基于区域分割的水下目标实时识别系统

提出了一种基于最优阈值分割算法的水下目标自动实时识别系统。该系统首先运用去噪、图像均衡等方法对实时摄取的水下图像进行预处理。然后运用基于遗传算法优化的 Otsu(即大津方法)最优阈值分割算法对所得图像进行区域分割并提取图像的特征向量。最后采用 BP 神经网络对提取的特征向量进行自动分类从而最终确定了水下目标的类型。水槽仿真试验表明该方法能够在恶劣的环境下自动地检测水下目标,而且该方法具有较强的抗光线干扰能力和较高的准确度。     

图像混合噪声的一种组合滤波消除方法

提出了一种基于高斯拉普拉斯边缘检测的含高斯噪声和脉冲噪声的图像组合滤波去噪方法,即首先对含有混合噪声的图像进行中值滤波,再用高斯拉普拉斯边缘检测方法检测出图像的边缘,得到边缘图像;然后利用自适应Wiener滤波对中值滤波后得到的图像进一步滤波去噪,最后将边缘图像嵌入经Wiener滤波得到的平滑图像中。此种方法不但能够有效去除含高斯噪声和脉冲噪声的图像中的噪声,而且可以保持图像的边缘信息,提高了图像的去噪效果和清晰度。     

A data mining approach to face detection

In this paper, we propose a novel face detection method based on the MAFIA algorithm. Our proposed method consists of two phases, namely, training and detection. In the training phase, we first apply Sobel's edge detection operator, morphological operator, and thresholding to each training image, and transform it into an edge image. Next, we use the MAFIA algorithm to mine the maximal frequent patterns from those edge images and obtain the positive feature pattern. Similarly, we can obtain the negative feature pattern from the complements of edge images. Based on the feature patterns mined, we construct a face detector to prune non-face candidates. In the detection phase, we apply a sliding window to the testing image in different scales. For each sliding window, if the slide window passes the face detector, it is considered as a human face. The proposed method can automatically find the feature patterns that capture most of facial features. By using the feature patterns to construct a face detector, the proposed method is robust to races, illumination, and facial expressions. The experimental results show that the proposed method has outstanding performance in the MIT-CMU dataset and comparable performance in the BioID dataset in terms of false positive and detection rate.     

一种新的基于小波变换的边缘检测算法

应用小波变换理论对图像进行平滑降噪处理,对降噪图像进行多级小波分解,从而获取多分辨率图像。对小波分解的各级小波系数求其局部模极大值,从而得到不同分辨率下的图像边缘,合并不同分辨率下的图像边缘得到一个组合边缘,细化图像边缘。实验证明。这种方法对有噪声污染的图像进行边缘检测效果好于LoG、Sobel、Canny等经典的边缘检测方法。     

一种改进的LoG图像边缘检测方法

对LoG算子边缘检测算法的性能进行分析,指出LoG算子在实际应用中的不足。针对LoG算子的缺点。通过实验数据得出图像灰度共生矩阵的熵与高斯空间系数的关系。实现使用LoG算子对图像进行检测边缘时能根据具体的图像的熵值自动获取适合该图像的高斯空间系数的值。因此。提出的改进算法既能有效的抑制噪声又能较精确的定位边缘。     

结合区域和边界信息的图像显著度检测

目的 图像显著度检测是许多图像应用的核心问题,为了能够在复杂背景下准确提取图像中前景对象的位置和尺度信息,提出一种结合区域和边界信息的图像显著度检测方法。方法 对于图像区域信息,提出一种基于图像等照度线的方法检测显著区域信息。该方法针对不同的特征(颜色、亮度和方向)提出统一的计算方法,使得不同特征下获得的显著信息具有一致的度量标准,从而方便后续多特征显著度图的融合。对于图像边界信息,采用一种结合多尺度Beltrami过滤器的全局方法检测显著边界信息。多尺度Beltrami过滤器可以显著增强图像中的边界信息。利用全局显著度检测方法对经过过滤器处理过的图像可以准确地获取图像中最为显著的边界信息。最后,由于区域和边界分别代表图像中的不同类型信息,可以直接采用线性融合方式构建最终的图像显著度图。结果 与其他9种流行图像显著度检测算法相比,本文算法无论在简单还是复杂背景下均能够较为准确地检测出图像中的显著度信息(Precision、Recall、F测试中获得的平均值为0.5905,0.6554,0.7470的最高测试结果)。结论 提出一种结合区域和边界信息的图像显著度检测算法,通过区域和边界信息相结合的方式实现图像中显著对象的准确检测。实验结果表明本文算法具有良好的适用性和鲁棒性,为图像中复杂背景下对象检测打下坚实基础。     

