Composite description based on color vector quantization and visual primary features for CBIR tasks

Multimedia Tools and Applications - This paper presents a novel method for content-based color image retrieval that combines color vector quantization and visual primary features into a compact...     

Error sensitivity model based on spatial and temporal features

Packet loss and error propagation induced by it are significant causes of visual impairments in video applications. Most of the existing video quality assessment models are developed at frame or sequence level, which can not accurately describe the impact of packet loss on the local regions in one frame. In this paper, we propose an error sensitivity model to evaluate the impact of a single packet loss. We also make full use of the spatio-temporal correlation of the video and analyze a set of features that directly impact the perceptual quality of videos, based on the specific situation of video packet loss. With the aid of the support vector regression (SVR), these features are used to predict the error sensitivity of the local region. The proposed model is tested on six video sequences. Experimental results show that the proposed model predicts sensitivity of videos to different packet loss cases with certain reasonable accuracy, and provides good generalization ability, which turns out outperform the state-of-art image and video quality assessment methods.

     

基于CV模型和NSCT的红外与可见光图像融合

针对传统融合方法在光照不足、目标隐藏或目标和背景颜色接近时,容易出现目标信息丢失或减弱的现象,提出一种将基于CV模型的目标提取与NSCT相结合的方法。该方法使用动态轮廓线模型对红外目标进行搜索检测识别,将源图像序列分为目标和背景区域,利用非下采样Contourlet变换对输入图像进行多尺度、多方向稀疏分解,准确捕获图像中的高维奇异信息,并在目标和背景区域里分别采用不同的融合规则,将其与小波融合方法、拉普拉斯融合方法、NSCT方法作对比,并通过熵、平均梯度、空间频率、标准差等参数对融合后的图像进行定量分析。实验结果表明,该方法不但较好地提高了融合图像的目标探测性,而且融合结果中的目标比较清晰,亮度较高,目视效果较好,在主观视觉效果与客观评价指标上均取得了很好的融合效果。     

结合引导解码和视觉注意力的图像语义描述模型

针对输入的图像视觉信息不能在每一步解码过程中动态调整,同时为了提高图像语义描述模型的精度和泛化能力,提出了一种结合引导解码和视觉注意力机制的双层长短时记忆（long short term memory,LSTM）网络的图像语义描述模型。将提取到的图像的视觉和目标特征通过一个引导网络建模后送入LSTM网络的每一时刻,实现端到端的训练过程;同时设计了基于图像通道特征的视觉注意力机制,提高了模型对图像细节部分的描述。利用MSCOCO和Flickr30k数据集对模型进行了训练和测试,结果显示模型性能在不同的评价指标上都得到了提升。     

Egocentric visual scene description based on human-object interaction and deep spatial relations among objects

Multimedia Tools and Applications - Visual Scene interpretation is one of the major areas of research in the recent past. Recognition of human object interaction is a fundamental step...     

基于改进的C-V模型虚拟人脑图像分割模型

C-V模型是一种较为经典的分割模型,但传统的C-V模型仅能够将图像分割成单一的目标部分与背景部分;用于彩色图像分割往往基于目标的强度信息;在曲线演化过程中需要重新初始化水平集函数保持符号距离函数。针对这些问题,使用PCA理论将颜色空间投影到新的空间中,可以扩大两者的颜色距离;使用局部信息可校正颜色强度不均匀;将距离约束项引入到模型中,使模型能够无需重新初始化,提高了演化速度。实验结果表明改进的算法能较精确地得到分割结果。     

基于特征的彩色位图隐写分析

针对互联网上流行的真彩位图文件的隐写算法工具InplainView, 根据算法嵌入原理和特征分析,成功实现了对隐秘图像的检测;通过研究从隐秘图像中所提取消息的字符频度分布,提出了对嵌入消息加密的密钥恢复解决方案,有效提高了隐写分析性能。最后的实验结果表明,该隐写分析方法简单、高效,便于实用。     

