一种基于触觉信息的脉冲图注意力残差卷积物体检测算法

触觉传感器(柔性电子皮肤)在机器人进行人机交互和工具操作时发挥着重要作用,如何有效利用触觉信息进行物体检测是当前研究的主要瓶颈.鉴于此,提出一种脉冲图残差卷积神经网络SNN-Atten-ResGCN的物体检测算法.首先使用图残差网络ResGCN模型训练触觉时间序列的表征信息,通过引入深度学习模型中的注意力机制拟合触觉数据图形结构的局部特征;然后对重构的触觉图形输入由3个LIF神经元和2个FC全连接层组成的SNN脉冲神经网络训练得到特征向量;最后投票层Vote解码网络特征并检测物体类别.在EvTouch-Objects和EvTouch-Containers两个家庭常见物体触觉数据集上进行对比实验,实验结果表明,所提出方法在保证模型迭代效率的同时,对各种不同的家庭工具对象和容器对象的检测准确率、精度、召回率和$F_1$-score均有提升.     

Adaptive document block segmentation and classification

This paper presents an adaptive block segmentation and classification technique for daily-received office documents having complex layout structures such as multiple columns and mixed-mode contents of text, graphics, and pictures. First, an improved two-step block segmentation algorithm is performed based on run-length smoothing for decomposing any document into single-mode blocks. Then, a rule-based block classification is used for classifying each block into the text, horizontal/vertical line, graphics, or-picture type. The document features and rules used are independent of character font and size and the scanning resolution. Experimental results show that our algorithms are capable of correctly segmenting and classifying different types of mixed-mode printed documents.     

Interactivity Improves Usability of Geographic Maps for Visually Impaired People

Tactile relief maps are used by visually impaired people to acquire mental representation of space, but they retain important limitations (limited amount of information, braille text, etc.). Interactive maps may overcome these limitations. However, usability of these two types of maps has never been compared. It is then unknown whether interactive maps are equivalent or even better solutions than traditional raised-line maps. This study presents a comparison of usability of a classical raised-line map versus an interactive map composed of a multitouch screen, a raised-line overlay, and audio output. Both maps were tested by 24 blind participants. We measured usability as efficiency, effectiveness, and satisfaction. Our results show that replacing braille with simple audio-tactile interaction significantly improved efficiency and user satisfaction. Effectiveness was not related to the map type but depended on users’ characteristics as well as the category of assessed spatial knowledge. Long-term evaluation of acquired spatial information revealed that maps, whether interactive or not, are useful to build robust survey-type mental representations in blind users. Altogether, these results are encouraging as they show that interactive maps are a good solution for improving map exploration and cognitive mapping in visually impaired people.     

Extraction of Binary Character/Graphics Images from Grayscale Document Images

The extraction of binary character/graphics images from gray-scale document images with background pictures, shadows, highlight, smear, and smudge is a common critical image processing operation, particularly for document image analysis, optical character recognition, check image processing, image transmission, and videoconferencing. After a brief review of previous work with emphasis on five published extraction techniques, viz., a global thresholding technique, YDH technique, a nonlinear adaptive technique, an integrated function technique, and a local contrast technique, this paper presents two new extraction techniques: a logical level technique and a mask-based subtraction technique. With experiments on images of a typical check and a poor-quality text document, this paper systematically evaluates and analyses both new and published techniques with respect to six aspects, viz., speed, memory requirement, stroke width restriction, parameter number, parameter setting, and human subjective evaluation of result images. Experiments and evaluations have shown that one new technique is superior to the rest, suggesting its suitability for high-speed low-cost applications.     

A Deep Residual Network for Geometric Decontouring

Grayscale images are intensively used to construct or represent geometric details infield of computer graphics. In practice, displacement mapping technique often allows an 8-bit grayscale image input to manipulate the position of vertices. Human eyes are insensitive to the change of intensity between consecutive gray levels, so a grayscale image only provides 256 levels of luminances. However, when the luminances are converted into geometric elements, certain artifacts such as false contours become obvious. In this paper, we formulate the geometric decontouring as a constrained optimization problem from a geometric perspective. Instead of directly solving this optimization problem, we propose a data-driven method to learn a residual mapping function. We design a Geometric DeContouring Network (GDCNet) to eliminate the false contours effectively. To this end, we adopt a ResNet-based network structure and a normal-based loss function. Extensive experimental results demonstrate that accurate reconstructions can be achieved effectively. Our method can be used as a relief compressed representation and enhance the traditional displacement mapping technique to augment 3D models with high-quality geometric details using grayscale images efficiently.     

