基于X射线钢芯传送带图像的缺陷检测算法

钢丝绳芯输送带是煤矿的主要传输设备,然而煤炭生产常常会因为钢丝绳缺陷引起的崩断而中断.因此,为了保证安全生产,防止恶性事故发生,需要检测钢丝绳芯输送带的缺陷情况.本文以线性X射线阵列采集运行钢丝绳芯皮带的图像序列,根据其图像纹理特征,提出了一种线状局部二进制模式纹理编码算子(line-shaped LBP)检测钢丝绳芯图像缺陷,并在VC++平台上实现了钢丝绳芯输送带在线缺陷检测、存储、报告打印和显示缺陷的目标.大量实验结果表明,该算法检测精度平均值可达到90%.     

岩心颗粒彩色图像的多维特征KFCM聚类分割算法

岩心颗粒的彩色图像包含的信息具有复杂性和多样性,除了人眼视觉系统容易感知的颜色与空间形状特征之外,还隐含着更深层次的纹理特征信息。提出一种多维特征核模糊C均值(Kernel Fuzzy C-Means,KFCM)聚类分割算法:首先使用Gabor滤波器组在频域的不同尺度和方向上对岩心颗粒彩色图像进行卷积滤波处理,并将Gabor滤波结果作为频谱的局部纹理特征;然后将纹理特征、颜色特征以及图像像素点空间位置信息合并到核模糊C均值聚类算法中,从而实现岩心颗粒彩色图像的分割。结果表明:与其他算法的分割结果相比,多维特征KFCM聚类分割算法能更准确地识别不同类型的岩心颗粒的彩色图像,获得了良好的分割结果。     

基于空间邻域信息的二维模糊聚类图像分割

传统模糊C均值聚类(FCM)算法进行图像分割时仅利用了像素的灰度信息,并且使用对噪声较敏感的欧氏距离作为像素与聚类中心距离度量的标准,因此抗噪性能较差.为了克服传统FCM算法的局限性,本文提出了一种基于空间邻域信息的二维模糊聚类图像分割方法(2DFCM).该方法利用二维直方图描述的像素邻域关系属性,一方面为聚类提供较准确的初始聚类中心,从而避免聚类中的死点问题;另一方面通过提出聚类中心同时在像素值、像素邻域值二维方向上进行更新的思想,建立了包含邻域信息的新的聚类目标函数,实现了图像的分割.实验结果表明,这种方法抗噪能力强、收敛速度快,是一种有效的模糊聚类图像分割方法.     

基于随机权重粒子群和K-均值聚类的图像分割

K-均值聚类具有简单、快速的特点,因此被广泛应用于图像分割领域.但K-均值聚类容易陷入局部最优,影响图像分割效果.针对K-均值的缺点,提出一种基于随机权重粒子群优化（RWPSO）和K-均值聚类的图像分割算法RWPSOK.在算法运行初期,利用随机权重粒子群优化的全局搜索能力,避免算法陷入局部最优;在算法运行后期,利用K-均值聚类的局部搜索能力,实现算法快速收敛.实验表明：RWPSOK算法能有效地克服K-均值聚类易陷入局部最优的缺点,图像分割效果得到了明显改善;与传统粒子群与K-均值聚类混合算法（PSOK）相比,RWPSOK算法具有更好的分割效果和更高的分割效率.     

基于SNIC超像素融合纹理特征和上下文内容的显著性目标检测算法

针对显著性目标检测算法在面对复杂场景图像时存在背景错误凸显和不能凸显纹理细节的问题,提出一种改进的基于SNIC超像素融合纹理特征和上下文内容的显著性目标检测算法。对图像进行SNIC超像素分割,基于超像素的距离、颜色得到超像素显著图;利用LBP算子得到图像的纹理显著图,将超像素显著图以及纹理显著图结合得到初级显著图,最后将初级显著图与CA模型下的显著图融合,得到最终显著图。基于MSRA10K数据集将该文算法与其他5种算法进行对比测试。结果表明：该文所提出的算法与其他现有的显著目标检测算法相比,该文算法可有效抑制相似背景的干扰,突出目标区域的纹理信息,并且具有较高的准确度和稳定性。     

模拟退火与模糊C-均值聚类相结合的图像分割算法

模糊C-均值(FCM)聚类算法是一种结合无监督聚类和模糊集合概念的图像分割技术,比较有效,但存在着受初始聚类中心和隶属度矩阵影响,可能收敛到局部极小的缺点.将模拟退火算法(SA)与模糊C-均值聚类算法相结合,在合理选择冷却进度表的基础上,依据模糊C-均值聚类算法建立模拟退火算法的目标函数,实现了基于模拟退火的模糊C-均值聚类图像分割算法.实验表明,该方法具有搜索全局最优解的能力,因而可得到很好的图像分割结果.     

