基于多卷积核DPCNN的维吾尔语文本分类联合模型

由于维吾尔语形态丰富且资源匮乏,因此直接使用现有的深度学习模型并不能很好地完成文本分类任务。基于此,该文提出了MDPLC文本分类模型,即首先将预先训练的词向量和经Bi-LSTM处理得到的语义信息进行融合,进而得到全句语义依赖,然后通过组合池化的CNN进一步加强局部语义学习,同时以双通道的方式使用多卷积核DPCNN捕获文本语义信息,最后融合两种模型提取到的信息完成文本分类任务。为验证该模型的有效性,该文分别采用中文、英文和维吾尔文短、长文本数据集进行实验,实验结果表明,该模型在多个分类任务中取得的性能都高于现有主流深度学习模型,验证了该模型在不同语种、语义表达稀疏和语义丰富各种情况下的鲁棒性。     

Multispectral textured image segmentation using a multi-resolution fuzzy Markov random field model on variable scales in the wavelet domain

This article proposes a new multispectral image texture segmentation algorithm using a multi-resolution fuzzy Markov random field model for a variable scale in the wavelet domain. The algorithm considers multi-scalar information in both vertical and lateral directions. The feature field of the scalable wavelet coefficients is modelled, combining with the fuzzy label field describing the spatially constrained correlations between neighbourhood features to achieve a more accurate parameter estimation. The extended scalable label field models the label data from different scales to obtain more homogeneous areas; image segmentation results are finally obtained according to the Bayesian rule from a coarser to a finer scale. Multispectral texture images and remote-sensing images are used to test the effectiveness of the the proposed method. Segmentation results show that the new method simultaneously presents a better performance in achieving the homogeneity of the region and accuracy of detected boundaries compared with existing image segmentation algorithms.     

多参数加权的无缝纹理映射算法

目的 针对基于图像3维重建中纹理映射存在缝隙的问题,提出一种多参数加权的无缝纹理映射算法。方法 算法根据图像的标定信息对三角格网进行聚类分割,将重建模型聚类成不同参考图像的网格贴片,并对贴片排序生成纹理图像,加权融合重建顶点的法线角度、图像视点、模型深度等信息生成纹理贴片像素,最后采用多分辨率分解融合技术消除纹理贴片缝隙,实现无缝的纹理映射。结果 对不同的测试数据进行了验证,本文算法在保持一定清晰度的前提下消除了纹理的缝隙,即使对于构网误差较大的区域也能得到较为满意的结果,同时本文算法支持大数据的3维纹理映射。结论 提出了一种无缝的纹理映射算法,算法通过构造一个平滑的加权方程融合多源信息消除纹理的接缝,实验结果表明了本文算法的有效性及实用性,得到了高保真的无缝纹理映射效果,可应用到城市级别的大场景3维重建领域。     

结合分水岭的纹理梯度各向异性图像分割

目的 目前,许多图像分割算法对含有丰富纹理信息的图像的分割效果并不理想,尤其是在不同纹理的边缘信息的保持方面。为了解决这一问题,提出一种基于连续纹理梯度信息的各向异性图像分割算法。方法 在分水岭算法的基础上,引入纹理梯度各向异性算法,能够在避免纹理信息影响分割效果的前提下,最大限度地保证纹理边缘信息的完整。针对纹理特征数据敏感的特性,本文将离散的图像高度信息映射到连续的纹理梯度空间,能够有效减少由细小差异造成的过分割现象。结果 本文方法在BSD500 Dataset和Stanford Background Dataset中选择了大量的纹理信息丰富的图片与最新的分割算法进行了实验与对比。本文方法在分割效果（降低过分割现象）、保持边缘信息和分割准确率等方面均获得明显改进,并在图像分割的平均准确率方面与最新算法进行比较发现,本文算法的平均分割准确率达到90.9%,明显超过了其他最新算法,验证了本文方法的有效性。结论 本文提出的基于分水岭的纹理梯度各向异性算法对纹理图像的分割具有保边和准确的特点,采用连续梯度空间的方法能够有效地减少传统分水岭算法的过分割现象。本文方法主要适用于纹理信息丰富（自然纹理和人工纹理）的图片。     

