应用多方向光源分割带钢表面缺陷

光源的照明方式和安装角度对采集到的图像质量有很大的影响,这种不同会导致同一幅缺陷图像产生不同的纹理效果。目前的采集系统一直将光源的影响看作负面因素,事实上如果将不同方向光源对带钢缺陷图像信息的影响用于分割,能够获得更全面、准确的图像信息,因为光源序列的分割方法比单光源包含了更多的缺陷特性。首先采集不同方向光源照射下的图像序列,再提取图像最大强度值位置对应的光源倾角方向作为特征,最后在特征空间运用线性判别函数得到分割结果。实验结果表明提出的方法能获取更高对比度的缺陷图像,正确地将缺陷从背景图像中分割出来。     

Colour segmentation and highlight detection on a 1-D feature space

Specularly reflecting surfaces often corrupt a real scene and degrade system performance. In this paper, we present an algorithm for colour segmentation as well as highlight detection. This algorithm models the human colour vision perception with the physical properties of sensors, illumination and surface reflectances. For image to be dependent only on the body reflectance, the reflection due to illumination, shading and highlights should be discounted. The dichromatic reflection model which describes the colour of the reflected light as a linear combination of the colour of the light due to surface reflection (highlights) and body reflection (object colour) is used. The input image data is first mapped from device coordinates onto the CIE 1931 xy chromaticity diagram where colour clustering occurs. Since the feature space is 3-D, colour clustering is a computationally expensive process. A more efficient method is the dimensionality reduction of the feature space. Using information from the xy chromaticity diagram, the estimated colour clusters are then projected onto a line for 1-D thresholding. The error of projection is minimized by the Fisher's linear discriminant method. A program recognizing nine colours on a 1024 × 1024 image is presented. Colour segmentation of 99% accuracy within 25 s is also achieved.     

一种基于复杂背景下的昆虫彩色图像分割方法

根据复杂背景下昆虫彩色图像的特点,采用了一种融合颜色和空间信息的JSEG分割方法.首先对图像进行颜色量化,然后使用区域增长法合并较小区域从而实现图像分割.在实验中,利用JSEG分割方法分别对原图像和加白噪声后的图像进行分割,结果表明,JSEG算法对昆虫图像中的噪声不敏感,可以高效地实现复杂背景下昆虫彩色图像的分割.     

偏置场下光栅图像的目标轮廓特征点检测方法

文章目标是解决有偏场环境下带有光栅图像的目标轮廓特征点检测问题。针对目标轮廓特征检测中存在的有偏光照环境和光栅模式,提出了一个两步解决方案。首先采用一种新的基于有偏场估计的图像模糊聚类迭代算法,对原灰度图像进行分割;接着,利用Harris特征检测器提取分割后目标图像的候选特征点,并在Harris特征检测算法中提出了基于特征响应函数直方图的罚值选择方法。实验结果表明,在光栅纹理和偏置场并存情况下,该文提出的方法优于传统Harris角检测器,解决了传统Harris角检测在该特定环境下所面临的精度下降问题。文章提出的算法可用于偏置场环境下光栅图像目标形状分析。     

超球流形约束下的3DMM分步全局优化

通过综合运用人脸空间的超球流形约束、基于梯度的启发式全局优化、光照的球面谐波描述以及凸包可见点集的直接消隐方法,提出一种三维可形变模型的图像匹配方法.首先通过形状超球流形约束下的全局优化算法求解摄像机参数和形状参数,然后使用以上参数和凸包点集的直接消隐方法确定物像点对应关系,最后根据物像点对应关系由反射率超球流形约束下的全局优化算法求解光照参数和反射率参数.定量的对比实验结果表明,该方法无需借助分区域拟合、人为估计参数值、层次匹配策略或复杂的特征组合,即可由单幅图像恢复三维可形变模型(3DMM)的全部参数.     

