Demand-driven image transmission with levels of detail and regions of interest

In this paper, we introduce a formal model which describes consistently levels of detail and regions of interest for the progressive transmission of raster images. This model serves as the foundation of a wavelet-based image communication framework which supports the progressive, redundancy-free transmission of multiple, possibly overlapping regions of interest in an image. To support demand-driven transmission, we introduce a method for interleaving control commands with the embedded bit stream. Since the dyadic wavelet decomposition allows the image resolutions in x and y direction to differ at most by a factor of two, we propose a new wavelet decomposition scheme which raises this number to a power of two for increased flexibility. We discuss some applications including the rectangular fish eye view, a focus and context display technique for raster images which efficiently uses this transmission method and saves screen real-estate.     

Multimedia recipe reading: Predicting learning outcomes and diagnosing cooking interest using eye-tracking measures

This study aimed to explore the relationships between students' visual behaviors and learning outcomes, and between visual behaviors and prior cooking interest in multimedia recipe learning. An eye-tracking experiment, including pretest, recall test, and retention test, was conducted with a sample of 29 volunteer hospitality majors in Taiwan. The multimedia recipe included a static page showing the ingredients in a text-and-picture representation and a dynamic page showing the knife skills in a text-and-video representation. Total reading time, total fixation duration, number of fixations and inter-scanning count were used to explore the students' visual attention distributions among the different representation elements and their visual strategies for learning the recipe. The results showed that all students paid more visual attention to the text than to the picture information for the static recipe, and paid more visual attention to the video than to the text on the dynamic page. In addition, the visual attention paid to the text on the dynamic page was negatively correlated with the retention of the episodic knowledge of knife skills. In contrast, the visual attention paid to the text on the static ingredient page was positively correlated with students' prior cooking interest. Finally, the inter-scanning count between text and video on the dynamic page was the best index to negatively predict students' learning retention. Total fixation duration on the text information on the static page was the best index to positively predict students' prior cooking interest. Future studies and applications are discussed.     

Use of power law models in detecting region of interest

In this paper, we shall address the issue of semantic extraction of different regions of interest. The proposed approach is based on statistical methods and models inspired from linguistic analysis. Here, the models used are Zipf law and inverse Zipf law. They are used to model the frequency of appearance of the patterns contained in images as power law distributions. The use of these models allows to characterize the structural complexity of image textures. This complexity measure indicates a perceptually salient region in the image. The image is first partitioned into sub-images that are to be compared in some sense. Zipf or inverse Zipf law are applied to these sub-images and they are classified according to the characteristics of the power law models involved. The classification method consists in representing the characteristics of the Zipf and inverse Zipf model of each sub-image by a point in a representation space in which a clustering process is performed. Our method allows detection of regions of interest which are consistent with human perception, inverse Zipf law is particularly significant. This method has good performances compared to more classical detection methods. Alternatively, a neural network can be used for the classification phase.     

基于感兴趣区域的图像质量评价方法

将图像质量的评价划分为感兴趣区域与非感兴趣区域的加权组合评价,在感兴趣区域内使用梯度算子改进结构相似评价方法,非感兴趣区域沿用经典的结构相似评价。实验结果表明,该方法能较好地考虑感兴趣区域的重要性,更符合人的主观视觉质量。     

一种基于视觉兴趣性的图象质量评价方法

图象质量的正确评价是图象信息工程领域内一项很有意义的研究课题,但现有的图象客观评价方法并不完全符合人眼视觉特性。合理地评价图象质量应充分遵循人眼的视觉特性,但由于受到人的心理、文化背景、周围环境、不同的应用场合等多种因素的影响,人眼对同一幅图象中的不同区域往往具有不同的感兴趣程度,即人眼具有视觉兴趣性特性,该文在充分利用视觉兴趣性特性的基础上,针对只存在一个感兴趣区的图象,提出了一种简化的图象质量     

噪声信道下保护图像感兴趣区的多描述编码*

将感兴趣区编码和多描述编码相结合,提出一种噪声信道下保护图像感兴趣区的多描述编码方法。该方法将图像分为感兴趣区和背景区,并采用多描述编码方法,将感兴趣区和背景区码流编码成多个描述。同时对感兴趣区和背景区描述码流采用不同的冗余树分配方案,以进一步增强图像感兴趣区的抗分组丢失能力。实验证明,该方法即使在信道拥塞较为严重的情况下,也能为图像的感兴趣区提供令人满意的重建质量。     

