一种新的强鲁棒性的边缘检测方法

针对图像同时叠加脉冲噪声和高斯白噪声的非标准分布噪声的情况,本文提出一种新的基于统计向量和神经网络的强鲁棒性的边缘检测方法。首先选取窗口子区域内若干中间值像素点构造了由4个统计量组成的统计向量。然后计算训练图像的统计向量作为样本,对不加噪的训练图像的统计向量降维并作双阈值处理得到学习边缘图,对BP神经网络训练。最后将训练的BP神经网络直接用于边缘检测。新方法对脉冲噪声和高斯白噪声均具有较好的鲁棒性,BP神经网络的结构和训练都比较简单,而且不需要设定阈值检测边缘。     

基于深度置信网络的随机脉冲噪声快速检测算法

为提高现有随机脉冲噪声(RVIN)检测算法的检测准确率和执行效率,该文试图从构建描述能力更强的特征矢量和训练非线性映射更为准确的预测模型两个方面入手,实现一种基于训练策略的快速RVIN检测算法。一方面,提取多个不同阶的对数绝对差值排序统计值并结合一个能够反映图像边缘特性的统计值作为刻画图块中心像素点是否为噪声的特征矢量。在计算量增加极少的情况下,显著提升了特征矢量的描述能力。另一方面,基于深度置信网络(DBN)训练RVIN预测模型(RVIN检测器)将特征矢量映射为噪声类型标签,实现了比浅层预测模型更为准确的映射。大量实验数据表明：与现有的RVIN检测算法相比,所提算法在检测准确率和执行效率两个方面都更有优势。

     

Edge Drawing: A combined real-time edge and segment detector

We present a novel edge segment detection algorithm that runs real-time and produces high quality edge segments, each of which is a linear pixel chain. Unlike traditional edge detectors, which work on the thresholded gradient magnitude cluster to determine edge elements, our method first spots sparse points along rows and columns called anchors, and then joins these anchors via a smart, heuristic edge tracing procedure, hence the name Edge Drawing (ED). ED produces edge maps that always consist of clean, perfectly contiguous, well-localized, one-pixel wide edges. Edge quality metrics are inherently satisfied without a further edge linking procedure. In addition, ED is also capable of outputting the result in vector form as an array of chain-wise edge segments. Experiments on a variety of images show that ED produces high quality edge maps and runs up to 10% faster than the fastest known implementation of the Canny edge detector (OpenCV’s implementation).     

Edge detection in noisy images by neuro-fuzzy processing

A novel neuro-fuzzy (NF) operator for edge detection in digital images corrupted by impulse noise is presented. The proposed operator is constructed by combining a desired number of NF subdetectors with a postprocessor. Each NF subdetector in the structure evaluates a different pixel neighborhood relation. Hence, the number of NF subdetectors in the structure may be varied to obtain the desired edge detection performance. Internal parameters of the NF subdetectors are adaptively optimized by training by using simple artificial training images. The performance of the proposed edge detector is evaluated on different test images and compared with popular edge detectors from the literature. Simulation results indicate that the proposed NF operator outperforms competing edge detectors and offers superior performance in edge detection in digital images corrupted by impulse noise.     

Quantitative design and evaluation of enhancement/thresholding edge detectors

Quantitative design and performance evaluation techniques are developed for the enhancement/thresholding class of image edge detectors. The design techniques are based on statistical detection theory and deterministic pattern-recognition classification procedures. The performance evaluation methods developed include: a)deterministic measurement of the edge gradient amplitude; b)comparison of the probabilities of correct and false edge detection; and c) figure of merit computation. The design techniques developed are used to optimally design a variety of small and large mask edge detectors. Theoretical and experimental comparisons of edge detectors are presented.     

Detecting boundaries in a vector field

A vector gradient approach is proposed to detect boundaries in multidimensional data with multiple attributes (a vector field). It is used to extend a gradient edge detector to color images. The statistical effects of noise on the distribution of the amplitudes and directions of the vector gradient are characterized. The noise behavior of the L ₂ norm of the scalar gradients is also characterized for comparison. When the attribute components are highly correlated, as is often the case in color images, use of the vector gradient shows a small gain in signal-to-noise ratio over that of the L₂ norm of the scalar gradients. This small gain may or may not be significant, depending on other measures an edge detector uses to deal with noise     

Color edge detection using vector order statistics

A method is proposed whereby a color image is treated as a vector field and the edge information carried directly by the vectors is exploited. A class of color edge detectors is defined as the minimum over the magnitudes of linear combinations of the sorted vector samples. From this class, a specific edge detector is obtained and its performance characteristics studied. Results of a quantitative evaluation and comparison to other color edge detectors, using Pratt's (1991) figure of merit and an artificially generated test image, are presented. Edge detection results obtained for real color images demonstrate the efficiency of the detector.     