基于同态滤波抑制光照变化的视频分割算法

针对光照变化较大时基于颜色差分直方图的视频分割算法不能有效更新背景,导致后续输入图像前景目标分割失效的问题,提出一种基于同态滤波抑制光照变化的视频分割算法。首先利用同态滤波算法对输入和背景图像(RGB)在HSV空间中亮度分量进行同参矫正,然后将矫正后图像转换到RGB空间,最后利用颜色差分直方图算法进行视频分割。文中算法有效解决颜色差分直方图算法无法将受光照变化影响较大区域更新到背景中的问题,实现背景的实时有效更新,保证稳健地从后续输入图像分割前景目标。3组视频仿真结果表明该算法与高斯混合和Codebook算法相比具有运算速度快,对光照变化鲁棒的优点。     

Unsupervised building detection in complex urban environments from multispectral satellite imagery

A generic algorithm is presented for automatic extraction of buildings and roads from complex urban environments in high-resolution satellite images where the extraction of both object types at the same time enhances the performance. The proposed approach exploits spectral properties in conjunction with spatial properties, both of which actually provide complementary information to each other. First, a high-resolution pansharpened colour image is obtained by merging the high-resolution panchromatic (PAN) and the low-resolution multispectral images yielding a colour image at the resolution of the PAN band. Natural and man-made regions are classified and segmented by the Normalized Difference Vegetation Index (NDVI). Shadow regions are detected by the chromaticity to intensity ratio in the YIQ colour space. After the classification of the vegetation and the shadow areas, the rest of the image consists of man-made areas only. The man-made areas are partitioned by mean shift segmentation where some resulting segments are irrelevant to buildings in terms of shape. These artefacts are eliminated in two steps: First, each segment is thinned using morphological operations and its length is compared to a threshold which is determined according to the empirical length of the buildings. As a result, long segments which most probably represent roads are masked out. Second, the erroneous thin artefacts which are classified by principal component analysis (PCA) are removed. In parallel to PCA, small artefacts are wiped out based on morphological processes as well. The resultant man-made mask image is overlaid on the ground-truth image, where the buildings are previously labelled, for the accuracy assessment of the methodology. The method is applied to Quickbird images (2.4 m multispectral R, G, B, near-infrared (NIR) bands and 0.6 m PAN band) of eight different urban regions, each of which includes different properties of surface objects. The images are extending from simple to complex urban area. The simple image type includes a regular urban area with low density and regular building pattern. The complex image type involves almost all kinds of challenges such as small and large buildings, regions with bare soil, vegetation areas, shadows and so on. Although the performance of the algorithm slightly changes for various urban complexity levels, it performs well for all types of urban areas.     

基于色差空间的并行彩色插值算法及其FPGA实现

针对各种彩色插值算法存在的缺陷即算法的硬件可实现性和图像恢复后的质量之间的矛盾,提出了一种基于色差空间的并行彩色插值算法.该算法以5×5菱形领域内像素点的色差分量几乎相同为前提,利用当前像素的已知颜色分量和不同颜色分量之间的关联性插值得到未知的颜色分量.同时考虑到FPGA强大的并行处理能力,采用FPGA来实现该算法.MATLAB仿真和时序分析验证了算法的可靠性和高效性,使以较少的硬件资源达到较好的插值效果成为了可能.     

无需先验知识的红外显著性目标分割评价准则

为了在无先验知识的情况下,客观评价红外图像中显著性目标分割效果,文中提出一种无需先验知识的红外目标分割评价准则。针对红外图像中显著目标的特性,建立3种评价指标:局部视觉亮度差指标、全局视觉显著性指标和亮度波动性指标,这3种指标分别对应于分割前景局部区域的视觉亮度对比度、分割前景在全局背景下的视觉显著程度和分割前景内部亮度的一致性程度。综合3种指标,建立红外目标分割的评分准则。实验证明文中准则的评价结果能较好地符合主观人眼视觉感知与客观实际,适用于无先验知识的红外目标分割评价。     

高斯尺度空间下估计背景的自适应阈值分割算法

为有效分割非均匀光照图像,提出一种在高斯尺度空间下估计背景的自适应阈值分割算法. 首先,利用二维高斯函数对待处理图像进行卷积操作来构建一个高斯尺度空间,在此空间下进行背景估计,并采用背景差法来消除非均匀光照干扰,从而提取出目标图像;然后,采用 矫正进行增强处理以突出较暗目标信息;最后,经强调谷底的最大类间方差法进行全局分割得到最终结果. 为验证算法的有效性,对非均匀光照条件下文本图像以及非文本图像进行了测试,并与基于偏移场的模糊C均值方法、灰度波动变换自适应阈值分割算法和自适应最小误差阈值分割算法,在错误分割率和运行时间上进行了对比. 实验结果表明,对比以上三种方法,该算法的分割结果更为理想.     

