基于线条方向直方图的图像情感语义分类

图像语义分类在基于语义的图像检索中具有重要意义,但是图像的情感语义描述和分类方面的研究在近年来才刚刚起步。该文利用图像的低层特征实现了图像高层情感语义(“静感”和“动感”)的分类。图像的线条与情感之间存在明显的联系,选用线条方向直方图作为图像特征,利用概率神经网络(PNN)完成语义分类,实验表明该方法具有较好的效果。     

基于神经网络生成图像语义的算法研究

提出一种利用神经网络获取图像语义的算法。通过构建一个RBF神经网络,在图像的颜色、纹理、形状等低层视觉特征和高层语义特征之间建立映射关系。利用遗传算法训练RBF网络,获得RBF网络的隐节点个数、中心、宽度和连接权值等参数值,训练成功后的神经网络能够自动获取图像的语义。实验结果表明,该算法具有较好的基于语义的检索效果,体现了人对图像内容的理解,符合人的思维习惯。     

基于免疫规划的神经网络规则抽取算法

建立图像视觉特征和情感语义的映射关系是人工智能方向的研究热点。从神经网络的功能性观点出发,提出了一种基于免疫规划的图像情感的规则抽取算法。在对已标注情感的中国情绪图片库(CAPS)中图像颜色特征进行量化的基础上,算法将训练好的神经网络的隐层神经元输出值进行聚类,缩小搜索空间,抽取出精度高,可理解性好的符号规则,完成了图像低阶特征到高阶情感的映射。实验结果表明该方法的实用性和可行性。     

基于模糊熵的空间语义图像检索模型研究*

根据模糊熵理论和改进的空间信息分布,提出了颜色空间特征语义图像检索模型。阐述基于语法规则的颜色空间特征语义描述方法,构造从低层颜色空间特征到高层语义之间的映射,根据这些模糊语义值进行图像检索。实验结果表明,该模型能够有效地对图像高层语义进行刻画,由此实现的模型不仅能获得高效和稳定的检索结果,获得与人类视觉感知较好的一致性,该算法还能很好地消除低层图像空间特征和高层语义之间的语义鸿沟。     

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。     

基于MPEG-7和MM混合模型的图像自动标注算法

为了弥补图像低层视觉特征和高层语义之间的"语义鸿沟",改善图像自动标注的性能,提出了基于多媒体描述接口(MPEG-7)和MM(Mixture Model)混合模型的图像标注算法。该算法采用MPEG-7标准推荐的颜色和纹理描述子提取图像的低层视觉特征,通过MM混合模型建立低层特征到高层语义空间的映射,实现了基于图像整体低层特征的多标签图像自动标注。通过在corel图像数据集上的一系列实验测试验证了该方法的可行性和有效性。     

基于本体的图像情感语义识别研究

抽取图像颜色、形状、纹理特征,通过本体映射,建立本体表示的图像情感特征库。以中国情感图片系统作为训练样本,挖掘图像特征与情感之间的关联关系,并通过语义网规则语言SWRL（Semantic Web Rule Language）表示关联规则,建立情感映射规则库。情感推理引擎使用情感映射规则对图像特征进行推理,达到识别图像情感语义的目的。     

基于卷积神经网络的遥感图像水体提取

为解决基于遥感图像监测地表水资源变化的问题,在深度学习的框架下,基于卷积神经网络(CNN)提出了用于遥感图像水体提取的模型.利用网络爬虫的方式,搜集遥感图像,并通过随机裁剪、数据清洗等方式构建训练、验证和测试数据集.通过对低层语义特征学习提取抽象的高层特征,基于提取的高层特征进行网络模型训练.实验结果表明:水体提取的精...     