基于异构特征聚合的局部视图扭曲型纸币识别

如何识别同一物体的不同结构的表现形式,对于机器而言,是一个比较困难的识别工作.本文以易变形的纸币为例,提出了一种基于异构特征聚合的局部视图扭曲型纸币识别方法.首先利用灰度梯度共生矩阵、Haishoku算法和圆形LBP分别获得纹理风格、色谱风格和纹理,这些特征从不同的角度描述了局部纸币图像,然后通过VGG-16、ResN...     

自适应残差图像的分数阶全变分去噪算法

目的 全变分（TV）去噪模型具有较好的去噪效果,但对于图像的弱边缘和纹理细节的保持不够理想。自适应分数阶全变分（AFTV）模型根据图像局部信息,区分图像的纹理区域和非纹理区域,自适应计算投影算法中的软阈值,可较好地保持图像的弱边缘和纹理细节,但该方法当噪声增大时“阶梯”效应比较明显,弱边缘和纹理细节保持效果不够理想。针对该问题,提出一种改进的分数阶全变分去噪算法。方法 该算法在计算残差图像时,用分数阶全变分模型替代整数一阶全变分模型,并根据较精确的残差图像的局部方差区分图像纹理区域和平坦区域,使保真项参数的自适应选取更加合理,提高了算法的去噪性能。结果 针对3种不同类型的噪声图像,将本文模型与TV模型和AFTV模型进行对比实验,并采用峰值信噪比（PSNR）和结构相似性（SSIM）评定去噪效果和纹理保持能力。对于高斯噪声图像,本文算法在PSNR方面比TV模型和AFTV模型分别可平均提高2.72 dB和1.38 dB,SSIM分别可平均提高0.047和0.020。对于椒盐噪声图像,本文算法结合中值滤波算法在PSNR和SSIM方面比传统中值滤波算法分别可平均提高1.308 dB和0.011。对于泊松噪声图像,本文算法在PSNR、SSIM方面与AFTV较接近,比TV分别可提高1.59 dB和0.005。结论 通过对添加不同类型的噪声图像进行实验,结果表明提出的算法在去噪性能上与TV和AFTV相比均有较大提高,尤其对于噪声较大的图像效果更为显著,在去噪效率上与AFTV的时间复杂度相当,时耗接近略有降低。且本文算法普适性较好,能有效去除多种典型类型的噪声。     

广义统计区域合并的SAR图像浮筏养殖信息提取

目的 海水浮筏养殖是海域使用动态监测中的重要类型,合成孔径雷达（SAR）卫星遥感影像可以克服海洋气象环境的影响,有效反映浮筏养殖区域。由于浮筏养殖信息受乘性相干斑噪声污染严重,为了降低噪声敏感性,改进得到广义局部二值模式（GLBP）,进而将其用于改进广义统计区域合并算法（GSRM）,构建以GLBP_GSRM为核心的多特征集成模型,得到更具纹理一致性的超像素,实现浮筏养殖信息精确提取。方法 根据SAR数据的乘性噪声特性改进局部二值模式算子得到GLBP算子,将其加入GSRM的合并准则中,结合纹理信息的超像素分割能得到更具纹理一致性的超像素,有效抑制相干斑噪声。进而利用非下采样轮廓波变换得到轮廓信息丰富数据特征,使用FCS（fuzzy compactness and separation）算法聚类实现浮筏养殖信息的无监督提取。结果 实验选取辽宁省长海县邻近海域作为研究区域,针对C波段的Radarsat-2 SAR和X波段的TerraSAR图像,分别比较同一图像不同区域和不同图像同一区域的提取结果,结合实地现场调查结果表明所提模型对不同类型SAR图像均能精确无监督地提取浮筏养殖信息,分类精度均高于85%,明显优于经典无监督算法,验证模型的有效性。结论 所提模型充分集成纹理特征、空间特征和轮廓特征,有效解决相干斑噪声干扰信息提取的问题,针对不同类型SAR遥感图像,均能在复杂的海洋背景中实现有效地无监督浮筏养殖信息提取,提高海水养殖自动监测准确度。     

