基于空间关系一致性的图像自动配准方法

提出了一种基于空间关系一致性的图像自动配准方法,处理具有全局仿射变换的图像配准问题.首先利用Mcan-shift算法和区域标记算法从参考图像和待配准图像中提取区域特征作为配准基元;然后采用高斯函数平滑后的区域特征重心点坐标之间的欧式距离描述匹配特征的空间关系一致性,从而定义一个以匹配矩阵为自变量的空间关系一致性度量函数,使它在两幅图像的最佳配准位置达到最大值,将图像配准问题转化为一个最优化问题;最后利用一个局部选代优化算法求解.高斯函数的方差是度量函数中惟一的预设参数,但它对优化求解的结果基本没有影响,在实际中容易设定,保证了方法的自动性、稳健性和适应性.实际图像的实验结果表明本文方法能有效解决具有全局仿射变换的图像配准问题.     

基于偏最小二乘分析的双模粒子滤波目标跟踪

针对在复杂背景下,基于主成分分析(PCA)的目标跟踪方法准确率较低的问题,使用偏最小二乘分析,提出一种双模粒子滤波的跟踪算法.首先采用偏最小二乘分析对目标区域建模,作为观测模型;然后利用仿射变换描述目标的形变过程,分别在李群及其切向量空间上建立双模的动态模型;最后结合特征空间更新策略,使用粒子滤波实现目标跟踪.实验表明,所提出的算法能够有效滤除背景噪声,跟踪结果稳定且准确.     

面向3D网格模型的多重数字水印算法

为了解决单盲水印网格算法难以抵抗多种攻击的问题,提出一种鲁棒的3D网格模型的多重数字水印算法.该算法分别对3D网格模型的顶点信息和拓扑信息嵌入2种不同类型的单鲁棒性水印,从而使模型既能抵抗大面积的剪切攻击,又能抗击一定强度的噪声攻击;且在水印提取时不需要原始模型信息.实验结果表明,该算法能有效地提高水印抗平移、旋转、缩放、非均匀缩放、剪切、噪声和顶点乱序等攻击的能力.     

一种新的基于最大边缘准则的监督流形学习方法

在深入研究局部样条嵌入算法(LSE)的基础上,引入明确的线性映射关系,构建平移缩放模型和正交化特征子空间,提出了一种正交局部样条判别投影算法(O-LSDP),有效解决了原始LSE算法存在的两个主要问题:样本外点学习问题和无监督模式学习问题。该算法能够应用于模式分类问题并显著改善算法的分类识别能力。在标准人脸数据库上进行的实验比较分析验证了该算法的有效性与可行性。     

面向自动扫描的三维形状多层次局部匹配算法

为了让机器人在对未知场景的扫描与重建过程中同时获得对该场景的理解,需要基于目前已有的部分信息进行物体分割与识别,解决基于不完整点云的局部匹配问题.针对已有的局部匹配方法面临着匹配准确度低、计算复杂度高等问题,提出三维形状的多层次局部匹配算法.在粗层次上,通过使用改进的词袋方法进行降维加速;在细层次上,通过精细地筛选三维特征点对之间的对应关系提升精度.首先使用基于深度学习描述子的多尺度SVM方法对数据库中模型上的特征点进行聚类,然后采用基于空间关系的视觉词袋方法在数据库中检索候选模型,最后基于全局和局部等距性对不完整点云与候选模型间的特征点对对应关系进行筛选.文中对于各部分算法分别进行验证,并与相关算法进行对比和评估,实验结果表明,该算法显著提高了局部匹配的准确性,为机器人在线场景扫描、分析、重建等相关工作提供了十分有意义的参考和支持.     

一种新的基于MMC和LSE的监督流形学习算法

针对局部样条嵌入算法 （Local spline embedding,LSE） 存在样本外点学习和无监督模式学习问题,本文提出了一种新颖的正交局部样条判别投影算法 （O-LSDP）.该算法通过引入明确的线性映射关系,构建平移缩放模型,以及正交化特征子空间,从而使该算法能够应用于模式分类问题并显著改善了算法的分类识别能力.在标准人 脸数据库和植物叶片数据库上的实验结果验证了该算法的有效性与可行性.     