基于神经网络的三维模型视觉特征分析

首先从形状、颜色、纹理材质三个主要视觉特性入手,阐述模型的特征描述符,设计三元组视觉特征向量用于神经网络进行模型分类。具体基于感知器神经网络、Hopfield神经网络分别实现了对三维物体的分类。实验表明,基于神经网络的分类器能对基于视觉特征描述的三维物体进行有效识别。     

基于复合图文特征的视觉问答模型研究

针对当前主流视觉问答(visual question answering,VQA)任务使用区域特征作为图像表示而面临的训练复杂度高、推理速度慢等问题,提出一种基于复合视觉语言的卷积网络(composite visionlinguistic convnet,CVlCN)来对视觉问答任务中的图像进行表征.该方法将图像特征和问题语义通过复合学习表示成复合图文特征,然后从空间和通道上计算复合图文特征的注意力分布,以选择性地保留与问题语义相关的视觉信息.在VQA-v2数据集上的测试结果表明,该方法在视觉问答任务上的准确率有明显的提升,整体准确率达到64.4％.模型的计算复杂度较低且推理速度更快.     

An efficient spatial access method for spatial images containing multiple non-overlapping features

In this paper we propose and analyze a new spatial access method, namely the S*-tree, for the efficient secondary memory encoding and manipulation of images containing multiple non-overlapping features (i.e., coloured images). The S*-tree is based on a non-straightforward and space efficient extension to coloured images of its precursor, namely the S⁺-tree, which was explicitly designed for binary images. To assess experimentally the qualities of the S*-tree, we test it against the HL-quadtree, a previous spatial access method for coloured images, which is known to be space and time efficient. Our experiments show that the S*-tree reaches up to a 75% of space saving, and performs constantly less I/O accesses than the HL-quadtree in solving classical window queries.     

基于视觉词汇形状描述的图像表示方法

针对目前图像表示中引入空间位置信息的空间金字塔匹配方法缺乏对图像中视觉物体平移、缩放和旋转的考虑,提出一种基于视觉词汇形状描述模型的图像表示方法。该方法相对于每个视觉单词的几何中心建立空间几何模型,保证平移不变性;给出对数极坐标空间金字塔匹配,对对数极半径做归一化,保证缩放不变性;在空间金字塔划分过程中确定极角的主方向,从而保证旋转不变性。分别在Caltech-101数据集和自建图像数据集上对该方法进行了验证和比较。实验结果表明,该方法提高了分类识别准确率,特别是对于包含明显平移、缩放和旋转变化的图像数据集;该方法的方差较小,说明其鲁棒性更强。     

视觉相似性计算的艺术图像自组织方法

为解决大量数字化艺术图像常规组织和管理复杂低效问题,提出一种基于图像相似性计算的自组织方法,对艺术图像提取了颜色、纹理、空间布局和SIFT等用于相似性计算的视觉特征表示,并根据艺术图像空间布局特点设计计算模型,试验了特征的聚类效果。采用多层版本近邻传播聚类（MLAP）算法为基础,对实验图像库进行层次化聚类,构建图像的层次化浏览结构。实验结果表明,该方法在艺术图像的管理和使用上都有着良好的性能。     

基于视觉相似性的去色图像质量评估

针对基于结构相似性的去色图像质量评估算法没有充分利用图像的梯度特征且采用的对比度相似度特征会忽略图像连续颜色块的一致性导致算法与人类视觉主观判定有较大出入的问题,提出一种基于图像视觉相似性的去色图像质量评估算法--C2G-VSIM。该算法以彩色图像为参考图像,由不同去色算法产生的与之相关的去色灰度图像作为测试图像,对参考图像以及测试图像进行颜色空间转换,并且进行高斯滤波,充分考虑了图像亮度相似度和结构相似度特征,并在此基础上首先引入一种新的颜色一致性对比特征以促使C2G-VSIM对全局颜色对比度特征进行捕捉,其次引入梯度幅值特征至C2G-VSIM中以提高算法对图像梯度特征的敏感度,最后联合得到图像质量评估因子C2G-VSIM。在Cadík的数据集上的实验结果表明,C2G-VSIM与人类视觉主观评定的等级相关性在准确度和主观评判喜爱度上分别达到了0.8155和0.7634,相对于基于彩色图和灰度图的结构相似性（C2G-SSIM）评估算法在未增加较大耗时的情况下,准确度有明显提高。所提算法与人类视觉主观判定具有较高的一致性,且计算简单,在实际工程中能大规模且有效地对去色图像进行自动化评分。     