基于粗糙集的图像感兴趣区域自动提取算法

在分析常规区域生长算法的基础上,提出一种基于粗糙集理论的感兴趣区域自动提取算法．在显著度图和相对位置指示图的基础上,以像素点的显著度、相对位置及颜色信息构成知识表达系统,通过属性约简和值约简,导出了有用的区域生长决策规则。实验结果表明：该方法与现有算法相比,它能够更好地提取图像感兴趣区域。     

阅读眼动追踪语料库的构建与应用研究综述

阅读文字时眼球的运动反映了人类的认知过程。阅读眼动数据是认知心理学、应用语言学、计算机科学等领域中重要的基础数据,而我国在阅读眼动研究的基础数据方面较欠缺。针对这一现状,首先介绍了阅读眼动追踪语料库产生的背景以及国内外的相关文献;然后从影响阅读眼动的低水平视觉因素和高水平视觉因素角度介绍了阅读眼动追踪语料库的内容及所使用的各项眼动指标,如单一注视时间、首次注视时间、凝视时间、总注视时间、回视出次数、回视入次数等,并分析了使用语料库研究法进行阅读眼动研究相比传统阅读眼动研究具有的3个优势;最后从语料库眼动指标变量、语料规模、语料内容、语料语种、被试规模、被试特征、采集设备等方面介绍了国外已经建成的较有影响力的若干阅读眼动追踪语料库,以供阅读眼动研究者参考。在眼动追踪语料库应用研究方面,对认知心理学、应用语言学和计算机科学等相关领域已开展的主要研究进行述评,重点介绍了在计算机科学的眼动可计算模型、自然语言处理、模式识别3个领域中基于阅读眼动追踪语料库开展的典型研究。在中文阅读眼动追踪语料库的构建与应用研究方面,介绍了我国相关研究的开展现状,分析了我国在眼动基础数据方面欠缺的原因,并从国家、...     

Finding a small number of regions in an image using low-level features

Many computer vision applications, such as object recognition, active vision, and content-based image retrieval (CBIR) could be made both more efficient and effective if the objects of most interest could be segmented easily from the background. In this paper, we discuss how to compute and process low-level features in order to obtain “reasonable” regions for the putative objects. This process is a precursor to the detection of salient objects in an image, a subject discussed in a companion report [1]. Although considerable work has been done on image segmentation, there still does not exist an “off-the-shelf” solution applicable to all types of images. A major issue has been the lack of a good measure of quality of a particular segmentation. In this paper, three different measures are considered: the non-parametric measure (NP) proposed by Pauwels and Frederix [2], the modified Hubert index (MH) [3], and a threshold-based measure with a manually selected threshold. From the experimental results, we have found that the simple threshold-based measure gave consistently better results than the other two more complex, statistically based measures. The particular image segmentation method we have employed in this study is also described in detail.     

Registering georeferenced photos to a building information model to extract structures of interest

Vision-based techniques are being used to inspect structures such as buildings and infrastructure. Due to various backgrounds in the acquired images, conventional vision-based techniques rely heavily on manual processing to extract relevant structures of interest for subsequent analysis in many applications, such as distress detection. This practice is laborious, time-consuming, and error-prone. To address the challenge, this study proposes a new method that automatically matches a georeferenced real-life photo with a building information model-rendered synthetic image to allow the extraction of relevant structure of interest. Field experiments were conducted to validate and evaluate the proposed method. The average accuracy of this method is 79.21% and the processing speed is 140 s per image. The proposed method has the potential to reduce the workload of image processing for vision-based structural inspection.     

Task-based scanpath assessment of multi-sensor video fusion in complex scenarios

The combining of visible light and infrared visual representations occurs naturally in some creatures, including the rattlesnake. This process, and the wide-spread use of multi-spectral multi-sensor systems, has influenced research into image fusion methods. Recent advances in image fusion techniques have necessitated the creation of novel ways of assessing fused images, which have previously focused on the use of subjective quality ratings combined with computational metric assessment. Previous work has shown the need to apply a task to the assessment process; the current work continues this approach by extending the novel use of scanpath analysis. In our experiments, participants were shown two video sequences, one in high luminance (HL) and one in low luminance (LL), both featuring a group of people walking around a clearing of trees. Each participant was shown visible and infrared (IR) inputs alone; and side-by-side (SBS); in an average (AVE) fused; a discrete wavelet transform (DWT) fused; and a dual-tree complex wavelet transform (DT-CWT) fused displays. Participants were asked to track one individual in each video sequence, as well as responding by key press when other individuals carried out secondary actions. Results showed the SBS display to lead to much poorer accuracy than the other displays, while reaction times in carrying out the secondary task favoured AVE in the HL sequence and DWT in the LL sequence. Results are discussed in relation to previous findings regarding item saliency and task demands, and the potential for comparative experiments evaluating human performance when viewing fused sequences against naturally occurring fusion processes such as the rattlesnake is highlighted.     