Image smog restoration using oblique gradient profile prior and energy minimization

Removing the smog from digital images is a challenging pre-processing tool in various imaging systems. Therefore, many smog removal (i.e., desmogging) models are proposed so far to remove the effect of smog from images. The desmogging models are based upon a physical model, it means it requires efficient estimation of transmission map and atmospheric veil from a single smoggy image. Therefore, many prior based restoration models are proposed in the literature to estimate the transmission map and an atmospheric veil. However, these models utilized computationally extensive minimization of an energy function. Also, the existing restoration models suffer from various issues such as distortion of texture, edges, and colors. Therefore, in this paper, a convolutional neural network (CNN) is used to estimate the physical attributes of smoggy images. Oblique gradient channel prior (OGCP) is utilized to restore the smoggy images. Initially, a dataset of smoggy and sunny images are obtained. Thereafter, we have trained CNN to estimate the smog gradient from smoggy images. Finally, based upon the computed smog gradient, OGCP is utilized to restore the still smoggy images. Performance analyses reveal that the proposed CNN-OGCP based desmogging model outperforms the existing desmogging models in terms of various performance metrics.     

Manual/automatic colorization for three-dimensional geometric models utilizing laser reflectivity

While laser scanners can produce a high-precision 3D shape of a real object, appearance information of the object has to be captured by an image sensor, such as a digital camera. This paper proposes a novel and simple technique for colorizing 3D geometric models based on laser reflectivity. Laser scanners capture the range data of a target object from the sensors. Simultaneously, the power of the reflected laser is obtained as a by-product of the range data. The reflectance image, which is a collection of laser reflectance depicted as a grayscale image, contains rich appearance information about the target object. The proposed technique is an alternative to texture mapping, which has been widely used to realize photo-realistic 3D modeling but requires strict alignment between range data and texture images. The proposed technique first colorizes a reflectance image based on the similarity of color and reflectance images. Then the appearance information (color and texture information) is added to a 3D model by transferring the color in the colorized reflectance image to the corresponding range image. Some experiments and comparisons between texture mapping and the proposed technique demonstrate the validity of the proposed technique.     

基于风格迁移纹理合成与识别的构造式信息隐藏

传统的信息隐藏算法大都通过修改载体达到隐藏秘密信息的目的,但不可避免地会在载体数据中留下修改痕迹,故常难以抵抗隐写分析技术的检测,为此无载体信息隐藏应运而生.无载体信息隐藏并非不使用载体,而是不对载体数据进行修改.为了提高无载体信息隐藏算法的隐藏容量和鲁棒性,提出了一种基于风格迁移纹理合成与识别的构造式信息隐藏算法.该算法首先选取不同类别的自然图像和纹理图像分别建立内容图像库和纹理风格图像库,并根据内容图像库中自然图像的类别构建二进制码的映射字典;其次为了接收方能够从含密图像中提取出秘密信息,需要构建带标签的纹理图像库,并将其作为训练集输入到卷积神经网络中,通过迭代训练获得纹理图像识别模型.在秘密信息隐藏时,根据秘密信息片段选择对应类别的自然图像,并按照一定的顺序组合成含密拼接图像,随后从纹理图像库中随机选择一张纹理图像,通过风格迁移的方法将含密拼接图像转换成含密纹理图像,从而完成秘密信息隐藏过程.在信息提取过程中,通过纹理图像识别模型可准确识别出含密纹理图像原本对应的图像类别,再对照映射字典即可提取出秘密信息.实验结果表明,所提算法生成的含密纹理图像具有良好的视觉效果,秘密信息隐藏容...     