基于三维网格模型的双重数字盲水印算法

为提高一重三维模型数字水印的安全性,提出一种基于三维网格模型的双重数字盲水印算法。通过改变三角网格顶点在其一环相邻顶点所确定的局部几何空间中的位置和三角面片顶点排列顺序,嵌入双重水印,使模型能抵抗严重的剪切攻击及一定程度的噪声攻击。算法在提取水印时无需原始模型。仿真结果表明,该算法能够有效抵抗平移、旋转、均匀缩放、顶点乱序、多边形乱序及剪切等攻击,具有嵌入可读水印的不可见性。     

一种快速模板匹配目标识别算法

该文拟将计算机视觉中传统模板匹配方法与对场景物体的中心矩描述方法相结合,提出了一种效率较高的匹配算法。算法在匹配识别上不仅不受物体方位旋转及尺寸缩放变化影响,而且能较精确地求出物体相对于模板的缩放比例和偏转角度。文中给出了与传统模板匹配算法对照的实验结果。     

一种基于仿射变换模型的目标跟踪算法

在图像目标跟踪的应用中,传统方法多采用基于平移运动模型和相关（correlation）类型匹配准则的跟踪算法。该类算法以目标仅发生平移运动为假设前提,难以有效适应目标在图像中通常会发生的缩放、旋转和错切等变化。本文应用了一种基于仿射变换模型的目标跟踪算法。该算法建立起包含六个参数的仿射变换模型,以其描述目标在序列图像中的变化,然后构造适当的匹配误差目标函数,并采用牛顿迭代法求解得到最优的仿射参数。实验结果表明,该算法具有较强的鲁棒性,能够得到较好的跟踪效果。     

用于图像分割的局部区域一致性流形约束MRF模型

针对区域马尔可夫随机场(MRF)模型难以有效描述图像复杂先验知识的问题,提出一种基于局部区域一致性流形约束MRF(LRCMC-MRF)模型.首先,所提模型利用高维数据的低维流形分布表征图像局部区域的复杂几何结构先验,建立图像局部区域的流形先验约束;其次,基于Pairwise MRF模型,建立一种包含更多图像局部信息的局部空间自适应MRF模型;最后,基于贝叶斯理论,将复杂局部区域几何结构先验和局部空间自适应统计特征融合,利用Gibbs采样算法对所提出模型进行优化.实验结果表明,与基于常规区域的MRF模型相比,所提出的分割算法具有较好的分割效果.     

三角形约束下的词袋模型图像分类方法

视觉词袋模型广泛地应用于图像分类与图像检索等领域.在传统词袋模型中,视觉单词统计方法忽略了视觉词之间的空间信息以及分类对象形状信息,导致图像特征表示区分能力不足.本文提出了一种改进的视觉词袋方法,结合显著区域提取和视觉单词拓扑结构,不仅能够产生更具代表性的视觉单词,而且能够在一定程度上避免复杂背景信息和位置变化带来的干扰.首先,通过对训练图像进行显著区域提取,在得到的显著区域上构建视觉词袋模型.其次,为了更精确的描述图像的特征,抵抗多变的位置和背景信息的影响,该方法采用视觉单词拓扑结构策略和三角剖分方法,融入全局信息和局部信息.通过仿真实验,并与传统的词袋模型及其他模型进行比较,结果表明本文提出的方法获得了更高的分类准确率.     