Morphological segmentation and classification of marble textures at macroscopical scale

This paper presents a methodology mainly based on mathematical morphology to segment and classify colour images of polished samples of marbles at the macroscopic scale. The distinct textural regions are segmented through a watershed-based procedure, and the over-segmentation problem is surpassed with the merging of adjacent regions according to criteria based on the analysis of alternative gradients obtained in grey and colour images. The classification of the elementary textural units in three classes (vein, background and transition) is performed with a morphological partitioning method of feature space. The evaluation and analyses of the methodology and alternatives presented are performed on a set of polished Portuguese marbles.     

基于图论的彩色图像快速分割方法研究

基于图论的图像分割方法作为一种全局的分割方法,当图像的信息量增大时,问题求解将非常耗时.提出一种基于图论的彩色图像快速分割方法,该方法首先用区域生长法将彩色图像划分为内部相似的一些区域,再用最小支撑树MST(Minimum spanning tree)方法在这些区域之间进行分割,产生最终的分割图像.以彩色图像作为研究对象,实验结果表明,相对于传统的MST图论分割方法,该方法在取得较好分割效果的同时,提高了分割速度.     

A new and robust method for character segmentation and recognition in license plate images

This paper provides a new and fast method for segmentation and recognition of characters in license plate images. For this purpose, various methods have been proposed in literature. However, most of them suffer from: sensitivity to non-uniform illumination distribution, existence of shade in license plate, license plate color and the need for receiving an exact image of the license plate. In the proposed algorithm, non-uniform illumination and noise are reduced by a Gaussian lowpass filter and also by an innovational Laplacian-like transform and characters are segmented by a set of indigenous and relative features. To be prepared for recognition, the segmented characters are normalized by a local algorithm. Two feed-forward neural networks with back-propagation learning method are employed for character recognition. The principal component analysis (PCA) is used to decrease input data and, consequently, computational complexity. The proposed algorithm does not necessarily need an exact plate image and can receive a band from the vehicle original image as an input, which includes the plate. Our proposed method is completely robust to the disturbances such as non-uniform brightness distribution on the various positions of a license plate image and the plate color. In order to evaluate our algorithm, we applied it on a database including 120 vehicle images with different backgrounds, plate colors, brightness distributions, distances and viewing angles. The results confirm the robustness of the proposed method against severe imaging conditions.     

基于均值偏移的户外图像快速分割算法

提出一种改进的基于均值偏移的户外图像快速分割算法,使其能够满足基于视觉的户外移动机器人导航对图像处理的快速性要求。阐述了均值偏移算法的基本原理,给出了图像快速分割的具体实现方法:对图像进行尺度空间变换,用均值偏移算法在选定的颜色空间中对图像进行分割。通过对多种户外环境下采集到的图像进行实验,结果表明该算法对户外彩色图像快速分割取得了良好的效果。     

机车受电弓滑板磨耗的图像处理算法研究

将图像处理算法引入机车受电弓滑板的磨耗检测中,提出一种检测受电弓滑板实际厚度的测量算法。由于直接对图像进行边缘检测易受噪声、光照等因素影响,通过Hough变换对图像进行水平校正,由模糊聚类算法进行图像分割以去除光照不均及噪声的干扰,对分割后图像采用Canny算子精确提取滑板的边缘信息。考虑提取边缘的不连续性,引入结合数学形态学的边缘生长方法实现不连续边缘的连接,通过图像标定计算出实际滑板磨耗厚度。     

A modified fuzzy C-means image segmentation algorithm for use with uneven illumination patterns

A novel fuzzy C-mean (FCM) algorithm is proposed for use when active or structured light patterns are projected onto a scene. The underlying inhomogeneous illumination intensity due to the point source nature of the projection, surface orientation and curvature has been estimated and its effect on the object segmentation minimized. Firstly, we modified the recursive FCM algorithm to include biased illumination field estimation. New clustering center and fuzzy clustering functions resulted based on the intensity and average intensity of a pixel neighborhood based object function. Finally, a dilation operator was used on the initial segmented image for further refinement. Experimental results showed the proposed method was effective for segmenting images illuminated by patterns containing underlying biased intensity fields. A higher accuracy was obtained than for traditional FCM and thresholding techniques.     