一种基于优先级的多个感兴趣区域图像编码方法

JPEG2000采用感兴趣区域编码能够实现一幅图像的多种质量压缩。针对以往提供的各种方法都对一个感兴趣区域进行编码的缺点,提出了实现多个感兴趣区域的无损压缩的方法。其主要特点是利用优先级的方法重新排列编码数据流中的包,通过优先级排列可以区分ROI和背景区域在每个分解级中的相对重要性,而且在同一幅图像中有多个感兴趣区域的时候,它能够提供多个优先级,能够很好的实现多个感兴趣区域无损压缩的图像编码。     

基于兴趣区域的无参考图像质量评价方法

为了评价不同失真类型图像的质量,提出了一种基于兴趣区域和自然图像统计特性的无参考图像质量评价方法。该方法对Itti模型进行改进,并利用改进的Itti模型提取失真图像的感兴趣区域和非感兴趣区域,在非下采样Contourlet域提取图像的统计特性,通过计算失真图像的不同区域与自然图像统计特性的差异来获得图像的质量分数。在LIVE数据集上与已有方法进行对比,实验结果表明,提出的方法和主观感知具有较好的一致性。     

基于视觉注意的医学图像感兴趣区域提取*

提出一种基于视觉注意机制的医学图像感兴趣区域提取方法。受生物学启发,该方法模仿人类自下而上的视觉选择性注意过程,通过计算图像中每个像素的全局对比度,构造相应的显著图,并根据显著图,检测出图像中的显著区域。利用多幅医学图像对本方法进行评估,结果表明,该方法能够快速、精确地提取图像中的感兴趣区域,在提取结果和运算速度上均取得了令人满意的效果。     

基于图像内容的用户兴趣模型研究

对信息主动服务（即“推”服务）中用户对图像兴趣问题进行了研究。基于分析用户对图像内容的兴趣程度、图像对图像内容的从属度和用户对图像的兴趣程度,提出了基于图像内容的用户兴趣模型,并对模型的性质和维护进行了初步分析。最后通过仿真算例演示了该模型的计算流程。     

基于SPIHT的感兴趣区域编码

感兴趣区域(ROI)编码是一种重要的图像编码思想,可用来解决图像质量与压缩比之间的矛盾,特别适合应用到医学图像压缩中.提出了一种基于层次树集合划分(SPIHT)算法的感兴趣区域编码方法,通过附加ROI掩模信息,无需提升小波系数,使得ROI优先于其它区域编码和传输.     

A saliency map based on sampling an image into random rectangular regions of interest

In this article we propose a novel approach to compute an image saliency map based on computing local saliencies over random rectangular regions of interest. Unlike many of the existing methods, the proposed approach does not require any training bases, operates on the image at the original scale and has only a single parameter which requires tuning. It has been tested on the two distinct tasks of salient region detection (using MSRA dataset) and eye gaze prediction (using York University and MIT datasets). The proposed method achieves state-of-the-art performance on the eye gaze prediction task as compared with nine other state-of-the-art methods.     

视觉关注度的立体图像质量评价

立体图像质量评价对立体视频技术的发展起着非常重要的作用。常用的PSNR(峰值信噪比)方法不能反映人类视觉感知特性,也不能直接应用到立体图像质量评价中。针对人类视觉对立体图像深度感知和重点关注感兴趣区的特点,提出基于纹理图和深度图感兴趣区的质量评价方法。首先对纹理图和对应的深度图利用视觉关注度提取工具提取感兴趣区,然后在评价的过程中对各感兴趣区根据感兴趣程度分配基于像素的权重系数,最后将权重系数应用在立体图像的各个区域中进行评价。实验结果表明该方法得到的立体图像质量客观评价结果与主观评价结果之间具有更好的一致性,符合人眼视觉系统感知特性。