结合面料属性和触觉感测的织物识别

目的 织物识别是提高纺织业竞争力的重要计算机辅助技术。与通用图像相比,织物图像通常只在纹理和形状特征方面呈现细微差异。目前常见的织物识别算法仅考虑图像特征,未结合织物面料的视觉和触觉特征,不能反映出织物本身面料属性,导致识别准确率较低。本文以常见服用织物为例,针对目前常见织物面料识别准确率不高的问题,提出一种结合面料属性和触觉感测的织物图像识别算法。方法 针对输入的织物样本,建立织物图像的几何测量方法,量化分析影响织物面料属性的3个关键因素,即恢复性、拉伸性和弯曲性,并进行面料属性的参数化建模,得到面料属性的几何度量。通过传感器设置对织物进行触感测量,采用卷积神经网络（convolutional neural network,CNN）提取测量后的织物触感图像的底层特征。将面料属性几何度量与提取的底层特征进行匹配,通过CNN训练得到织物面料识别模型,学习织物面料属性的不同参数,实现织物面料的识别并输出识别结果。结果 在构建的常见服用织物样本上验证了本文方法,与同任务的方法比较,本文方法识别率更高,平均识别率达到89.5%。结论 提出了一种基于面料属性和触觉感测的织物图像识别方法,能准确识别常用的服装织物面料,有效提高了织物识别的准确率,能较好地满足实际应用需求。     

基于特征约束点的纹理映射算法

纹理映射技术用于生成物体表面的纹理细节,是真实感图形技术的重要组成部分,也是计算机图形学的一个重要研究方向.针对目前很多纹理映射算法计算量大,方法比较复杂的缺点,应用Candide3作为三维网格模型,提出了一种快速有效的基于特征约束点的纹理映射算法.通过在三维网格模型和纹理图像上选取少量对应的特征约束点,利用三角网格剖分算法在纹理图像上建立选取特征点的三角网格.进而通过求取质心坐标的方法计算出三维网格模型上所有特征点的纹理坐标并完成整个三维网格模型的纹理映射.实验结果表明,提出的算法计算速度较快,能够得到高真实度的纹理映射效果,并且适用于不同纹理图像映射到同一三维网格模型上.     

Text segmentation using gabor filters for automatic document processing

There is a considerable interest in designing automatic systems that will scan a given paper document and store it on electronic media for easier storage, manipulation, and access. Most documents contain graphics and images in addition to text. Thus, the document image has to be segmented to identify the text regions, so that OCR techniques may be applied only to those regions. In this paper, we present a simple method for document image segmentation in which text regions in a given document image are automatically identified. The proposed segmentation method for document images is based on a multichannel filtering approach to texture segmentation. The text in the document is considered as a textured region. Nontext contents in the document, such as blank spaces, graphics, and pictures, are considered as regions with different textures. Thus, the problem of segmenting document images into text and nontext regions can be posed as a texture segmentation problem. Two-dimensional Gabor filters are used to extract texture features for each of these regions. These filters have been extensively used earlier for a variety of texture segmentation tasks. Here we apply the same filters to the document image segmentation problem. Our segmentation method does not assume any a priori knowledge about the content or font styles of the document, and is shown to work even for skewed images and handwritten text. Results of the proposed segmentation method are presented for several test images which demonstrate the robustness of this technique. This work was supported by the National Science Foundation under NSF grant CDA-88-06599 and by a grant from E. 1. Du Pont De Nemours & Company.     

基于LBC的计算机生成图像盲鉴别算法

针对现有的计算机生成图像盲鉴别算法选用的分类特征维度较高、通用性差等问题,提出了一种基于局部二进制计数模式的计算机生成图像盲鉴别算法.首先,将原始图像由RGB颜色空间转换为HSV颜色空间;然后,提取HSV颜色空间图像及其下采样图像的局部二进制计数模式矩阵,求取矩阵归一化直方图;最后,将上述直方图作为分类特征送入SVM分类器,实现计算机生成图像的盲鉴别.实验结果表明,该算法可以有效地鉴别自然图像和计算机生成图像,与现有算法相比具有更高的识别率和较低的特征维度.     

