基于图匹配网络的小样本违禁物品分割算法

自动化安检技术是维护公共安全、提升安检效率的一项有效措施。在实际场景中很难获得充足的违禁品标注样本用于神经网络的训练,并且在不同场景和安全级别下违禁品的类别也有所不同。为解决基于神经网络的违禁品检测方法所面临的样本不均衡问题,以及避免模型在分割新的违禁品类别时需重新训练的现象,文中提出一种基于图匹配网络的小样本违禁物品分割算法。文中模型将测试图像与参考图像并行输入到图匹配网络中,并根据匹配结果从测试图像中分割出违禁品。所设计的图匹配模块不仅从图间节点的相似性考虑匹配问题,并利用DeepEMD算法建立全局概念,进一步提高测试图和参考图的匹配结果。在SIXray数据集和Xray-PI数据集上的实验表明:本模型在单样本分割任务中得到36.4%和51.2%的类平均交并比,分别比目前先进的单样本分割方法提高2.5%和2.3%。由此表明所设计的算法能有效提升小样本X光图像分割算法的精确度。     

二元裂解算子交替方向乘子法的核极限学习机

凸优化形式的核极限学习机(KELM)具有较高的分类准确率,但用迭代法训练凸优化核极限学习机要较传统核极限学习机的解线性方程法花费更长时间.针对此问题,该文提出一种2元裂解算子交替方向乘子法(BSADMM-KELM)来提高凸优化核极限学习机的训练速度.首先引入2元裂解算子,将求核极限学习机最优解的过程分裂为两个中间算子的优化过程,再通过中间算子的迭代计算而得到原问题的最优解.在22个UCI数据集上所提算法的训练时间较有效集法平均快29倍,较内点法平均快4倍,分类精度亦优于传统的核极限学习机;在大规模数据集上该文算法的训练时间优于传统核极限学习机.     

基于自组织增量-图卷积神经网络的金相图半监督学习

采用深度学习对钢铁材料显微组织图像分类,需要大量带标注信息的训练集.针对训练集人工标注效率低下问题,该文提出一种新的融合自组织增量神经网络和图卷积神经网络的半监督学习方法.首先,采用迁移学习获取图像数据样本的特征向量集合;其次,通过引入连接权重策略的自组织增量神经网络(WSOINN)对特征数据进行学习,获得其拓扑图结构,并引入胜利次数进行少量人工节点标注;然后,搭建图卷积网络(GCN)挖掘图中节点的潜在联系,利用Dropout手段提高网络的泛化能力,对剩余节点进行自动标注进而获得所有金相图的分类结果.针对从某国家重点实验室收集到的金相图数据,比较了在不同人工标注比例下的自动分类精度,结果表明:在图片标注量仅为传统模型12％时,新模型的分类准确度可达到91％.     

基于深度学习的地址信息自动标注研究

文本序列的自动标注能够解决深度学习普遍面临的人工标注成本过高的问题.本文针对地址信息的实体表述特征,构建基于实体边界矩阵（Entity Boundary Matrix,EBM）的表示模型,在此基础上提出了一种基于深度学习和KNN标签修正算法（K-Nearest Neighbours Correction Algorithm,KNN-CA）的不需要任何人工标注训练集的自动标注算法.首先获取预置小区数据集并构建离线特征库和初始化在线特征库;接着通过匹配算法求解EBM并利用KNN-CA进行优化,再通过数据增广得到自动标注的训练集;然后训练BiLSTM-CRF深度学习模型并预测所有未曾标注的地址信息的序列标注;最后再次利用KNN-CA优化可求解EBM的序列标注,由此构建适用于中文地理命名实体（Chinese Geospatial Named Entities,CGSNE）识别及相关研究的序列标注语料库.实验表明,标注数据的F1值达到了95.35%.     

基于GA-KELM的复杂路面病害分割算法

针对大多数路面裂缝检测算法对坑洼、松散和车辙等复杂病害分割效果一般,适应较差的问题。提出了一种基于训练样本自动选取与改进的核极限学习机相结合的检测方法。首先使用二维Otsu选取训练样本并提取LBP特征和HOG特征。然后采用遗传算法对核极限学习机中随机给定的输入权值和隐含层偏差进行优化。将降维后得到的特征向量作为特征属性对改进的核极限学习机进行训练。最后用训练好的分类器对路面病害进行检测。经实验证明,该算法与对比实验相比分割精度提高了24.8%,运行时间为4.31s 是一种鲁棒性较强的检测方法。     

二元裂解算子交替方向乘子法的核极限学习机

凸优化形式的核极限学习机(KELM)具有较高的分类准确率,但用迭代法训练凸优化核极限学习机要较传统核极限学习机的解线性方程法花费更长时间。针对此问题,该文提出一种2元裂解算子交替方向乘子法(BSADMM-KELM)来提高凸优化核极限学习机的训练速度。首先引入2元裂解算子,将求核极限学习机最优解的过程分裂为两个中间算子的优化过程,再通过中间算子的迭代计算而得到原问题的最优解。在22个UCI数据集上所提算法的训练时间较有效集法平均快29倍,较内点法平均快4倍,分类精度亦优于传统的核极限学习机;在大规模数据集上该文算法的训练时间优于传统核极限学习机。     

