Perceptual adaptive insensitivity for support vector machine image coding

Support vector machine (SVM) learning has been recently proposed for image compression in the frequency domain using a constant /spl epsiv/-insensitivity zone by Robinson and Kecman. However, according to the statistical properties of natural images and the properties of human perception, a constant insensitivity makes sense in the spatial domain but it is certainly not a good option in a frequency domain. In fact, in their approach, they made a fixed low-pass assumption as the number of discrete cosine transform (DCT) coefficients to be used in the training was limited. This paper extends the work of Robinson and Kecman by proposing the use of adaptive insensitivity SVMs for image coding using an appropriate distortion criterion , based on a simple visual cortex model. Training the SVM by using an accurate perception model avoids any a priori assumption and improves the rate-distortion performance of the original approach.     

A Resource Aware MapReduce Based Parallel SVM for Large Scale Image Classifications

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them support vector machines (SVMs) are used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large. This paper presents RASMO, a resource aware MapReduce based parallel SVM algorithm for large scale image classifications which partitions the training data set into smaller subsets and optimizes SVM training in parallel using a cluster of computers. A genetic algorithm based load balancing scheme is designed to optimize the performance of RASMO in heterogeneous computing environments. RASMO is evaluated in both experimental and simulation environments. The results show that the parallel SVM algorithm reduces the training time significantly compared with the sequential SMO algorithm while maintaining a high level of accuracy in classifications.     

No-reference image quality assessment based on localized discrete cosine transform for JPEG compressed images

In this paper, we propose a new no-reference image quality assessment for JPEG compressed images. In contrast to the most existing approaches, the proposed method considers the compression processes for assessing the blocking effects in the JPEG compressed images. These images have blocking artifacts in high compression ratio. The quantization of the discrete cosine transform (DCT) coefficients is the main issue in JPEG algorithm to trade-off between image quality and compression ratio. When the compression ratio increases, DCT coefficients will be further decreased via quantization. The coarse quantization causes blocking effect in the compressed image. We propose to use the DCT coefficient values to score image quality in terms of blocking artifacts. An image may have uniform and non-uniform blocks, which are respectively associated with the low and high frequency information. Once an image is compressed using JPEG, inherent non-uniform blocks may become uniform due to quantization, whilst inherent uniform blocks stay uniform. In the proposed method for assessing the quality of an image, firstly, inherent non-uniform blocks are distinguished from inherent uniform blocks by using the sharpness map. If the DCT coefficients of the inherent non-uniform blocks are not significant, it indicates that the original block was quantized. Hence, the DCT coefficients of the inherent non-uniform blocks are used to assess the image quality. Experimental results on various image databases represent that the proposed blockiness metric is well correlated with the subjective metric and outperforms the existing metrics.

     

WMSN中基于兴趣区域检测的JPEG编码算法

为了提高资源受限的无线多媒体传感器网络中视频监控图像序列的压缩效果,提出一种基于变化检测和DCT系数裁剪的JPEG图像编码方法。通过变化检测算法确定监控图像中的兴趣区域,对于兴趣区域保留全部DCT系数进行编码,在背景区域编码时对DCT系数进行裁剪。算法分析和仿真实验结果表明,提出的方法能同时保证高的压缩率和兴趣区域的图像质量,在图像质量和能量消耗之间达到了一个较好的平衡。     

一种用于文本分类的语义SVM及其在线学习算法

该文利用SVM在小训练样本集条件下仍有高泛化能力的特性,结合文本分类问题中同类别文本的特征在特征空间中具有聚类性分布的特点,提出一种使用语义中心集代替原训练样本集作为训练样本和支持向量的SVM:语义SVM。文中给出语义中心集的生成步骤,进而给出语义SVM的在线学习(在线分类知识积累)算法框架,以及基于SMO算法的在线学习算法的实现。实验结果说明语义SVM及其在线学习算法具有巨大的应用潜力:不仅在线学习速度和分类速度相对于标准SVM及其简单增量算法有数量级提高,而且分类准确率方面具有一定优势。     

