A study of tile design for tactile guide pathways

Tactile guide paths can assist blind people to follow a particular route by using their shod feet to detect and distinguish raised patterns. Two kinds of tile are used to form a tactile guide path, pathway tiles with raised strip patterns are used to indicate the direction of travel to be taken and dome tiles with raised dot patterns are used to indicate a potential hazard or a junction. However, the contrast between these two tiles is not very great, so the users may not detect a junction or hazard. The experiment reported here compared existing guide paths with a possible new design, in which, the stimulation from pathway tiles was altered to provide a higher contrast with dome tiles. Twenty-three blind subjects participated in this study. They negotiated an existing guide path and a new design guide path. Each path was 30.3 m long and containing 10 junctions. Performance and responses of the subjects were used to evaluate the paths. The results showed that junction discrimination accuracy and time for the new design were significantly better than for the old design. The subjects also said that that new design was better.

Relevance to industry

Improving the discriminability of the patterns on tactile guide paths may result in enhancing the mobility of blind people. They can then perhaps become more independent and employable.     

A novel histogram transformation to improve the performance of thresholding methods in edge detection

The gradient image is used to detect edge points, and the gradient histogram is a typical case of a unimodal histogram. It is well-documented that bi-modal thresholding methods (such as the Otsu method) detect edges poorly. Therefore, specific unimodal thresholding methods are used to detect edge points. However, unimodal thresholding methods (such as the Rosin method) sometimes obtain very noisy results. In this paper, we propose a histogram transformation to improve the performance of some thresholding methods. Using the Berkeley Segmentation Dataset, we present quantitative performance results in an edge detection task to show that our transformation improves the performance of the Otsu and Rosin methods. Our histogram transformation can be used by any histogram thresholding method, but the performance of the method, using the transformed histogram, will depend of the criterion used by this method.     

A curved surface display for three fingers based on human visual and tactile sensory fusion

In general, it is difficult to present tactile information because arbitrary curvatures of the curved surface and many degrees of freedom need to be realised. On the other hand, psychophysical studies have suggested that human visual and tactile sensations have an illusory fusion characteristic. This means that we can recognise curved surfaces of objects through visual and tactile sensations, even if exact tactile information is not presented. Hence, by utilising the human characteristic of sensory fusion, realisation of a curved surface display can be simplified. From such motivation, the human fusion characteristics of visual and tactile sensation are measured, and are quantitatively analysed. Based on the analysed results, a curved surface display for three fingers is developed. In the curved surface display, only four curved patterns are utilised instead of presenting many curved patterns. Performance of the developed tactile display is proved through evaluated experiments.     

一种基于知识的头部图像提取方法

文章提出了一种基于知识的头肩图像中头部图像的提取方法。首先,应用Sobel算子提取图像的边缘并进行二值化;然后根据边缘图像提取头肩图像的边缘;最后依据人脸知识提取头部图像。用实验室人脸图像库的96幅人脸对该方法进行检验。实验结果表明:文章提出的头部图像提取方法具有较好的效果。     

A gravitational approach to edge detection based on triangular norms

We study the method of Sun et al. for edge detection based on the Law of Universal Gravity. We analyze the effect of the substitution of the product operation by other triangular norms in the calculation of the gravitational forces. We treat edges as fuzzy sets for which membership degrees are extracted from the resulting gravitational force on each pixel. We consider several prototypical triangular norms and experimentally show that their features determine the kind of edges detected. The new method is tested on the Berkeley Segmentation Dataset, showing to be competitive compared to the Canny method.     

一种基于遗传算法的立体匹配方法

根据遗传算法容易获得全局最优解的特点,文章首先利用沈俊边缘检测算子获得图像的边缘特征,然后改进了遗传算法,设计了染色体表示方法、适应度函数以及相应的遗传操作。使之适合于立体匹配的要求。实验结果表明该方法效果良好,具有实用价值。     

基于均值漂移和边缘检测的轮廓跟踪算法

实时的轮廓跟踪算法可以为视频监控系统提供物体的轮廓信息以供对物体类别、物体行为等进行识别.提出一种基于均值漂移和边缘检测的轮廓跟踪算法.方法中,首先利用均值漂移算法跟踪得到目标物体的中心位置,同时用高斯统计模型进行背景更新,从前景图像和背景图像中分别得到具有相同位置和大小的前景矩形区域和背景矩形区域,然后用背景分割的方法得到目标物体区域,再对目标物体区域进行边缘检测就得到了目标物体的轮廓,进而实现了对目标物体的轮廓跟踪.实验表明,可以实时、准确、稳定地对目标物体进行轮廓跟踪.     