Urban road extraction from high-resolution optical satellite images

In recent years, many approaches have been exploited for automatic urban road extraction. Most of these approaches are based on edge and line detecting algorithms. In this paper, a new integrated system for automatic extraction of main roads in high-resolution optical satellite images is present. Firstly, a multi-scale greylevel morphological cleaning algorithm is proposed to reduce the grey deviation of the road regions. Secondly, based on the greylevel difference between road surfaces and environmental objects, a colour high-resolution satellite image is segmented into a simplified imagemap by using the mean shift algorithm, which consists of three stages. The first stage deals with image filtering, the second stage deals with colour segmentation, and the third stage is proposed to fuse small regions in the segmented image. The mean shift filter algorithm not only smoothes the image, but also preserves abrupt changes (i.e. edges) in the local structure. The mean shift segmentation algorithm is a straightforward extension of the smoothing algorithm, which preserves discontinuity. From the histogram of the simplified imagemap, we can find the potential road surfaces, and use greylevel threshold to convert the segmented image into a binary one. The binary image is processed by using binary mathematical morphological closing and opening to remove small objects and to open the connected street blocks. We use a contour tracing algorithm to remove holes in street-block regions and to detect the street blocks' contours. In this research we found that many street blocks' contours were preserved perfectly, except for some of them which were depressed. Finally, we utilize the convex hull algorithm to smooth the street blocks' zigzag edges and to close the gaps in some street blocks, and then, we get the road edges. The integrated system for road network extraction is tested on the red band of an IKONOS multispectral image; all algorithms in this study are developed in C++ under Windows XP operating system. Results of the road network extraction are presented to illustrate the validation of the extracting strategy and the corresponding algorithms in this research, and future prospects are exposed.     

红外图像分割算法分析

根据红外图像的特点,提出了一种测量目标红外辐射面积的算法。采用二维otsu算法和变闽值统计平均算法的目标图像进行分割算法,采用均值算法和中值算法去除图像噪声,采用二维otsu算法初二值化去噪后图像,在以此阂值为基准变换闽值得到一组二值化后图像,统计平均二值化后的图像,设定阀值得到最终二值化结果,在结合原图像得到分割结果。最后通过与一维和二维otsu图像分割算法试验比较,验证了此算法的有效性。     

基于特征距离的阈值法及其在眼科图象分割中的应用

医学图象的识别与分析能够为临床提供定量比的诊断依据,而图象分割是其中最关键的一步。为提高医学图象侵分割效果,提出了一种基于特征距离的阈值分割算法,并将其与颜色特征分类相结合,来对眼科裂隙灯生物显微镜图象上的角膜充血区进行分割,分割结果可用于角膜充血区的定量体分析,另外,该算法中的样本典型值是通过一种三维直方图分块算法来确定的,实验结果表明,该算法可以有效地分割出角膜充血,其分割效果优于欧氏距离阈值法,且分析数据的精度能够达到临床诊断的要求。     

A method of illumination compensation for human face image based on quotient image

Illumination variation is one of the critical factors affecting face recognition rate. A novel approach for human face illumination compensation is presented in this paper. It constructs the nine-dimension face illumination subspace based on quotient image. In addition, with the aim to improve algorithm efficiency, a half-face illumination image is proposed and the low-dimension training set of the face image under different illumination conditions are obtained by means of PCA and wavelet transform. After processing, two different illumination compensation strategies are given: one is adding light, and the other is removing light. Based on the illumination compensation strategy, we implement the typical illumination sample image synthesis and the standard illumination sample image synthesis on a PCA feature subspace and a wavelet transform subspace, respectively, and the illumination compensation of the gray images and the color images are further realized. Experimental results based on the Yale Face Database B, the Extended Yale Face Database B and the CAS-PEAL Face Database indicate that execution time after compensation is approximately half the time and face recognition rate is improved by 20% compared with that of the original images.