OAO-SVMs的训练时间性能分析及算法改进

支持向量机(SVM)算法是统计学习理论中最年轻的分支。结构风险最小化原则使其具有良好的学习推广性。但在实际应用中,训练速度慢一直是支持向量机理论几个亟待解决的问题之一,这一点在SVM向多类问题领域推广时表现的尤为明显。文中将从样本分布与类别数量两方面入手,对传统的SVM多分类OAO算法进行训练时间性能上的分析,并引入分层的思想,提出传统OAO-SVMs算法的改进模型H-OAO-SVMs。通过与其他常见多分类SVMs训练时间的比较表明:改进后的H-OAO-SVMs模型具有更优的训练时间性能。     

基于增量学习支持向量机的音频例子识别与检索

音频例子识别与检索的主要任务是构造一个良好的分类学习机，而在构造过程中，从含有冗余样本的训练库中选择最佳训练例子、节省学习机的训练时间是构造分类机面临的一个挑战，尤其是对含有大样本训练库音频例子的识别．由于支持向量是支持向量机中的关键例子，提出了增量学习支持向量机训练算法．在这个算法中，训练样本被分成训练子库按批次进行训练，每次训练中，只保留支持向量，去除非支持向量．与普通和减量支持向量机对比的实验表明，算法在显著减少训练时间前提下，取得了良好的识别检索正确率．     

Comparison of artificial neural networks and support vector machine classifiers for land cover classification in Northern China using a SPOT-5 HRG image

This article presents a sufficient comparison of two types of advanced non-parametric classifiers implemented in remote sensing for land cover classification. A SPOT-5 HRG image of Yanqing County, Beijing, China, was used, in which agriculture and forest dominate land use. Artificial neural networks (ANNs), including the adaptive backpropagation (ABP) algorithm, Levenberg–Marquardt (LM) algorithm, Quasi-Newton (QN) algorithm and radial basis function (RBF) were carefully tested. The LM–ANN and RBF–ANN, which outperform the other two, were selected to make a detailed comparison with support vector machines (SVMs). The experiments show that those well-trained ANNs and SVMs have no significant difference in classification accuracy, but the SVM usually performs slightly better. Analysis of the effect of the training set size highlights that the SVM classifier has great tolerance on a small training set and avoids the problem of insufficient training of ANN classifiers. The testing also illustrates that the ANNs and SVMs can vary greatly with regard to training time. The LM–ANN can converge very quickly but not in a stable manner. By contrast, the training of RBF–ANN and SVM classifiers is fast and can be repeatable.     

基于支持向量机的自适应图像水印技术

提出一种基于支持向量机的自适应图像空域水印嵌入算法.由于支持向量机与人眼视觉系统在自学习、泛化和非线性逼近等方面具有极大的相似性,算法利用支持向量机模拟人眼视觉特征,结合图像的局部相关特性,自适应地确定图像的最佳嵌入位置和嵌入强度.首先,利用无导师的模糊聚类分析方法对图像各像素进行初步的聚类,为有导师的支持向量机找到分类规则;然后,从各类别中选出隶属度超过一定阈值的像素作为支持向量机分类的训练样本集,建立支持向量机的分类模型,根据此模型对图像各像素再次分类,从而确定水印的最佳嵌入位置;最后结合图像自身的局部相关性,自适应地调整水印嵌入位置的像素值.该算法在提取水印时不需要原始载体图像.实验结果表明,此算法对多种图像处理均具有很好的稳健性和图像感知质量,其性能优于相关文献上的相近方法.     

A MapReduce-based distributed SVM algorithm for automatic image annotation

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them Support Vector Machines (SVMs) have been used extensively due to their generalization properties. However, SVM training is notably a computationally intensive process especially when the training dataset is large. This paper presents MRSMO, a MapReduce based distributed SVM algorithm for automatic image annotation. The performance of the MRSMO algorithm is evaluated in an experimental environment. By partitioning the training dataset into smaller subsets and optimizing the partitioned subsets across a cluster of computers, the MRSMO algorithm reduces the training time significantly while maintaining a high level of accuracy in both binary and multiclass classifications.     