Enriched Latent Dirichlet Allocation for Sentiment Analysis

One of the main benefits of unsupervised learning is that there is no need for labelled data. As a method of this category, latent Dirichlet allocation (LDA) estimates the semantic relations between the words of the text effectively and can play an important role in solving various issues, including emotional analysis in combination with other parameters. In this study, three novel topic models called date sentiment LDA (DSLDA), author–date sentiment LDA (ADSLDA), and pack–author–date sentiment LDA (PADSLDA) are proposed. The proposed models extend LDA through some extra parameters such as date, author, helpfulness, sentiment, and subtopic. The proposed models use helpfulness in the Gibbs sampling algorithm. Helpfulness is a part of readers who found the review helpful. The proposed models divide the words into two categories: the words more affected by the distribution of subtopic and the words more affected by the main topic. In this study, a new concept called pack is introduced, and a new model called PADSLDA is proposed for sentiment analysis at pack level. The proposed models outperformed the baseline models because according to evaluations results, the extra parameters can appropriately affect the generating process of words in a review. Sentiment analysis at the document level, perplexity, and topic coherence are the main parameters used in the evaluations.     

一种图像局部特征的语义提取方法

本文提出了一种基于期望最大化(EM)算法的局部图像特征的语义提取方法。首先提取图像的局部图像特征,统计特征在视觉词汇本中的出现频率,将图像表示成词袋模型;引入文本分析中的潜在语义分析技术建立从低层图像特征到高层图像语义之间的映射模型;然后利用EM算法拟合概率模型,得到图像局部特征的潜在语义概率分布;最后利用该模型提取出的图像在潜在语义上的分布来进行图像分析和理解。与其他基于语义的图像理解方法相比,本文方法不需要手工标注,以无监督的方式直接从图像低层特征中发掘图像的局部潜在语义,既求得了局部语义信息,又获得了局部语义的空间分布特性,因而能更好地对场景建模。为验证本文算法获取语义的有效性,在15类场景图像上进行了实验,实验结果表明,该方法取得了良好的分类准确率。     

A co-boost framework for learning object categories from Google Images with 1st and 2nd order features

Conventional object recognition techniques rely heavily on manually annotated image datasets to achieve good performances. However, collecting high quality datasets is really laborious. The image search engines such as Google Images seem to provide quantities of object images. Unfortunately, a large portion of the search images are irrelevant. In this paper, we propose a semi-supervised framework for learning visual categories from Google Images. We exploit a co-training algorithm, the CoBoost algorithm, and integrate it with two kinds of features, the 1st and 2nd order features, which define bag of words representation and spatial relationship between local features, respectively. We create two boosting classifiers based on the 1st and 2nd order features in the training, during which one classifier provides labels for the other. The 2nd order features are generated dynamically rather than extracted exhaustively to avoid high computation. An active learning technique is also introduced to further improve the performance. Experimental results show that the object models learned from Google Images by our method are competitive with the state-of-the-art unsupervised approaches and some supervised techniques on the standard benchmark datasets.     

Visual information fusion for object-based video image segmentation using unsupervised Bayesian online learning

An algorithm using the unsupervised Bayesian online learning process is proposed for the segmentation of object-based video images. The video image segmentation is solved using a classification method. First, different visual features (the spatial location, colour and optical-flow vectors) are fused in a probability framework for image pixel clustering. The appropriate modelling of the probability distribution function (PDF) for each feature-cluster is obtained through a Gaussian distribution. The image pixel is then assigned a cluster number in a maximum a posteriori probability framework. Different from the previous segmentation methods, the unsupervised Bayesian online learning algorithm has been developed to understand a cluster's PDF parameters through the image sequence. This online learning process uses the pixels of the previous clustered image and information from the feature-cluster to update the PDF parameters for segmentation of the current image. The unsupervised Bayesian online learning algorithm has shown satisfactory experimental results on different video sequences.     

基于判别特征加权的GPLVM算法

高斯过程隐变量模型是最近提出的比较流行的无监督降维方法.但是,它是一种无监督的机器学习算法,没有突出类结构,使得结果不能有效地表示类别信息.因此,提出一种利用判别特征值对高斯过程隐变量模型进行加权的算法,该算法不仅能够加强模型在低维流形上的判别性,而且能很好地保持类内的流形结构.     

