半色调图像纹理特征提取方法

提出基于局部二值化模式和像素相关算子的半色调图像纹理特征提取方法,以实现误差分散类半色调图像的分类。该方法是将误差分散类图像先进行局部二值化模式变换,再以任一像素点为中心,取适当的距离提取八个方向的像素相关值作为图像的特征向量,最后将提取的特征通过BP神经网络进行分类。实验结果表明,提出的算法适用于二值图像的特征提取,能够降低局部二值模式的特征维数,提高时间效率和空间利用率;相对灰度共生矩阵算法提出的算法在计算复杂度、识别精度等性能方面都有所改善。     

基于BEMD和LBP提取特征的纹理分类

对于纹理图像的分类,采用二维经验模式分解将图像分解成一系列的固有模态函数(IMF)和残差,并结合局部二值模式(LBP)对所提取到的各IMF图像和残差图像进行特征提取的方法。为了验证算法的有效性,对自然纹理进行特征提取,并结合支持向量机(SVM)算法对提取的特征向量进行分类,分类精确度达到98%以上。     

自适应加权融合显著性结构张量和LBP的表情识别

针对局部二值模式（Local Binary Pattern，LBP）提取纹理特征时忽略了图像的局部结构信息问题，提出一种自适应加权融合显著性结构张量和LBP的表情识别算法。该算法通过对整幅图片进行显著性区域检测得到全局显著图来消除细小的纹理和噪声。在显著图的基础上进一步提取两种显著性纹理特征，根据每种特征信息熵的贡献度来作为特征向量的加权依据。利用支持向量机（Support Vector Machine，SVM）进行表情图像的分类。实验结果表明，自适应加权融合的两种纹理特征能够较好地描述人脸的特征，有效地提高表情识别率。     

ILBP算子在浓雾天气形势图识别中的应用

纹理是天气形势图的突出特征,有效地从天气形势图提取并表示其纹理是实现雾型实时在线预报的基础。基于此,提出一种改进的局部二值模式算法,通过调整局部二值模式(LBP)算子中二进制多项式的权重,实现其提取特定方向上纹理特征的目标。将江苏地区2010年—2017年500张浓雾天气形势图作为数据集,采用Chi统计法匹配测试数据与基准数据的相似度进行天气分类。实验结果表明,该算法的准确率、虚警率及临界成功指数分别为0.884、0.15和0.76,均优于LBP算法,具有较高的识别准确性与可靠性。     

基于纹理特征和轮廓光流矢量的烟雾识别

为了提高火灾探测的准确率和快速性,提出了基于纹理特征和轮廓光流矢量的烟雾识别算法。一方面为了获得更全面的纹理特征,建立图像金字塔,使用局部二值模式（ LBP）和基于方差的局部二值模式（ LBPV）结合的新方法分别提取金字塔不同层的纹理特征。另一方面是动态纹理特征,由于烟雾运动的湍流特性导致方向具有特定的一致性,改进了对全部可疑区域进行分析的方法,仅对可疑区域轮廓进行光流矢量分析,降低运算量。将静态纹理特征和动态纹理特征输入支持向量机（ SVM ）中进行识别。采用“静—静—动”的新型识别方法,实验结果表明：该算法能够及时准确报警,可靠率高。     

基于形状特征及纹理特征的中药材检索方法

为有效提取中药材图像的特征,提高中药材图像分类准确率并提升检索性能,对中药材图像的梯度方向直方图形状特征和局部二元模式纹理特征进行研究,对2种特征进行维数改进,提出一种基于形状特征和纹理特征的中药材检索方法。使用改进的图像梯度方向直方图和分块局部二元模式进行形状及纹理的特征提取;对提取得到的特征向量进行线性组合;采用一对一方式构造多分类器,使用支持向量机进行分类检索。实验结果表明,组合降维特征提取算法能在中药材图像数据集中取得较好的识别效果。     