View-based recognition of real-world textures

A new method for recognizing 3D textured surfaces is proposed. Textures are modeled with multiple histograms of micro-textons, instead of more macroscopic textons used in earlier studies. The micro-textons are extracted with the recently proposed multiresolution local binary pattern operator. Our approach has many advantages compared to the earlier approaches and provides the leading performance in the classification of Columbia-Utrecht database textures imaged under different viewpoints and illumination directions. It also provides very promising results in the classification of outdoor scene images. An approach for learning appearance models for view-based texture recognition using self-organization of feature distributions is also proposed. The method performs well in experiments. It can be used for quickly selecting model histograms and rejecting outliers, thus providing an efficient tool for vision system training even when the feature data has a large variability.     

结合纹理结构的分数阶TV模型的图像修复

目的 TV（total variation）模型在图像修复时易导致图像中具有弱导数性质的纹理和边缘细节等信息变得模糊,为了克服该缺陷,分数阶微分被引入到TV模型中,但传统的分数阶TV模型对弱边缘和弱纹理等细节信息的保持仍不够理想,并且没有充分利用图像已知区域的先验信息,修复精度仍有待提高。方法 针对该问题,提出结合纹理结构信息和分数阶TV模型的图像修复算法。改进的模型在分数阶TV模型求解时,在梯度计算过程中增加了一个极小值,克服了正则项和数据项在零点处的不可微,从而增加了模型的稳定性。再则改进的模型根据图像已知区域的先验信息确定待修复区域的纹理方向,从而更好地保持了图像中的纹理细节和弱边缘信息。结果 将本文算法与3种修复效果较好的算法进行对比,采用客观评价指标：均方差（MSE）、峰值信噪比（PSNR）和差值图像进行评价,实验结果表明本文算法在不同的纹理图像修复中均取得较好的效果,如对标准图像库中的Barbara和Lena图像以及岩石图像进行修复后,与原始TV模型相比,它们的峰值信噪比分别提高5.94%、8.07%和3.85%,灰度均方差分别降低48.66%、65.89%和35%;与分数阶TV模型相比,它们的峰值信噪比分别提高4.17%、8.59%和1.81%,灰度均方差分别降低37.90%、68.00%和18.68%。结论 提出的模型相对于原始的TV模型和分数阶TV模型,均能有效地提高图像修复的精度,适合于包含较多弱纹理和弱边缘信息的图像修复,该模型是TV模型的重要延伸和推广。     

真实感3D重建中的纹理映射技术

精确的纹理映射是体现模型视觉真实感的关键因素。本文在阐述纹理映射技术原理的基础上,探讨了基于3维激光扫描设备进行3D重建过程中,实现具有高度真实感的纹理映射所遇到的实际问题,提出了基于纹理的模型重构和纹理光照连续性重建算法,解决了纹理图像空间不连续、光照不连续等因素对模型真实感的影响,并通过真实数据的实验对算法有效性进行了验证,为大型户外实体的真实感3D重建奠定了技术基础。     

基于多特征融合的深层网络图像语义识别方法

图像是一种用来传达情感的重要工具,人类的情感会因不同的视觉刺激而异。采用了一种基于小数据集的数据扩充方式,并将图像的手工提取的低级特征（颜色特征、纹理特征）和网络自动提取到的高级特征（图像对象类别特征和图像深层情感特征）融合的方法,识别图像的复合情感。最终输出包含图像和对象在内的高级语义描述性短语。在公共数据集IAPS和GAPED上进行了实验,并与传统手工提取方法和VGG16、Fine-tune Alexnet两种已有模型进行了比较,该方法在测试性能上优于其他的识别方法,情感识别准确率能达到66.54%。     