基于改进的OCC情感模型的自然风景图像分类研究

网络技术的发展和图像获取设备的普及导致数字图像迅速增长,依靠先进的技术提取图像蕴含的情感语义实现图像情感语义分类正是当前各行业急需解决的问题。为此提出一种基于改进的OCC情感模型的自然风景图像情感语义分类方法。通过融入性格、心情因素描述图像的个性情感,使用BP神经网络实现,解决图像分类中的语义理解问题。使用百度图片频道上下载的600张场景图像进行训练和测试,实验通过与人工计算结果相比较,取得了良好的分类效果,可为更多类型的图像情感语义分类打好基础,具有一定的实用价值。     

一种新颖的低层视觉特征到高层语义的映射方法*

通过在低层视觉特征上提取图像的局部颜色和纹理特征,再利用模糊神经网络建立低层视觉特征和高层语义特征之间的映射,实现了图像属性信息的有效传递和可靠检索.最后,为了提高检索效率,把相关反馈引进到图像检索系统中.实验证明,该方法取得了较好的检索查全率和准确率.     

基于Bi-LSTM的财金文本情感分类研究

针对现有文本情感分析方法准确率不高、实时性不强以及特征提取不充分的问题,构建了双向长短时记忆神经网络(Bi-LSTM)模型。利用双向循环长短时记忆神经网络(Bi-LSTM)提取文本的上下文信息;然后,对已提取的上下文特征利用LSTM进行局部语义特征提取;最后,采用语法规则,构建情感分类器。通过与RNN、Bi-LSTM等单一模型对比。实验结果表明,多层LSTM结构相比传统RNN(循环神经网络)的ROUGE(语义恢复度)值更高,具有较好的学习能力。     

基于卷积神经网络的语义分割算法研究

针对语义分割中残差网络并不能完好地提取图像信息和分割效果差的问题,提出一种联合特征金字塔模型(JFP)用来融合残差网络的输出特征,并结合暗黑空间金字塔池化模型(ASPP)进一步提取特征。在解码部分应用简单的解码结构,恢复图像尺寸完成语义分割;同时引入注意力模型作为辅助语义分割网络,辅助神经网络进行训练。该方法分别在Pascal VOC 2012数据集和增强的Pascal VOC 2012数据集上对网络进行训练,并在Pascal VOC 2012的验证集上进行测试,其平均交并集之比(mIoU)分别达到了78.55%和80.14%,表明该方法具有良好的语义分割性能。     

中国古代小说图像的语义获取方法

针对中国古代小说图像的特性,提出了一种利用人工神经网络获取图像语义的方法。利用人工神经网络在图像的纹理、形状等低层视觉特征和高层语义特征间建立映射关系,利用改进的遗传算法确定人工神经网络的参数和权值,利用训练后的人工神经网络获取图像的语义。实验结果表明,所提出的方法具有理想的图像语义获取效果,能充分反映人对图像内容的理解,具有很好的应用价值。     

FERNN: An Algorithm for Fast Extraction of Rules from Neural Networks

Before symbolic rules are extracted from a trained neural network, the network is usually pruned so as to obtain more concise rules. Typical pruning algorithms require retraining the network which incurs additional cost. This paper presents FERNN, a fast method for extracting rules from trained neural networks without network retraining. Given a fully connected trained feedforward network with a single hidden layer, FERNN first identifies the relevant hidden units by computing their information gains. For each relevant hidden unit, its activation values is divided into two subintervals such that the information gain is maximized. FERNN finds the set of relevant network connections from the input units to this hidden unit by checking the magnitudes of their weights. The connections with large weights are identified as relevant. Finally, FERNN generates rules that distinguish the two subintervals of the hidden activation values in terms of the network inputs. Experimental results show that the size and the predictive accuracy of the tree generated are comparable to those extracted by another method which prunes and retrains the network.     

残差密集空间金字塔网络的城市遥感图像分割

目的 遥感图像语义分割是根据土地覆盖类型对图像中每个像素进行分类,是遥感图像处理领域的一个重要研究方向。由于遥感图像包含的地物尺度差别大、地物边界复杂等原因,准确提取遥感图像特征具有一定难度,使得精确分割遥感图像比较困难。卷积神经网络因其自主分层提取图像特征的特点逐步成为图像处理领域的主流算法,本文将基于残差密集空间金字塔的卷积神经网络应用于城市地区遥感图像分割,以提升高分辨率城市地区遥感影像语义分割的精度。方法 模型将带孔卷积引入残差网络,代替网络中的下采样操作,在扩大特征图感受野的同时能够保持特征图尺寸不变;模型基于密集连接机制级联空间金字塔结构各分支,每个分支的输出都有更加密集的感受野信息;模型利用跳线连接跨层融合网络特征,结合网络中的高层语义特征和低层纹理特征恢复空间信息。结果 基于ISPRS （International Society for Photogrammetry and Remote Sensing） Vaihingen地区遥感数据集展开充分的实验研究,实验结果表明,本文模型在6种不同的地物分类上的平均交并比和平均F₁值分别达到69.88%和81.39%,性能在数学指标和视觉效果上均优于SegNet、pix2pix、Res-shuffling-Net以及SDFCN （symmetrical dense-shortcut fully convolutional network）算法。结论 将密集连接改进空间金字塔池化网络应用于高分辨率遥感图像语义分割,该模型利用了遥感图像不同尺度下的特征、高层语义信息和低层纹理信息,有效提升了城市地区遥感图像分割精度。     