用于纹理特征提取的改进的成对旋转不变共生局部二值模式算法

针对用于纹理特征提取的成对旋转不变共生局部二值模式（PRICoLBP）算法计算特征维度大、旋转不变性较差、对光照变化敏感的问题,提出一种融合局部纹理信息的改进PRICoLBP算法。首先,分别最大化和最小化图像像素点的二值序列,得到两个邻域像素点的坐标,由中心像素点坐标和得到的邻域像素点坐标计算出共生点对的坐标;其次,利用完备二值模式（CLBP）算法提取图像的每个像素点的纹理信息。在相同分类器下,对Brodatz、Outex（TC10,TC12）、Outex（TC14）、CUReT和KTH_TIPS数据库的分类实验中,所提算法的识别率比PRICoLBP算法分别提高了0.17、0.24、2.65、2.39和2.04个百分点。实验结果表明,所提算法在处理纹理旋转变化、光照条件多样的图像时具有较好的识别效果。     

一种基于多尺度局部纹理特征和CART决策树的野外火灾火焰图像识别算法

为了消除野外环境中枯草、枯树枝、枯树叶等干扰对象对野外火灾识别的影响,提高火焰识别的准确率,提出一种新的基于Gabor滤波和局部二值模式(LBP)的多尺度局部纹理特征提取方法,并构建Adaboost-SVM火焰图像分类器。利用火焰的颜色特征提取出疑似火焰区域;对疑似火焰区域进行Gabor滤波,再对Gabor滤波后不同尺度下的图像以16×16的像素邻域网格作为采样窗口,采用LBP提取其纹理特征;运用CART决策树对LBP特征向量进行降维,将分类回归树算法(CART)选择出来的特征输入到支持向量机(SVM)训练分类器,进行火灾火焰图像识别。实验结果表明,野外火灾火焰的识别准确率为96%,证明了该算法的有效性。     

改进FCM和LFP相结合的白细胞图像分类

研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率.由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法.应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题.对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法.运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93％.     

基于梯度和局部多值模式的图像纹理特征提取

为了进一步增强局部二值模式的纹理特征表达能力,提出了一种将图像梯度同局部多值模式相结合的纹理特征提取方法.该方法首先计算出图像的梯度幅度和梯度方向,并根据量化的梯度方向对幅度图进行分解,之后利用得到的幅度图对其进行局部多值模式特征的提取,得到一种新的纹理特征,最后将得到的特征进行图像检索实验.实验结果表明,在纹理丰富的检索库上,该方法所提取的纹理特征更加具有通用性,相对传统局部二值模式图像检索方法具有更好的稳健性和更好的检索效果.     

图像隐藏信息与图像噪声分辨研究

针对图像经过信息隐藏与经过噪声干扰具有不同的特性,从图像隐藏信息和加噪的数学原理入手,引入图像直方图和差分直方图的模型,在图像小波分解高频系数差分直方图的数学模型基础上,利用高频系数差分数值的方差对图像是否隐藏信息或被噪声干扰进行分辨,给出了具体的计算判断方法。最后,在标准图像集上进行实验。结果表明,即使在图像直观统计参数基本相同的情况下,该方法也能明显分辨出两种不同的干扰现象,取得良好结果。     

Geometry-based image retrieval in binary image databases

In this paper, a geometry-based image retrieval system is developed for multi-object images. We model both shape and topology of image objects using a structured representation called curvature tree (CT). The hierarchy of the CT reflects the inclusion relationships between the image objects. To facilitate shape-based matching, triangle-area representation (TAR) of each object is stored at the corresponding node in the CT. The similarity between two multi-object images is measured based on the maximum similarity subtree isomorphism (MSSI) between their CTs. For this purpose, we adopt a recursive algorithm to solve the MSSI problem and a very effective dynamic programming algorithm to measure the similarity between the attributed nodes. Our matching scheme agrees with many recent findings in psychology about the human perception of multi-object images. Experiments on a database of 13500 real and synthesized medical images and the MPEG-7 CE-1 database of 1400 shape images have shown the effectiveness of the proposed method.     

Smart image design for large image databases

We propose an active image information system based upon the concept of smart images. A smart image is an image with an associated knowledge structure, consisting of protocols, hot spots, active indexes and attributes. This active image information system enables us to accomplish the objectives of timely delivery and easy accessibility by handling long-duration operations and supporting unitary image information usage. The experimental prototype of the smart image system is described.     