全局人工鱼群算法在类间方差图像分割中的应用与实现

针对传统类间方差算法中阈值选取效率低、鲁棒性差、分割精度低的问题,根据全局人工鱼群算法可以快速有效地捕捉到图像分割最优阈值,提出了一种基于全局人工鱼群算法的类间方差图像分割算法。该算法将全局人工鱼群算法用于类间方差的寻优过程中,对算法的收敛速度及其分割效果进行了仿真,并与遗传算法、基本人工鱼群算法进行比较,结果表明,该算法提高了收敛速度,改善了纹理信息的准确性,分割精度高、效果理想。     

基于WDFB及形态膨胀的图像压缩算法

将小波和方向滤波器组结合,实现了一种非冗余的图像变换WDFB,它满足各向异性尺度关系,能更稀疏地表示诸如边缘和纹理等几何特征.利用WDFB的优势,提出一种基于形态学操作的有效的图像压缩算法.该算法利用重要树来表达子带间的相关性,同时采用形态膨胀算子来聚类子带内的重要系数.实验结果表明,新算法在PSNR指标上明显优于基于小波的压缩算法,尤其对于含有丰富纹理的图像.例如对于512×512的Barbara图,在0.25bpp压缩率下,新算法比SPIHT和MRWD算法的PSNR分别提高1.08dB和0.87dB.     

面向直方图加权的快速FCM的图像分割算法

提出一种改进的图像分割算法SWFFCM(special weight fast fuzzy C-means algorithm),该方法将需要聚类的二维像素点投影到一维灰度直方图空间,利用不同灰度值图像空间像素离散程度的区别,对一维灰度直方图进行线性加权,每一个灰度值变量使用四分位相对离差系数作为其权值.实验表明,算法减少了FCM(fuzzy C-means algorithm)算法的迭代数量,提高了图像聚类分割速度,减少了像素点错分比例,从而提高了图像的分割精度.     

一种基于mean shift的多通道图像分割算法

目的针对目标与背景对象的色彩值比较接近的RGB图像中,目标对象难以有效分割的问题,探索一种基于mean shift的RGB多通道图像的分割方法。方法根据RGB图像的3个通道对颜色的敏感性差异,运用均值偏移算法对RGB图像的3个通道分层聚类,再引入可靠性因子,分别对3个单通道的各聚类像素进行可靠性计算,并保留可靠性高的像素作为分割结果,最后采用逻辑"或"运算融合单通道的分割结果,得到最终分割图像。结果与一般分割算法相比,该方法的分割效果好,误分率低,改善了图像的分割质量。结论该算法具有很好的推广性,能够应用于彩色印品缺陷检测、彩色包装图像检测中。     

融合卫星云图的直方图统计法纹理检测

纹理检测及分析不仅对于云图的自动识别,而且对云图的日常应用非常重要。本文采用直方图统计法对融合卫星云图进行了纹理检测和分析,提出了采用信息熵度量卫星云图上的“稠密度”,并利用夏季融合云图进行了大量试验。试验结果表明,信息熵纹理检测结果优于其它统计量,能检测出强云团内部的不同纹理特征,且纹理图像可应用于日常气象工作中。本文在深层次、多角度挖掘气象卫星遥感数据信息方面做了一些探索性的工作。     

An Efficient Steganalysis Model Based on Multi-Scale LTP and Derivative Filters

Local binary pattern (LBP) is one of the most advanced image classification recognition operators and is commonly used in texture detection area. Research indicates that LBP also has a good application prospect in steganalysis. However, the existing LBP-based steganalysis algorithms are only capable to detect the least significant bit (LSB) and the least significant bit matching (LSBM) algorithms. To solve this problem, this paper proposes a steganalysis model called msdeLTP, which is based on multi-scale local ternary patterns (LTP) and derivative filters. The main characteristics of the msdeLTP are as follows: First, to reduce the interference of image content on features, the msdeLTP uses derivative filters to acquire residual images on which subsequent operations are based. Second, instead of LBP features, LTP features are extracted considering that the LTP feature can exhibit multiple variations in the relationship of adjacent pixels. Third, LTP features with multiple scales and modes are combined to show the relationship of neighbor pixels within different radius and along different directions. Analysis and simulation show that the msdeLTP uses only 2592-dimensional features and has similar detection accuracy as the spatial rich model (SRM) at the same time, showing the high steganalysis efficiency of the method.     