结合DCT和SVM的故障诊断方法研究

针对故障诊断研究中,样本数据维数过高导致故障模式分类时SVM学习强度太大的问题,利用DCT方法在降噪处理时体现出“能量集中”和“高频抑制”的特性,提出一种基于DCT的SVM故障诊断方法。先对故障样本进行DCT降维,再利用SVM方法对主要维离散余弦系数进行模式训练来代替对故障样本的直接训练,从而大大抑制了噪声对故障分类的影响,同时也减少了诊断运算量,最后通过实验仿真验证了算法的有效性。     

一种文本分类的在线SVM学习算法

本文提出了一种用于文本分类的RBF 支持向量机在线学习算法。利用RBF 核函数的局部性,该算法仅对新训练样本的某一大小邻域内且位于“可能带”中的训练样本集进行重新训练,以实现对现有SVM的更新。为高效的实现该邻域大小的自适应确定,使用ξa 泛化错误估计在所有现有训练样本集上对当前SVM的泛化错误进行定性估计。同时引入泛化能力进化因子,使得结果SVM在分类效果上具有自动调整能力,并防止分类能力的退化。在TREC - 5 真实语料上的对比测试结果表明,该算法显著地加速了增量学习的过程而同时保证结果SVM的分类效果。     

Parallelizing multiclass support vector machines for scalable image annotation

Machine learning techniques have facilitated image retrieval by automatically classifying and annotating images with keywords. Among them, Support Vector Machines (SVMs) are used extensively due to their generalization properties. SVM was initially designed for binary classifications. However, most classification problems arising in domains such as image annotation usually involve more than two classes. Notably, SVM training is a computationally intensive process especially when the training dataset is large. This paper presents a resource aware parallel multiclass SVM algorithm (named RAMSMO) for large-scale image annotation which partitions the training dataset into smaller binary chunks and optimizes SVM training in parallel using a cluster of computers. A genetic algorithm-based load balancing scheme is designed to optimize the performance of RAMSMO in balancing the computation of multiclass data chunks in heterogeneous computing environments. RAMSMO is evaluated in both experimental and simulation environments, and the results show that it reduces the training time significantly while maintaining a high level of accuracy in classifications.     

基于JPEG双量化效应的图像盲取证

JPEG图像的双量化效应为JPEG图像的篡改检测提供了重要线索.根据JPEG图像被局部篡改后,又被保存为JPEG格式时,未被篡改的区域(背景区域)的离散余弦变换(DCT)系数会经历双重JPEG压缩,篡改区域的DCT系数则只经历了1次JPEG压缩.而JPEG图像在经过离散余弦变换后其DCT域的交流(AC)系数的分布符合一个用合适的参数来描述的拉普拉斯分布,在此基础上提出了一种JPEG图像重压缩概率模型来描述重压缩前后DCT系数统计特性的变化,并依据贝叶斯准则,利用后验概率表示出图像篡改中存在的双重压缩效应块和只经历单次压缩块的特征值.然后设定阈值,通过阈值进行分类判断就可以实现对篡改区域的自动检测和提取.实验结果表明,该方法能快速并准确地实现篡改区域的自动检测和提取,并且在第2次压缩因子小于第1次压缩因子时,检测结果相对于利用JPEG块效应不一致的图像篡改盲检测算法和利用JPEG图像量化表的图像篡改盲检测算法有了明显的提高.     

Multispectral landuse classification using neural networks and support vector machines: one or the other,or both?

Land use classification is an important part of many remote sensing applications. A lot of research has gone into the application of statistical and neural network classifiers to remote‐sensing images. This research involves the study and implementation of a new pattern recognition technique introduced within the framework of statistical learning theory called Support Vector Machines (SVMs), and its application to remote‐sensing image classification. Standard classifiers such as Artificial Neural Network (ANN) need a number of training samples that exponentially increase with the dimension of the input feature space. With a limited number of training samples, the classification rate thus decreases as the dimensionality increases. SVMs are independent of the dimensionality of feature space as the main idea behind this classification technique is to separate the classes with a surface that maximizes the margin between them, using boundary pixels to create the decision surface. Results from SVMs are compared with traditional Maximum Likelihood Classification (MLC) and an ANN classifier. The findings suggest that the ANN and SVM classifiers perform better than the traditional MLC. The SVM and the ANN show comparable results. However, accuracy is dependent on factors such as the number of hidden nodes (in the case of ANN) and kernel parameters (in the case of SVM). The training time taken by the SVM is several magnitudes less.     