基于空频域联合闭值分割的轮廓检测方法

传统的边缘检测算子仅在空域上对梯度图像进行阈值分割来计算二值边缘图像,当应用在自然场景图像中时,检测结果中往往含有大量的干扰边缘。为了消除干扰边缘,提高传统边缘算子的轮廓检测性能,提出了基于空频域联合阈值分割的轮廓检测方法:首先对梯度图像进行频域阈值分割消除干扰边缘,然后进行空域阈值分割得到最终的二值边缘图。结合Canny算子,利用自然场景图像对该方法进行了性能评估,结果表明,该方法大大减少了干扰边缘,有效提高了Canny算子在复杂自然场景图像中的轮廓检测性能。     

Watershed-based hierarchical SAR image segmentation

Watershed transformation is a powerful image segmentation tool recently developed in mathematical morphology. In order to segment images initially oversegmented by watershed transformation, two approaches are considered: one is the thresholding of the gradient image proposed by us which is capable of keeping more salient image contours; the other is the well known centroid linkage region growing algorithm which merges regions with certain statistical similarities. By choosing suitable thresholds in the two approaches, hierarchical image segmentation algorithms can be constructed. A Ratio of Averages (ROA) edge detector is proposed to replace the morphological edge detectors prior to watershed transformation when applied to Synthetic Aperture Radar (SAR) images. Applications to SAR agricultural image segmentation with these hierarchical segmentation algorithms are presented. It is demonstrated that the algorithms are efficient in the segmentation of the SARimages and appropriate for land use applications when the land cover is made up of individual plots.     

遗传算法优化的形态学边缘检测算子

图像边缘检测通常是以类似于素描图的图像表达出物体的要素和特征,其任务是使图像边缘准确定位和抑制噪声。在传统形态学算子基础上提出一种遗传算法优化的形态学Top—Hat算子。实验表明。与传统的边缘检测算法相比,该算法不仅具有较强的边缘提取能力,而且通过合理选择结构元素能明显降低噪声对检测结果的影响,准确检测出图像边缘。     

Image segmentation using Atanassov’s intuitionistic fuzzy sets

The problem of segmentation in spite of all the work over the last decades, is still an important research field and also a critical preprocessing step for image processing, mostly due to the fact that finding a global optimal threshold that works well for all kind of images is indeed a very difficult task that, probably, will never be accomplished.During the past years, fuzzy logic theory has been successfully applied to image thresholding. In this paper we describe a thresholding technique using Atanassov’s intuitionistic fuzzy sets (A-IFSs). This approach uses Atanassov’s intuitionistic index values for representing the hesitance of the expert in determining whether the pixel belongs to the background or that it belongs to the object. First, we describe the general framework of this approach to bi-level thresholding. Then we present its natural extension to multilevel thresholding. This multilevel threshold methodology segments the image into several distinct regions which correspond to a background and several objects.Segmentation experimental results and comparison with Otsu’s multilevel thresholding algorithm for the calculation of two and three thresholds are presented.     

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.     

一种基于边缘轮廓线的LoG角点检测

角点是数字图像中目标的重要局部特征,提供了目标的低层次视觉特性。将Laplace of Gaussian变换引入到平面曲线,提出了一种基于边缘轮廓的LoG角点检测算子。深入分析LoG变换的几何特征,建立了边缘轮廓曲率和LoG范数间的等价度量关系。角点响应函数被定义为边缘点的LoG变换范数,边缘轮廓上LoG范数的局部极值点被认为是角点。并针对?祝-角点模型和圆周曲线模型,验证了这种定义的合理性。实验结果表明,相比经典角点检测算子,该文算法具有高效、稳定的优点。     

An efficient and accurate approach of circular object detection in color images

Object detection is a critical step of many image recognition systems. In this paper, we discuss the problem of circular shape object detection in still color images. An isotropic edge detector merged with spatial information and region based analysis is employed to extract image edge and obtain accurate gradient information of edge pixels, which assures the high accuracy of the subsequent circle detection. Then three circle parameters are estimated efficiently with only one 2-dimensional accumulator array and one 1-dimensional accumulator array, which greatly reduces the storage requirements and time complexity of our approach. Experimental results show that our method is robust in locating objects with complete or incomplete or concentric circle boundary in real color images without any prior knowledge.     