基于循环生成对抗网络的图像风格迁移

图像风格迁移是指将学习到的油画图像风格应用到其他图像上,让图像拥有油画的风格,当前生成对抗网络已被广泛应用到图像风格迁移中。针对循环生成对抗网络CycleGAN在处理图像时纹理清晰度不高的问题,提出了加入局部二值模式LBP算法的方法,将LBP算法加入生成对抗网络的生成器中,增强了循环对抗生成网络提取图像纹理特征内容的效果。针对生成图像产生噪声的问题,在损失函数中加入Total Variation Loss来约束噪声。实验结果表明,循环生成对抗网络加入LBP算法和Total Variation Loss后能提高生成图像的质量,使之具有更好的视觉效果。     

Inverting an Illumination Model from Range and Intensity Maps

We propose a solution to the problem of determining surface material properties from range and intensity data using a simplified version of the Torrance-Sparrow illumination model. The solution uses the photometric stereo method and regularization to invert the model equations at each point on a surface. Assuming a convex surface, one range map, and four or more intensity maps obtained using point light sources, we classify the surface into nonhighlight regions, specular highlight regions, and rank-deficient regions. This classification allows the appropriate solution method to be applied to each region. In nonhighlighted regions we use linear least squares, in highlight regions, nonlinear separable least squares with regularization, and in rank-deficient regions, interpolation. The solution consists of the values of the three parameters of the illumination model at each point on the surface. We believe this technique to be a useful adjunct to recently reported noncontact modeling systems. These systems have been designed to build computer graphics models automatically from real objects by determining surface geometry, surface relief texture, and material properties. Our technique greatly enhances the modeling of material properties. The paper concludes with a number of examples of the method applied to synthetic and real images, and a discussion of possibilities for future systems.     

3D fingerprint reconstruction system using feature correspondences and prior estimated finger model

The paper studies a 3D fingerprint reconstruction technique based on multi-view touchless fingerprint images. This technique offers a solution for 3D fingerprint image generation and application when only multi-view 2D images are available. However, the difficulties and stresses of 3D fingerprint reconstruction are the establishment of feature correspondences based on 2D touchless fingerprint images and the estimation of the finger shape model. In this paper, several popular used features, such as scale invariant feature transformation (SIFT) feature, ridge feature and minutiae, are employed for correspondences establishment. To extract these fingerprint features accurately, an improved fingerprint enhancement method has been proposed by polishing orientation and ridge frequency maps according to the characteristics of 2D touchless fingerprint images. Therefore, correspondences can be established by adopting hierarchical fingerprint matching approaches. Through an analysis of 440 3D point cloud finger data (220 fingers, 2 pictures each) collected by a 3D scanning technique, i.e., the structured light illumination (SLI) method, the finger shape model is estimated. It is found that the binary quadratic function is more suitable for the finger shape model than the other mixed model tested in this paper. In our experiments, the reconstruction accuracy is illustrated by constructing a cylinder. Furthermore, results obtained from different fingerprint feature correspondences are analyzed and compared to show which features are more suitable for 3D fingerprint images generation.     

一种基于亮度特征的图形图像分类方法

色彩管理中的自适应色域匹配技术，要求对不同渲染目的的图像自动分类。文中通过对图像的亮度直方图进行统计，提取了亮度级数和亮度直方图包络光滑度两个特征量，实现了一种基于该特征的图形图像分类方法，对自然照片和计算机生成图形这两种不同种类的图像进行了区分。     

A knowledge-based system for extracting text-lines from mixed and overlapping text/graphics compound document images

This paper presents a new knowledge-based system for extracting and identifying text-lines from various real-life mixed text/graphics compound document images. The proposed system first decomposes the document image into distinct object planes to separate homogeneous objects, including textual regions of interest, non-text objects such as graphics and pictures, and background textures. A knowledge-based text extraction and identification method obtains the text-lines with different characteristics in each plane. The proposed system offers high flexibility and expandability by merely updating new rules to cope with various types of real-life complex document images. Experimental and comparative results prove the effectiveness of the proposed knowledge-based system and its advantages in extracting text-lines with a large variety of illumination levels, sizes, and font styles from various types of mixed and overlapping text/graphics complex compound document images.     