Full band watermarking in DCT domain with Weibull model

In the framework of maximum-likelihood detection for image watermarking schemes, the conventional Generalized Gaussian Distribution (GGD), Cauchy and Student’s t distributions often fail to model the pulse-like distributions, such as Discrete Cosine Transform (DCT) coefficient distribution. Meanwhile DCT DC coefficients are often neglected in the image watermarking schemes. In this paper an improved full band image watermarking algorithm with utilization of Weibull distribution modeling the DCT AC and DC coefficients is proposed. Experiments indicate that compared with other popluar distributions such as the GGD, the Weibull model gives a closer fit on the distribution of AC coefficients in absolute domain with a smaller Kullback-Leibler (KL) divergence and lower Mean Square Error (MSE). The watermarking scheme with Weibull modeling the DCT AC coefficients (Weibull-AC) exhibits strong robustness under the attack of scaling and median filtering. The watermarking scheme with Weibull modeling the DCT DC coefficients (Weibull-DC) yields a better detection accuracy for bright and more detailed images. Combining the above two advantages, the proposed Weibull based full band watermarking in DCT domain (Weibull-FB) further improves its robustness under the attack of JPEG compression and achieves 10.47 % overall increment in the detection accuracy compared with the baseline system while maintaining good invisibility in the view of structural similarity (SSIM).     

一个新的基于DCT的自适应数字水印算法

本文提出了一个利用DCT系数的关系来进行水印嵌入和提取的算法。该算法利用人类视觉系统HVS的特点，通过巧妙调整DCT系数之间的相互关系来嵌入水印．从而使得图像在嵌入一个比较稳健的水印后的视觉失真尽可能最小。水印提取不需要原始图像。实验结果表明本算法的图像保真度较好，并对JPEG压缩、剪切等常见的图像处理方法具有较好的稳健性，并优于文献上的相关算法。     

基于DCT变换和零次学习的刑侦图像超分辨率

图像超分辨率在视频侦查领域有重要作用. 基于卷积神经网络的超分辨率算法通常在训练时输入人工合成的低分辨率图像, 学习高、低分辨率图像的映射, 很难应用于视频侦查领域. 真实低分辨率图像退化过程复杂未知, 且大都经过压缩算法的处理, 存在人工压缩痕迹, 导致超分辨率图像出现假纹理. 针对真实场景下的低分辨率图像提出一种基于离散余弦变换(DCT)和零样本学习的超分辨率算法. 该算法利用图像内部的重复相似性特点, 采用输入图像自身的子图像进行训练. 不同于以往超分辨率网络的输入, 所提算法采用子图像的离散余弦变换系数作为超分辨率网络的输入, 避免网络对输入图像的压缩痕迹进行放大, 减少假纹理. 在标准数据集和真实刑侦图像上的实验结果表明所提算法能减少图像中由压缩痕迹导致的假纹理.     

Improving the SVM gender classification accuracy using clustering and incremental learning

Gender recognition has been playing a very important role in various applications such as human–computer interaction, surveillance, and security. Nonlinear support vector machines (SVMs) were investigated for the identification of gender using the Face Recognition Technology (FERET) image face database. It was shown that SVM classifiers outperform the traditional pattern classifiers (linear, quadratic, Fisher linear discriminant, and nearest neighbour). In this context, this paper aims to improve the SVM classification accuracy in the gender classification system and propose new models for a better performance. We have evaluated different SVM learning algorithms; the SVM‐radial basis function with a 5% outlier fraction outperformed other SVM classifiers. We have examined the effectiveness of different feature selection methods. AdaBoost performs better than the other feature selection methods in selecting the most discriminating features. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, whereas method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods have increased the classification accuracy.     

基于支持向量机的人脸分类

提出了一种基于支持向量机的人脸分类方法，首先对人脸图像作二维离散余弦变换，取离散余弦变换系数作为特征，然后用支持向量机进行分类。用Essex人脸图像数据库进行性别分类，取得了很好的分类效果。