基于自组织增量-图卷积神经网络的金相图半监督学习

采用深度学习对钢铁材料显微组织图像分类,需要大量带标注信息的训练集。针对训练集人工标注效率低下问题,该文提出一种新的融合自组织增量神经网络和图卷积神经网络的半监督学习方法。首先,采用迁移学习获取图像数据样本的特征向量集合;其次,通过引入连接权重策略的自组织增量神经网络(WSOINN)对特征数据进行学习,获得其拓扑图结构,并引入胜利次数进行少量人工节点标注;然后,搭建图卷积网络(GCN)挖掘图中节点的潜在联系,利用Dropout手段提高网络的泛化能力,对剩余节点进行自动标注进而获得所有金相图的分类结果。针对从某国家重点实验室收集到的金相图数据,比较了在不同人工标注比例下的自动分类精度,结果表明:在图片标注量仅为传统模型12%时,新模型的分类准确度可达到91%。     

一种基于正则优化的批次继承极限学习机算法

极限学习机(ELM)作为一种新型神经网络,具有极快的训练速度和良好的泛化性能。针对极限学习机在处理高维数据时计算复杂度高,内存需求巨大的问题,该文提出一种批次继承极限学习机(B-ELM)算法。首先将数据集均分为不同批次,采用自动编码器网络对各批次数据进行降维处理;其次引入继承因子,建立相邻批次之间的关系,同时结合正则化框架构建拉格朗日优化函数,实现批次极限学习机数学建模;最后利用MNIST, NORB和CIFAR-10数据集进行测试实验。实验结果表明,所提算法具有较高的分类精度,并且有效降低了计算复杂度和内存消耗。     

网格梯度曲率模型零度Metropolis-Hastings遥感图像缺失重建

针对矩形网格遥感图像可微随机域数据缺失重建过程中,存在重建效果不佳且计算效率不高的问题,提出一种网格化全局几何约束零度Metropolis-Hastings遥感图像缺失数据随机重建算法.首先,构建遥感图像的随机梯度-曲率重建模型,通过全局几何约束相互作用随机场模型,匹配整个网格样本的梯度和曲率,从而满足蒙特卡罗模拟应用条件;其次,采用蒙特卡罗算法改进版本零度Metropolis-Hastings算法,实现遥感图像缺失数据重建,该方式不承担对底层数据的概率分布参数描述,有助于降低用户参与度,提高计算效率,适用大型遥感图像数据集的无监督自动处理;最后,通过与其他分类或插值方法实验对比显示,所提算法在数据重建效果和计算效率上均要优于对比算法.     

K插值单纯形法核极限学习机的研究

针对核极限学习机高斯核函数参数选优难,影响学习机训练收敛速度和分类精度的问题,该文提出一种K插值单纯形法的核极限学习机算法。把核极限学习机的训练看作一个无约束优化问题,在训练迭代过程中,用Nelder-Mead单纯形法搜索高斯核函数的最优核参数,提高所提算法的分类精度。引入K插值为Nelder-Mead单纯形法提供合适的初值,减少单纯形法的迭代次数,提高了新算法的训练收敛效率。通过在UCI数据集上的仿真实验并与其它算法比较,新算法具有更快的收敛速度和更高的分类精度。     

基于视觉与标注相关信息的图像聚类算法

算法首先按视觉相关程度对标注字进行打分,标注字的分值体现了语义一致图像的视觉连贯程度.利用图像语义类别固有的语言描述性,从图像标注中抽取具有明显视觉连贯性的标注字作为图像的语义类别,减少了数据库设计者繁琐的手工编目工作.按标注字信息对图像进行语义分类,提高了图像聚类的语义一致性.对4500幅Corel标注图像的聚类结果证实了算法的有效性.     

Automatic Image Annotation Based on Generalized Relevance Models

This paper presents a generalized relevance model for automatic image annotation through learning the correlations between images and annotation keywords. Different from previous relevance models that can only propagate keywords from the training images to the test ones, the proposed model can perform extra keyword propagation among the test images. We also give a convergence analysis of the iterative algorithm inspired by the proposed model. Moreover, to estimate the joint probability of observing an image with possible annotation keywords, we define the inter-image relations through proposing a new spatial Markov kernel based on 2D Markov models. The main advantage of our spatial Markov kernel is that the intra-image context can be exploited for automatic image annotation, which is different from the traditional bag-of-words methods. Experiments on two standard image databases demonstrate that the proposed model outperforms the state-of-the-art annotation models.     