The effectiveness of image features based on fractal image coding for image annotation

Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.     

Analysis of all-in-focus image processing in image restoration

We discuss a new deblurring problems in this paper. Focus measurements play a fundamental role in image processing techniques. Most traditional methods neglect spatial information in the frequency domain. Therefore, this study analyzed image data in the frequency domain to determine the value of spatial information. but instead misleading noise reduction results . We found that the local feature is not always a guide for noise reduction. This finding leads to a new method to measure the image edges in focus deblurring. We employed an all-in-focus measure in the frequency domain, based on the energy level of frequency components. We also used a multi-circle enhancement model to analyze this spatial information to provide a more accurate method for measuring images. We compared our results with those using other methods in similar studies. Findings demonstrate the effectiveness of our new method.     

基于特征匹配的亚像素级全景图像配准算法

为了提高全景图全自动拼接中图像配准的速度和匹配稳健性,提出了一种基于相对距离法去除外点的亚像素级图像配准算法,并给出了分析和实验结果,亚像素级像素定位误差在0.01~0.1之内。在对12组图像匹配的实验结果表明,该匹配算法的匹配正确率达到100%,且匹配的时间小于目前通用的RANSAC匹配算法。     

Probability-based reversible image authentication scheme for image demosaicking

In this paper, we propose a novel image authentication scheme to detect the tampered areas for image demosaicking with the reversibility preserving property. Image demosaicking is the process of reconstructing an RGB color image from the sampled data acquired by the digital camera that applies a color filter array to a single sensor. In the proposed scheme, the authentication data is embedded into the rebuilt components of the demosaicked pixels.From the results, it is shown that good image qualities of the embedded images are obtained by using the proposed scheme. When the illegal users modified the contents of the embedded images, the tampered areas in the modified images can be clearly detected by using the proposed scheme. The demosaicked images can be losslessly recovered if no modifications are done on the embedded images. The proposed authentication codes embedding process can be implemented by hardware in single sensor digital camera. Furthermore, the proposed scheme can be extended to protect the image integrity for cloud computing environments.     

基于图像增强的井下图像拼接

为了通过图像采集技术实时监控煤矿井下生产情况, 提出了基于图像增强的井下图像拼接算法。利用局部双边滤波算法对图像进行增强,在此基础上再利用近似的Hessian矩阵和框状滤波确定特征点的位置,然后,计算特征点的描述子向量,采用最近距离比次近距离的匹配算法将特征点配对,最后利用特征点对计算得出变换矩阵,采用线性渐变融合方法进行图像融合。通过图像增强前后特征点数量对比实验验证了增强算法的有效性,并证明了该算法显著提高了SURF（Speeded Up Robust Features）算法的拼接效率,有利于提高匹配的准确性和拼接的快速性。     

Attention-driven image interpretation with application to image retrieval

Visual attention, a selective procedure of human's early vision, plays a very important role for humans to understand a scene by intuitively emphasizing some focused regions/objects. Being aware of this, we propose an attention-driven image interpretation method that pops out visual attentive objects from an image iteratively by maximizing a global attention function. In this method, an image can be interpreted as containing several perceptually attended objects as well as a background, where each object has an attention value. The attention values of attentive objectives are then mapped to importance factors so as to facilitate the subsequent image retrieval. An attention-driven matching algorithm is proposed in this paper based on a retrieval strategy emphasizing attended objects. Experiments on 7376 Hemera color images annotated by keywords show that the retrieval results from our attention-driven approach compare favorably with conventional methods, especially when the important objects are seriously concealed by the irrelevant background.     

基于内容的图像检索技术与医学图像检索

在分析基于内容的图像检索技术特点的基础上，提出了4种基于内容的图像检索方法，并对每种方法的实现特别是特征抽取进行了一定的研究。根据医学图像的使用特点，对基于内容的医学图像检索技术进行了初步的研究；对医学图像特征的抽取，应将重点放在形状特征和纹理特征的抽取上；同时，对医学图像进行检索，还可以使用颜色空间分布特征，来进一步进行相似匹配。