多水平外区抑制的轮廓检测

提取自然图像中的物体轮廓是机器视觉研究的重要问题,主要困难在于自然图像中的纹理性边缘严重干扰了物体轮廓的提取。研究表明视皮层方位选择性神经元的非经典感受野机制使得人类视觉系统在处理自然图像时不仅能够抑制纹理性边缘,而且能够增强物体的轮廓。基于此人们提出多种仿生轮廓检测算法,但算法中被称为抑制水平的参量在取值较高时会漏检部分轮廓,而在其取值较低时又会引入过多的纹理性边缘。针对这一问题,提出多水平外区抑制轮廓检测算法,通过整合各级单水平外区抑制的检测信息,有效抑制了纹理性边缘和降低了漏检轮廓的可能性。实验结果表明,相对于传统算法,新算法在轮廓检测性能上提高了10%左右,并具有更好的稳健性。     

Unsupervised detection and localization of structural textures using projection profiles

The main goal of existing approaches for structural texture analysis has been the identification of repeating texture primitives and their placement patterns in images containing a single type of texture. We describe a novel unsupervised method for simultaneous detection and localization of multiple structural texture areas along with estimates of their orientations and scales in real images. First, multi-scale isotropic filters are used to enhance the potential texton locations. Then, regularity of the textons is quantified in terms of the periodicity of projection profiles of filter responses within sliding windows at multiple orientations. Next, a regularity index is computed for each pixel as the maximum regularity score together with its orientation and scale. Finally, thresholding of this regularity index produces accurate localization of structural textures in images containing different kinds of textures as well as non-textured areas. Experiments using three different data sets show the effectiveness of the proposed method in complex scenes.     

基于眼动数据的分类视觉注意模型

视觉注意是人类视觉系统中的重要部分,现有的视觉注意模型大多强调基于自底向上的注意,较少考虑自顶向下的语义,也鲜有针对不同类别图像的特定注意模型。眼动追踪技术可以客观、准确地捕捉到被试的注意焦点,但在视觉注意模型中的应用还比较少见。因此,提出了一种自底向上和自顶向下注意相结合的分类视觉注意模型CMVA,该模型针对不同类别的图像,在眼动数据的基础上训练分类视觉注意模型来进行视觉显著性预测。实验结果表明:与现有的其它8个视觉注意模型相比,该模型的性能最优。     

Chinese text location under complex background using Gabor filter and SVM

For the Chinese text location under complex background, this paper presents a novel method by combining Gabor filter and support vector machine (SVM). It bases on such a fact that Chinese characters are composed of four kinds of strokes. By extracting four kinds of stroke features with Gabor filters, Chinese text location problem can be transformed into a texture classification one, which can use SVM classifier for the purpose. So, the proposed method is composed of two phases. First, Gabor filters with different scales and orientations are employed to obtain four texture images representing the stokes of Chinese text in horizontal line, top-down vertical line, left-downward slope line and short pausing stroke directions. Then, the text regions and background regions in four texture images are used to train four SVM classifiers to distinguish the texture in four directions, by integrating an SVM classification network to obtain the final classification results, according to the sum of the weights to determine whether the block is the text region. Some experiments are conducted on a large amount of typical images with different texts and different fonts. Compared with some existing methods, the proposed approach achieves better results for Chinese text location.     

Automatic registration of laser reflectance and colour intensity images for 3D reconstruction

The objective of the work presented in this paper is to generate complete, high-resolution models of real world scenes from passive intensity images and active range sensors. In previous work, an automatic method has been developed in order to compute 3D models of real world scenes from laser range data. The aim of this project is to improve these existing models by fusing range and intensity data. The paper presents different techniques in order to find correspondences between the different sets of data. Based on these control points, a robust camera calibration is computed with a minimal user intervention in order to avoid the fastidious point and click phase that is still necessary in many systems. The intensity images are then re-projected into the laser coordinate frame to produce an image that combines the laser reflectance and the available video intensity images into a colour texture map.