一种基于优先搜索方向的边界跟踪算法

图像处理尤其是区域分析中,区域的边界是非常重要的信息。提出了一种基于优先搜索方向的边界跟踪方法。该方法是以区域为基本操作单元,以当前边界点和上一边界点所确定的方向的外法线方向为起始搜索方向,顺时针方向搜索下一个边界点,当下一个边界点与该区域第一个边界点重合时,该区域搜索完毕,并开始对下一个区域进行跟踪。利用这种方法跟踪出来的区域边界,不但能够很好的满足对边界一个像素的宽度、同一个区域的边界连通封闭、准确定位在区域外围轮廓上的要求,而且能够完整准确地保持目标区域外边界的自身原貌和特点,以及内、外边界彼此独立,可独立成图用。由于这种算法在跟踪过程中充分考虑已知边界点对后续边界点的影响,使得边界点保持了良好的相关关系,可以根据实际应用的要求,在跟踪过程中直接实现边界的矢量化。     

一种新颖的基于边缘检测的图像分割方法

针对家庭数字照片的特点以及应用范围,提出了带有衰减因子的Robert微分算子与动态的自适应阈值相结合的边缘检测方法,并利用了边缘检测后边缘点的方向信息,作为Hough变换的方向角,可以较快提取出边缘线段,从而通过边缘跟踪获得无噪声点的相似区域,这为进一步提取图像的颜色特征或形状特征提供了良好的基础。     

基于小波变换的矢量图形无损水印算法

目前,关于矢量图形水印有一些研究,但是并不存在比较通用的算法,且现有算法存在运算量大和没有考虑水印算法对矢量图形拓扑关系的影响等缺陷;在深入研究现有矢量图形水印算法的基础上,针对实际应用,提出了一种基于小波变换的改进算法。实验表明该算法有较好的鲁棒性,同时整个过程是可逆的,通过在高频小波系数中直接插入水印位的方法,可以在提取水印的过程中将空间数据还原,使水印可以不影响矢量图形的显示精度。     

A novel approach for edge detection based on the theory of universal gravity

This paper presents a new, simple and effective low-level processing edge detection algorithm based on the law of universal gravity. The algorithm assumes that each image pixel is a celestial body with a mass represented by its grayscale intensity. Accordingly, each celestial body exerts forces onto its neighboring pixels and in return receives forces from the neighboring pixels. These forces can be calculated by the law of universal gravity. The vector sums of all gravitational forces along, respectively, the horizontal and the vertical directions are used to compute the magnitude and the direction of signal variations. Edges are characterized by high magnitude of gravitational forces along a particular direction and can therefore be detected. The proposed algorithm was tested and compared with conventional methods such as Sobel, LOG, and Canny using several standard images, with and without the contamination of Gaussian white noise and salt & pepper noise. Results show that the proposed edge detector is more robust under noisy conditions. Furthermore, the edge detector can be tuned to work at any desired scale.     

一种基于边缘特征的海岸线检测方法

针对遥感图像中灰度特征的不稳定性,尤其是SAR（合成孔径雷达）图像中水陆灰度的弱对比性,提出一种利用相对稳定的边缘特征进行海岸线检测的新方法。该方法首先用Roberts算子提取海岸区域图像的梯度,并进行自动阈值分割,进而用轮廓跟踪的方法得到海岸线的粗略位置。借鉴主动轮廓的思想,设计一种轮廓逼近的方法,根据遥感图像的梯度强度对粗略的海岸线进行调整,最终得到精确的海岸线。实验表明这种方法在检测精度和抑制海域内干扰等方面都能达到令人满意的效果。     

基于自适应阈值的视频文本检测方法

视频和图像中的文本通常在基于内容的视频数据库检索、网络视频搜索,图像分割和图像修复等中起到重要作用,为了提高文本检测的效率,给出了一种基于多种特征自适应阈值的视频文本检测方法.方法是在Michael算法的基础上,利用文本边缘的强度,密度,水平竖直边缘比3个特征计算自适应局部阈值,用阈值能较好去除非文本区域,提取文本边缘,检测并定位文本,减少了Michael算法单一特征阈值的不利影响.在文本定位阶段引入了合并机制.减少了不完整区域的出现.实验结果表明有较高的精度和召回率,可用于视频搜索、图像分割和图像修复等.     