硬件加速的数字化放射图像重建算法

数字化放射图像重建技术被广泛应用于癌症放射治疗中,包括诊断、术前规划及术内辅助．提出一种两步法硬件加速数字化放射图像重建算法：第一步将光线投射的三个步骤,即几何变换、场景遍历和渲染,完全在可编程图形硬件中实现,从而快速模拟了X-光线的衰减过程;第二步利用浮点精度纹理和render-to-texture功能,快速模拟出高质量的X-光线的负片曝光效果．实验结果表明,该算法能高质量地交互重建数字化放射图像,适用于放射诊断及治疗等应用．     

图像局部纹理特性的静电力触觉渲染

目的 触摸触觉设备感知物体时,需要实现视觉-力触觉同步反馈,其中图像-力触觉反馈难点在于再现更真实的纹理触感的触觉渲染过程。本文提出了一种基于图像局部纹理特征的静电力触觉渲染模型,实现了更加清晰、触感真实的图像纹理的静电力触觉反馈。方法 首先,采用局部傅里叶变换方法强化局部纹理特征,提取傅里叶变换系数分离出表征形状和局部纹理、边缘的频域分量。其次,对局部纹理特征进行力触觉渲染,建立局部纹理特征与驱动信号的映射模型,采用比例模型将局部纹理特征值转化为同等级的静电力表达。最后,根据静电力与驱动信号的心理学模型,由局部纹理特征控制不同驱动信号的输出产生静电力触觉。结果 进行纹理触觉对比感知实验验证算法有效性,62.5%的实验参与者偏爱基于图像局部纹理的触觉渲染算法反馈的纹理触感,本文算法可以模拟多种图像的纹理、边缘的触感。结论 算法在频域分离图像局部纹理、边缘和形状特征,建立纹理-力触觉渲染模型,针对大多数图片可以有效地增强纹理触感,提升触觉再现交互技术的沉浸感。     

Image source acquisition identification of mobile devices based on the use of features

Nowadays, forensic analysis of digital images is especially important, given the frequent use of digital cameras in mobile devices. The identification of the device type or the make and model of image source are two important branches of forensic analysis of digital images. In this paper we have addressed both of these, with an approach based on different types of image features and the classification using support vector machines. The study has mainly focused on images created with mobile devices and as a result, the techniques and features have been adapted or created for this purpose. There have been a total of 36 experiments classified into 5 sets, in order to test different configurations of the techniques. In the configuration of the experiments, the future use of the technique by the forensic analyst in real situations to create experiments with high technical requirements was taken into account, amongst other things.     

Bit-mapped graphics: A semantics and theory

Because of its convenience and growing supporting technology, a form of raster graphics called bit-mapped graphics is becoming increasingly pervasive. A typical bit-mapped graphics environment supports the efficient manipulation of high-resolution images over a small intensity space. As such, a unique set of bit-map concepts and operations has evolved. This paper argues that a rigorous consideration of bit-mapped graphics is important and useful. A semantics of bit-mapped graphics is presented, which carefully distinguishes among scenes, bit-maps, and images. The semantic framework is then used to prove some interesting results regarding the 2D rendering, or rasterisation, of scenes into images. We also introduce the useful notion of “stable” lines, and consider the conditions under which a geometric transformation is “faithful” to a bit-map. Apart from their intrinsic interest, the results reported here constitute a first step towards arriving at a definitive understanding of the relationship between bit-mapped graphics and other computer graphics technologies.     

基于卷积块注意力模块的图像描述生成模型

图像描述生成模型是使用自然语言描述图片的内容及其属性之间关系的算法模型.对现有模型描述质量不高、图片重要部分特征提取不足和模型过于复杂的问题进行了研究,提出了一种基于卷积块注意力机制模块(CBAM)的图像描述生成模型.该模型采用编码器-解码器结构,在特征提取网络Inception-v4中加入CBAM,并作为编码器提取图片的重要特征信息,将其送入解码器长短期记忆网络(LSTM)中,生成对应图片的描述语句.采用MSCOCO2014数据集中训练集和验证集进行训练和测试,使用多个评价准则评估模型的准确性.实验结果表明,改进后模型的评价准则得分优于其他模型,其中Model2实验能够更好地提取到图像特征,生成更加准确的描述.