Learning Pseudo Metric for Intelligent Multimedia Data Classification and Retrieval

While people compare images using semantic concepts, computers compare images using low-level visual features that sometimes have little to do with these semantics. To reduce the gap between the high-level semantics of visual objects and the low-level features extracted from them, in this paper we develop a framework of learning pseudo metrics (LPM) using neural networks for semantic image classification and retrieval. Performance analysis and comparative studies, by experimenting on an image database, show that the LPM has potential application to multimedia information processing.     

基于图神经网络和语义知识的自然语言推理任务研究

自然语言推理任务的目的是推断两个句子之间的语义逻辑关系.该文通过模仿人类的推理过程构造模型,首先利用长短时记忆网络提取词的语境特征,模仿人类粗读句子的过程;然后依据外部语义知识,连接两个句子中有语义联系的词,构造一个以词为节点的语义图;接下来模仿人类比较两个句子的语义角色相似性的思维,用图卷积或图注意力神经网络聚合词在...     

An effective technique for the content based image retrieval to reduce the semantic gap based on an optimal classifier technique

Content Based Image Retrieval (CBIR) systems use Relevance Feedback (RF) in order to improve the retrieval accuracy. Research focus has been shifted from designing sophisticated low-level feature extraction algorithms to reducing the “semantic gap” between the visual features and the richness of human semantics. In this paper, a novel system is proposed to enhance the gain of long-term relevance feedback. In the proposed system, the general CBIR involves two steps—ABC based training and image retrieval. First, the images other than the query image are pre-processed using median filter and gray scale transformation for removal of noise and resizing. Secondly, the features such as Color, Texture and shape of the image are extracted using Gabor Filter, Gray Level Co-occurrence Matrix and Hu-Moment shape feature techniques and also extract the static features like mean and standard deviation. The extracted features are clustered using k-means algorithm and each cluster are trained using ANN based ABC technique. A method using artificial bee colony (ABC) based artificial neural network (ANN) to update the weights assigned to features by accumulating the knowledge obtained from the user over iterations. Eventually, the comparative analysis performed using the commonly used methods namely precision and recall were clearly shown that the proposed system is suitable for the better CBIR and it can reduce the semantic gap than the conventional systems.     

A comprehensive system for image scene classification

In recent years, image scene classification based on low/high-level features has been considered as one of the most important and challenging problems faced in image processing research. The high-level features based on semantic concepts present a more accurate and closer model to the human perception of the image scene content. This paper presents a new multi-stage approach for image scene classification based on high-level semantic features extracted from image content. In the first stage, the object boundaries and their labels that represent the content are extracted. For this purpose, a combined method of a fully convolutional deep network and a combined network of a two-class SVM-fuzzy and SVR are used. Topic modeling is used to represent the latent relationships between the objects. Hence in the second stage, a new combination of methods consisting of the bag of visual words, and supervised document neural autoregressive distribution estimator is used to extract the latent topics (topic modeling) in the image. Finally, classification based on Bayesian method is performed according to the extracted features of the deep network, objects labels and the latent topics in the image. The proposed method has been evaluated on three datasets: Scene15, UIUC Sports, and MIT-67 Indoor. The experimental results show that the proposed approach achieves average performance improvement of 12%, 11% and 14% in the accuracy of object detection, and 0.5%, 0.6% and 1.8% in the mean average precision criteria of the image scene classification, compared to the previous state-of-the-art methods on these three datasets.