Fusing semantic aspects for image annotation and retrieval

In this paper, we present an approach based on probabilistic latent semantic analysis (PLSA) to achieve the task of automatic image annotation and retrieval. In order to model training data precisely, each image is represented as a bag of visual words. Then a probabilistic framework is designed to capture semantic aspects from visual and textual modalities, respectively. Furthermore, an adaptive asymmetric learning algorithm is proposed to fuse these aspects. For each image document, the aspect distributions of different modalities are fused by multiplying different weights, which are determined by the visual representations of images. Consequently, the probabilistic framework can predict semantic annotation precisely for unseen images because it associates visual and textual modalities properly. We compare our approach with several state-of-the-art approaches on a standard Corel dataset. The experimental results show that our approach performs more effectively and accurately.     

基于改进的有效区域基因选择与跨模态语义挖掘的图像属性标注

图像属性标注是一种更细化的图像标注，它能缩小认知与特征间"语义鸿沟".现有研究多基于单特征且未挖掘属性蕴含的深层语义，故无法准确刻画图像内容.改进有效区域基因选择算法融合图像特征，并设计迁移学习策略，实现材质属性标注；基于判别相关分析挖掘特征间跨模态语义，以改进相对属性模型，标注材质属性蕴含的深层语义-实用属性.实验表明：材质属性标注精准度达63.11%，较最强基线提升1.97%；实用属性标注精准度达59.15%，较最强基线提升2.85%；层次化的标注结果能全面刻画图像内容.     

基于集成分类的暴恐图像自动标注方法

为减少暴恐图像对社会发展和青少年成长造成的不利影响，本文提出一种基于集成分类的暴恐图像自动标注方法，辅助筛除网页中的暴恐信息。该方法将暴恐图像的标注视作多标签分类问题，利用迁移学习训练多个子网络，然后通过集成学习对子网络的输出进行融合，同时在融合过程中针对各个标签在不同网络上的准确率进行权重分配，最后经过一系列矩阵运算得到图像的标注结果。实验结果表明，与传统机器学习算法相比，本文方法在准确率和召回率上都有较大提升，并改善了样本不均衡所造成的不同标签类别上模型标注精确度差异较大的问题。     

基于部件的自动目标检测方法研究

该文提出了一种新的自动目标检测算法,实现对自然场景图像及高分辨率遥感图像中结构相对复杂的人造目标的自动检测。该方法基于组成物体的几何部件处理问题,降低了对训练样本数量的需求。首先选择两类典型特征,基于机器学习训练对应的分类器,有效地减少了背景中某些物体与前景目标部分特性相似对检测方法准确率的影响;然后利用标值点过程对问题建模,以对目标分布的先验约束和分类器的响应作为数据能量,自顶向下地自动检测目标。实验结果表明,该方法准确率高、鲁棒性好,具有较强的实际应用价值。     

A Multi-Directional Search technique for image annotation propagation

Image annotation has attracted lots of attention due to its importance in image understanding and search areas. In this paper, we propose a novel Multi-Directional Search framework for semi-automatic annotation propagation. In this system, the user interacts with the system to provide example images and the corresponding annotations during the annotation propagation process. In each iteration, the example images are clustered and the corresponding annotations are propagated separately to each cluster: images in the local neighborhood are annotated. Furthermore, some of those images are returned to the user for further annotation. As the user marks more images, the annotation process goes into multiple directions in the feature space. The query movements can be treated as multiple path navigation. Each path could be further split based on the user’s input. In this manner, the system provides accurate annotation assistance to the user - images with the same semantic meaning but different visual characteristics can be handled effectively. From comprehensive experiments on Corel and U. of Washington image databases, the proposed technique shows accuracy and efficiency on annotating image databases.     

An Automatic Image Registration for Applications in Remote Sensing

This paper deals with a major problem encountered in the area of remote sensing consisting of the registration of multitemporal and/or multisensor images. In general, such images have different gray-level characteristics, and simple techniques such as those based on correlation cannot be applied directly. In this work, a new automatic satellite image registration approach is proposed. This technique exploits the invariant relations between regions of a reference and a sensed image, respectively. It involves an edge-based selection of the most distinctive control points (CPs) in the reference image. The search for the corresponding CPs in the sensed image is based on local similarity detection by means of template matching according to a combined invariants-based similarity measure. The final warping of the images according to the selected CPs is performed by using the thin-plate spline interpolation. The procedure is fully automatic and computationally efficient. The proposed algorithm for this technique has been successfully applied to register multitemporal SPOT and synthetic aperture radar images from urban and agricultural areas. The experimental results demonstrate the robustness, efficiency and accuracy of the algorithm.     

Automatic image orientation detection

We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified MDL criterion) extracted from a learning vector quantizer (LVQ) can be used to estimate the class-conditional densities of the observed features needed for the Bayesian methodology. We further show how principal component analysis (PCA) and linear discriminant analysis (LDA) can be used as a feature extraction mechanism to remove redundancies in the high-dimensional feature vectors used for classification. The proposed method is compared with four different commonly used classifiers, namely k-nearest neighbor, support vector machine (SVM), a mixture of Gaussians, and hierarchical discriminating regression (HDR) tree. Experiments on a database of 16 344 images have shown that our proposed algorithm achieves an accuracy of approximately 98% on the training set and over 97% on an independent test set. A slight improvement in classification accuracy is achieved by employing classifier combination techniques.