Image retrieval model based on weighted visual features determined by relevance feedback

An accurate and rapid method is required to retrieve the overwhelming majority of digital images. To date, image retrieval methods include content-based retrieval and keyword-based retrieval, the former utilizing visual features such as color and brightness, and the latter utilizing keywords that describe the image. However, the effectiveness of these methods in providing the exact images the user wants has been under scrutiny. Hence, many researchers have been working on relevance feedback, a process in which responses from the user are given as feedback during the retrieval session in order to define a user’s need and provide an improved result. Methods that employ relevance feedback, however, do have drawbacks because several pieces of feedback are necessary to produce an appropriate result, and the feedback information cannot be reused. In this paper, a novel retrieval model is proposed, which annotates an image with keywords and modifies the confidence level of the keywords in response to the user’s feedback. In the proposed model, not only the images that have been given feedback, but also other images with visual features similar to the features used to distinguish the positive images are subjected to confidence modification. This allows for modification of a large number of images with relatively little feedback, ultimately leading to faster and more accurate retrieval results. An experiment was performed to verify the effectiveness of the proposed model, and the result demonstrated a rapid increase in recall and precision using the same amount of feedback.     

基于小波系数相关性的图像自适应空域隐写术

定义图像中像素的嵌入失真是图像自适应隐写中的关键。为提高图像自适应隐写的安全性,根据最小化嵌入失真原则,提出了一种基于小波系数相关性的图像自适应空域隐写术。首先以一维高通、低通滤波器为工具构造方向滤波器;然后沿水平、垂直、对角线方向对图像进行方向滤波,并根据小波系数与其邻域系数的相关性对失真函数进行设计;最后根据像素的嵌入失真值,利用网格码(STC)对秘密信息进行嵌入。实验结果表明,该隐写术能够将嵌入区域集中在内容复杂的纹理区域,且能够有效抵抗通用隐写检测算法的分析。     

A SIFT features based blind watermarking for DIBR 3D images

Depth image based rendering (DIBR) is a promising technique for extending viewpoints with a monoscopic center image and its associated per-pixel depth map. With its numerous advantages including low-cost bandwidth, 2D-to-3D compatibility and adjustment of depth condition, DIBR has received much attention in the 3D research community. In the case of a DIBR-based broadcasting system, a malicious adversary can illegally distribute both a center view and synthesized virtual views as 2D and 3D content, respectively. To deal with the issue of copyright protection for DIBR 3D Images, we propose a scale invariant feature transform (SIFT) features based blind watermarking algorithm. To design the proposed method robust against synchronization attacks from DIBR operation, we exploited the parameters of the SIFT features: the location, scale and orientation. Because the DIBR operation is a type of translation transform, the proposed method uses high similarity between the SIFT parameters extracted from a synthesized virtual view and center view images. To enhance the capacity and security, we propose an orientation of keypoints based watermark pattern selection method. In addition, we use the spread spectrum technique for watermark embedding and perceptual masking taking into consideration the imperceptibility. Finally, the effectiveness of the presented method was experimentally verified by comparing with other previous schemes. The experimental results show that the proposed method is robust against synchronization attacks from DIBR operation. Furthermore, the proposed method is robust against signal distortions and typical attacks from geometric distortions such as translation and cropping.     

基于链码描述的图像图形特征提取

为提取云团反射率图像内部层次类特征和轮廓线上不规则的凹陷类特征,在构建基于图像内容的层次结构模型的基础上,提出相对极坐标系下的距离链码和基于八方向链码的累积导数和差码方法,前者用于层次类特征提取,后者用于轮廓形态特征的提取,构建梯度特征、云砧特征以及凹陷特征的提取算法.实验证明,该方法下的特征类间区分度高,运行速度快,可用于解决非刚体图像的相关特征的提取.