An image detection technique based on morphological edge detection and background differencing for real-time traffic analysis

The real-time vehicle detection from a traffic scene is the major process in image processing based traffic data collection and analysis techniques. The most common algorithm used for real-time vehicle detection is based on background differencing and thresholding operations. The efficiency of this method of image detection is heavily dependent on the background updating and threshold selection techniques. In this paper, a new background updating and a dynamic threshold selection technique is presented. An alternative image detection technique used in image processing is based on edge detection techniques. However, an edge detector extracts the edges of the objects of a scene irrespective of whether it belongs to the background details or the objects. Therefore, to separate these two, extra information is required. We have developed a new image detection method based on background differencing and edge detection techniques, which separates the objects from their backgrounds and works well under various lighting and weather conditions. This image detection technique together with other techniques for calculating traffic parameters e.g. counting number of vehicles, works in real-time on an 80386-based microcomputer operating at a clock speed of 33 MHz.     

基于零交叉的二维边缘检测算子的计算近似

本文通过对设计算子的一些期望性能的设定，简化了优化问题，并根据简化的信噪比测度代价函数，设计并实现了一种较优的利用拉普拉斯算子的基于零交叉的二维阶跃型边 缘检测算子。该算子具有旋转不变的特性，其支持域有限并且边缘保持平滑。本文在理论上对设计算进行了性能分析并与高斯－拉普拉斯算子进行了比较，实验结果验证了算
算子的设计思想和实现方法     

An edge detection based noise removal algorithm

We present an image denoising method using the edge map of an image. The denoised image is considered as a linear combination of the observed image and its average value, where the coefficients are controlled by a local edge detector. The parameters are set on suitable values related to noise energy computed by the curvature norm of the original image. Implementation can be done in a single iteration and the speed of the process is reasonably high. Noise reduction quality of the introduced method is compared with Wiener and Total Variation based filters for some images. The method appears to be easy, fast and useful for very noisy images. The differences between our method and the patent 6229578 “Edge Detection Based Noise Removal Algorithm” are explained.     

基于修正维纳滤波的小波包变换图像去噪

图像去噪是图像处理中一个非常重要的环节。为了改善降质图像质量,根据Donoho提出的小波阈值去噪算法,分析了维纳滤波原理,提出了一种基于修正维纳滤波的小波包变换图像去噪方法。利用修正维纳滤波对噪声图像进行处理,用处理后的图像计算噪声的标准方差,以此作为小波包的阈值。利用小波包对维纳滤波后的图像进行分解,实现对图像的低频和高频部分分别进行分解,用计算出的阈值对小波包树系数进行软阈值处理。利用小波包逆变换来获取去噪后的图像。结果表明：在噪声方差为0.01时,经该算法去噪后图像的PSNR比小波包自适应阈值去噪后的PSNR高出8.8 dB。该算法不仅能有效地去除加性高斯白噪声,而且能很好地保留边缘信息,极大地改善了图像的视觉质量。     

Automatic optic disk boundary extraction by the use of curvelet transform and deformable variational level set model

Efficient optic disk (OD) localization and segmentation are important tasks in automated retinal screening. In this paper, we take digital curvelet transform (DCUT) of the enhanced retinal image and modify its coefficients based on the sparsity of curvelet coefficients to get probable location of OD. If there are not yellowish objects in retinal images or their size are negligible, we can then directly detect OD location by performing Canny edge detector to reconstructed image with modified coefficients. Otherwise, if the size of these objects is eminent, we can see circular regions in edge map as candidate regions for OD. In this case, we use some morphological operations to fill these circular regions and erode them to get final locations for candidate regions and remove undesired pixels in edge map. Since usually OD is surrounded by vessels, we choose the candidate region that has maximum summation of pixels in strongest edge map, which obtained by performing an appropriate threshold on the curvelet-based enhanced image, as final location of OD. Finally, the boundary of the OD is extracted by using level set deformable model. This method has been tested on different retinal image datasets and quantitative results are presented.     

基于小波维纳滤波和各项异性扩散的图像去噪

提出一种基于小波和各项异性非线性扩散的新图像去噪算法。小波域局部阈值维纳滤波是一种简单有效的去噪方法,利用该方法先对原始图像进行初步去噪,以此引导非线性扩散模型中的边缘检测函数,再用非线性扩散进行去噪。实验表明:该算法不仅很好地保存了图像的边缘信息,而且有效地去除了图像中的大部分噪声,无论是视觉效果还是客观标准上都优于单纯的小波域维纳滤波或各项异性非线性扩散去噪。     

Automatic analysis of fuel spray images

Analysis of fuel spray droplets is being conducted in General Motors Research Laboratories to provide real-time information on in-focus droplet sizes and numerical density. This paper introduces a fast and efficient technique for automatic analysis of fuel spray images. The preprocessing stage consists of a global thresholding of the log-edge of the image. The thresholded image is then used as a reference to detect objects in the gray level image, and the recognition of in- and out-of-focus droplets is achieved through a 3-level tree classifier.