基于形态学重构的多结构元细胞图像边缘检测

细胞图像边缘检测结果为细胞形态学分析提供依据.针对传统边缘检测算法在细胞图像边缘检测中存在的问题.为了改善图像细节丢失的缺点,提出一种基于形态学重构的边缘检测算法.利用形态学重构运算保持边缘的良好特性,采用多结构元方案,设计形态学重构滤波器对细胞图像进行去噪处理,利用形态学梯度检测算子获取重构后的细胞图像边缘,对获得的多路细胞图像边缘进行加权处理,最终检测出细胞图像边缘.仿真结果表明算法检测效果优于传统边缘检测算子检测效果,检测出的细胞图像边缘连续且一致.     

A comparison study of user behavior on Facebook and Gmail

Email is one of the most important communication media to date, and millions of Internet users around the world spend the bulk of their time writing and reading electronic messages. The growing popularity of Social Network Sites (SNS) as a communication medium motivated us to explore the relationship between user behavior on SNS and email. In this paper, we collected objective, privacy-preserved behavior data from participants that were both active Facebook and Gmail users. We show that a large proportion of social interactions still occur through email messages, while participants tend to be more emotional on Facebook. We found that producing more content on Facebook does not necessarily decrease or increase the production of emails. By utilizing the quantitative analysis of usage data instead of surveys, we show that user behavior is likely consistent across SNS and email in some aspects, for example, users with more Facebook friends seem to email to more people, Facebook and Gmail share similar trend of “happiness”.     

Evaluating requirements modeling methods based on user perceptions: A family of experiments

Numerous methods and techniques have been proposed for requirements modeling, although very few have had widespread use in practice. One drawback of requirements modeling methods is that they lack proper empirical evaluations. This means that there is a need for evaluation methods that consider both the theoretical and practical aspects of this type of methods and techniques. In this paper, we present a method for evaluating the quality of requirements modeling methods based on user perceptions. The evaluation method consists of a theoretical model that explains the relevant dimensions of quality for requirements modeling methods, along with a practical instrument with which to measure these quality dimensions. Basically, it allows us to predict the acceptance of a particular requirements modeling method in practice, based on the effort of applying the method, the quality of the requirements artifacts produced, and the user perceptions with regard to the quality of the method. The paper also presents an empirical test of the proposed method for evaluating a Rational Unified Process (RUP) extension for requirements modeling. That test was carried out through a family of experiments conducted with students and practitioners and provides evidence of the usefulness of the evaluation method proposed.     

一种基于粗糙集的脉冲噪声图像边缘检测算法

研究并提出了一种图像边缘检测算法,对被脉冲噪声污染的图像进行预处理,从而便于图像的分析、理解等后续操作。与一般算法不同,该算法从图像的边缘特性入手来解决边缘检测问题,以由特性决定的一系列边缘点的约束条件作为算法基础,并用粗糙集理论解决了这些条件的相关问题,进而建立了整个边缘检测算法。计算机仿真表明,本文的算法能够有效地从含噪图像中提取边缘信息,较好地克服了传统算法对噪声的敏感性问题。     

A novel edge detection method based on the maximizing objective function

This paper proposes a novel edge detection method for both gray level images and color images. The 3×3 mask in the image is considered and two pixel sets S₀ and S₁ in the mask are used to define an objective function. The values of the objective function corresponding to four directions determine the edge intensity and edge direction of each pixel in the mask. After all pixels in the image have been processed, the edge map and direction map are generated. Then we apply the non-maxima suppression method to the edge map and the direction map to extract the edge points. The proposed method can detect the edge successfully, while double edges, thick edges, and speckles can be avoided.     

A survey on image segmentation

For the past decade, many image segmentation techniques have been proposed. These segmentation techniques can be categorized into three classes, (1) characteristic feature thresholding or clustering, (2) edge detection, and (3) region extraction. This survey summarizes some of these techniques. In the area of biomedical image segmentation, most proposed techniques fall into the categories of characteristic feature thresholding or clustering and edge detection.