阶段检测模型的行人3D平均精度提升了3.97%,二阶段检测模型的骑行者3D平均精度提升了3.37%。结论 结果证明文中方法能够显著提升目标检测性能,且各模块具有较好的移植性,可灵活嵌入到体素类三维检测模型中,带来相应的效果提升。     

基于改进YOLOv5的试剂卡印刷缺陷检测算法

目的 针对试剂卡生产企业采用人工分选印刷缺陷的试剂卡存在效率低、成本高、易漏检的问题，提出一种基于深度神经网络YOLOv5s的改进试剂卡印刷缺陷检测算法YOLOv5s-EF。方法 通过图像预处理算法获得高质量的缺陷图像数据集，在YOLOv5s的主干特征提取网络中添加高效通道注意力（Efficient Channel Attention, ECA）机制，增强特征图中重要特征的表示能力；引入焦点损失函数（Focal Loss）来缓解正负样本不均衡的影响；结合印刷区域的定位结果，二次精确定位并构建方位特征向量，提出一种特征向量相似度匹配方法。结果 实验结果表明，本文提出的试剂卡印刷缺陷检测算法在测试集上的检测平均准确度可以达到97.3%，速度为22.6帧/s。结论 相较于其他网络模型，本文提出的方法可以实现对多种印刷缺陷的识别与定位，模型具有较好的检测速度和鲁棒性，有利于提高企业生产的智能化水平。