3D卷积自编码器高光谱图像分类模型

目的 高光谱图像分类是遥感领域的基础问题，高光谱图像同时包含丰富的光谱信息和空间信息，传统模型难以充分利用两种信息之间的关联性，而以卷积神经网络为主的有监督深度学习模型需要大量标注数据，但标注数据难度大且成本高。针对现有模型的不足，本文提出了一种无监督范式下的高光谱图像空谱融合方法，建立了3D卷积自编码器（3D convolutional auto-encoder，3D-CAE）高光谱图像分类模型。方法 3D卷积自编码器由编码器、解码器和分类器构成。将高光谱数据预处理后，输入到编码器中进行无监督特征提取，得到一组特征图。编码器的网络结构为3个卷积块构成的3D卷积神经网络，卷积块中加入批归一化技术防止过拟合。解码器为逆向的编码器，将提取到的特征图重构为原始数据，用均方误差函数作为损失函数判断重构误差并使用Adam算法进行参数优化。分类器由3层全连接层组成，用于判别编码器提取到的特征。以3D-CNN （three dimensional convolutional neural network）为自编码器的主干网络可以充分利用高光谱图像的空间信息和光谱信息，做到空谱融合。以端到端的方式对模型进行训练可以省去复杂的特征工程和数据预处理，模型的鲁棒性和稳定性更强。结果 在Indian Pines、Salinas、Pavia University和Botswana等4个数据集上与7种传统单特征方法及深度学习方法进行了比较，本文方法均取得最优结果，总体分类精度分别为0.948 7、0.986 6、0.986 2和0.964 9。对比实验结果表明了空谱融合和无监督学习对于高光谱遥感图像分类的有效性。结论 本文模型充分利用了高光谱图像的光谱特征和空间特征，可以做到无监督特征提取，无需大量标注数据的同时分类精度高，是一种有效的高光谱图像分类方法。     

A Neural Basis Computational Model of Emotional Brain for Online Visual Object Recognition

In this study, we propose a novel visual object recognizer inspired by the human brain’s emotional learning. In the proposed computational model, the visual information is transferred through the ventral visual pathway to the amygdala, which is responsible for emotional visual stimuli. In the model, the orbitofrontal cortex (OFC) evaluates the amygdala response and tries to prevent inappropriate answers. The proposed visual recognizer is based on threshold logic units defined on the neural models of the amygdala and the OFC. According to the experimental results, the presented model learns the visual patterns quickly and shows higher performance than the brain emotional learning-based pattern recognizer (BRLPR) and multilayer perceptron (MLP) with Levenberg–Marquardt backpropagation (BPG) learning algorithm, in which the adaptive neurofuzzy inference system (ANFIS) cannot be trained because of the curse of dimensionality. The main features of the proposed model are the lower time and spatial complexity. Hence, it can be utilized in real-time visual object recognition.     

Scene classification based on a hierarchical convolutional sparse auto-encoder for high spatial resolution imagery

Efficiently representing and recognizing the semantic classes of the subregions of large-scale high spatial resolution (HSR) remote-sensing images are challenging and critical problems. Most of the existing scene classification methods concentrate on the feature coding approach with handcrafted low-level features or the low-level unsupervised feature learning approaches, which essentially prevent them from better recognizing the semantic categories of the scene due to their limited mid-level feature representation ability. In this article, to overcome the inadequate mid-level representation, a patch-based spatial-spectral hierarchical convolutional sparse auto-encoder (HCSAE) algorithm, based on deep learning, is proposed for HSR remote-sensing imagery scene classification. The HCSAE framework uses an unsupervised hierarchical network based on a sparse auto-encoder (SAE) model. In contrast to the single-level SAE, the HCSAE framework utilizes the significant features from the single-level algorithm in a feedforward and full connection approach to the maximum extent, which adequately represents the scene semantics in the high level of the HCSAE. To ensure robust feature learning and extraction during the SAE feature extraction procedure, a ‘dropout’ strategy is also introduced. The experimental results using the UC Merced data set with 21 classes and a Google Earth data set with 12 classes demonstrate that the proposed HCSAE framework can provide better accuracy than the traditional scene classification methods and the single-level convolutional sparse auto-encoder (CSAE) algorithm.