Characterization of Wire Rope Defects with Gray Level Co-occurrence Matrix of Magnetic Flux Leakage Images

Magnetic flux leakage (MFL) techniques are used extensively for non-intrusively detecting and characterizing wire rope defects. Traditionally, MFL signals are captured with induction coil sensors. However, the output of coil sensors is related to the wire rope speed, and they can only provide the axial distribution along the wire rope. Hall sensors array are designed due to the limitation of coil sensors. In this paper, a Hall sensors array was designed to capture the MFL signals both axially and circumferentially. 30-channel data from Hall sensors are processed to compose a MFL image. A digital image process technique is introduced to preprocess the MFL image, the MFL images from different types of defects show different texture characteristics. Gray level co-occurrence matrix is utilized for feature extraction of the texture in the MFL image. Five typical eigenvalues (contrast, correlation, energy, homogeneity and entropy) are used as the inputs of back propagation (BP) networks. After training with typical samples, the BP networks show good performance in the quantitative recognition of different defects. The result of this work shows that texture analysis method for MFL image is suitable for feature extraction and quantitative detection of wire rope defects.     

Gastrointestinal Tract Infections Classification Using Deep Learning

Automatic gastrointestinal (GI) tract disease recognition is an important application of biomedical image processing. Conventionally, microscopic analysis of pathological tissue is used to detect abnormal areas of the GI tract. The procedure is subjective and results in significant inter-/intra-observer variations in disease detection. Moreover, a huge frame rate in video endoscopy is an overhead for the pathological findings of gastroenterologists to observe every frame with a detailed examination. Consequently, there is a huge demand for a reliable computer-aided diagnostic system (CADx) for diagnosing GI tract diseases. In this work, a CADx was proposed for the diagnosis and classification of GI tract diseases. A novel framework is presented where preprocessing (LAB color space) is performed first; then local binary patterns (LBP) or texture and deep learning (inceptionNet, ResNet50, and VGG-16) features are fused serially to improve the prediction of the abnormalities in the GI tract. Additionally, principal component analysis (PCA), entropy, and minimum redundancy and maximum relevance (mRMR) feature selection methods were analyzed to acquire the optimized characteristics, and various classifiers were trained using the fused features. Open-source color image datasets (KVASIR, NERTHUS, and stomach ULCER) were used for performance evaluation. The study revealed that the subspace discriminant classifier provided an efficient result with 95.02% accuracy on the KVASIR dataset, which proved to be better than the existing state-of-the-art approaches.     

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。     

基于压缩量化与邻域空间LBP算子的图像哈希算法

目的为了解决哈希算法的感知鲁棒性与伪造检测能力不高的问题,提出基于特征压缩机制与邻域空间局部二值模式的紧凑图像哈希算法。方法首先利用2D线性插值技术,对输入图像进行预处理;嵌入Ring分割技术,将其变为二次图像;再利用Gabor滤波技术对其完成过滤;考虑到图像的颜色特征与其内在的空间关系,基于局部二值模式LBP设计邻域空间LBP算子,提取滤波图像的特征;构建特征压缩量化准则,输出紧凑的哈希二值数组;迭代Logistic映射,输出随机序列,通过量化每个序列值输出密钥流,通过构建动态引擎设计分段异加密模型,实现紧凑哈希序列的加密,获取图像哈希;最后计算原始哈希序列与待检测哈希序列的Hamming距离,实现图像信息的安全认证。结果与已有的哈希生成机制相比,文中算法所输出的哈希序列更紧凑,对旋转、伽马校正等篡改操作具有更好的感知鲁棒。结论所提哈希技术具备较高的安全性,在包装图标检索、信息检测等领域具有较好的价值。     

基于奇异熵的钢球表面缺陷特征提取研究

为评价钢球表面缺陷,应用小波分析、奇异值分解和信息熵相结合的方法提取钢球表面特征,基于奇异熵定义钢球表面图像特征参数,计算4种典型钢球表面缺陷图像的特征参数.结果表明:特征参数能反映图像的纹理特征,钢球表面损伤愈大,纹理愈复杂,其特征参数也愈大,特征参数可用于钢球表面缺陷的识别.     

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.