Combining spatial and scale-space techniques for edge detection to provide a spatially adaptive wavelet-based noise filtering algorithm

New methods for detecting edges in an image using spatial and scale-space domains are proposed. A priori knowledge about geometrical characteristics of edges is used to assign a probability factor to the chance of any pixel being on an edge. An improved double thresholding technique is introduced for spatial domain filtering. Probabilities that pixels belong to a given edge are assigned based on pixel similarity across gradient amplitudes, gradient phases and edge connectivity. The scale-space approach uses dynamic range compression to allow wavelet correlation over a wider range of scales. A probabilistic formulation is used to combine the results obtained from filtering in each domain to provide a final edge probability image which has the advantages of both spatial and scale-space domain methods. Decomposing this edge probability image with the same wavelet as the original image permits the generation of adaptive filters that can recognize the characteristics of the edges in all wavelet detail and approximation images regardless of scale. These matched filters permit significant reduction in image noise without contributing to edge distortion. The spatially adaptive wavelet noise-filtering algorithm is qualitatively and quantitatively compared to a frequency domain and two wavelet based noise suppression algorithms using both natural and computer generated noisy images.     

Adaptive pseudo dilation for gestalt edge grouping and contour detection

We consider the problem of detecting object contours in natural images. In many cases, local luminance changes turn out to be stronger in textured areas than on object contours. Therefore, local edge features, which only look at a small neighborhood of each pixel, cannot be reliable indicators of the presence of a contour, and some global analysis is needed. We introduce a new morphological operator, called adaptive pseudo-dilation (APD), which uses context dependent structuring elements in order to identify long curvilinear structure in the edge map. We show that grouping edge pixels as the connected components of the output of APD results in a good agreement with the gestalt law of good continuation. The novelty of this operator is that dilation is limited to the Voronoi cell of each edge pixel. An efficient implementation of APD is presented. The grouping algorithm is then embedded in a multithreshold contour detector. At each threshold level, small groups of edges are removed, and contours are completed by means of a generalized reconstruction from markers. The use of different thresholds makes the algorithm much less sensitive to the values of the input parameters. Both qualitative and quantitative comparison with existing approaches prove the superiority of the proposed contour detector in terms of larger amount of suppressed texture and more effective detection of low-contrast contours.     

Histogram-based morphological edge detector

Presents a new edge detector for automatic extraction of oceanographic (mesoscale) features present in infrared (IR) images obtained from the Advanced Very High Resolution Radiometer (AVHRR). Conventional edge detectors are very sensitive to edge fine structure, which makes it difficult to distinguish the weak gradients that are useful in this application from noise. Mathematical morphology has been used in the past to develop efficient and statistically robust edge detectors. Image analysis techniques use the histogram for operations such as thresholding and edge extraction in a local neighborhood in the image. An efficient computational framework is discussed for extraction of mesoscale features present in IR images. The technique presented in the present article, called the Histogram-Based Morphological Edge detector (HMED), extracts all the weak gradients, yet retains the edge sharpness in the image. A new morphological operation defined in the domain of the histogram of an image is also presented. An interesting experimental result was found by applying the HMED technique to oceanographic data in which certain features are known to have edge gradients of varying strength     

Adaptive threshold modulation for error diffusion halftoning

Grayscale digital image halftoning quantizes each pixel to one bit. In error diffusion halftoning, the quantization error at each pixel is filtered and fed back to the input in order to diffuse the quantization error among the neighboring grayscale pixels. Error diffusion introduces nonlinear distortion (directional artifacts), linear distortion (sharpening), and additive noise. Threshold modulation, which alters the quantizer input, has been previously used to reduce either directional artifacts or linear distortion. This paper presents an adaptive threshold modulation framework to improve halftone quality by optimizing error diffusion parameters in the least squares sense. The framework models the quantizer implicitly, so a wide variety of quantizers may be used. Based on the framework, we derive adaptive algorithms to optimize 1) edge enhancement halftoning and 2) green noise halftoning. In edge enhancement halftoning, we minimize linear distortion by controlling the sharpening control parameter. We may also break up directional artifacts by replacing the thresholding quantizer with a deterministic bit flipping (DBF) quantizer. For green noise halftoning, we optimize the hysteresis coefficients.     

A morphological gradient approach to color edge detection.

A new color edge detector based on vector differences is proposed. The basic technique gives as its output the maximum distance between the vectors within a mask. When applied to scalar-valued images, the method reduces to the classic morphological gradient. The technique is relatively computationally efficient and can also be readily applied to other vector-valued images. To improve the performance in the presence of noise, a novel pairwise outlier rejection scheme is employed. A quantitative evaluation using Pratt's figure of merit shows the new technique to outperform other recently proposed color edge detectors. In addition, application to real images demonstrates the approach to be highly effective despite its low complexity.     

Standardization of edge magnitude in color images.

Edge detection is a useful task in low-level image processing. The efficiency of many image processing and computer vision tasks depends on the perfection of detecting meaningful edges. To get a meaningful edge, thresholding is almost inevitable in any edge detection algorithm. Many algorithms reported in the literature adopt ad hoc schemes for this purpose. These algorithms require the threshold values to be supplied and tuned by the user. There are many high-level tasks in computer vision which are to be performed without human intervention. Thus, there is a need to develop a scheme where a single set of threshold values would give acceptable results for many color images. In this paper, an attempt has been made to devise such an algorithm. Statistical variability of partial derivatives at each pixel is used to obtain standardized edge magnitude and is thresholded using two threshold values. The advantage of standardization is evident from the results obtained.     

Similarity relation matrix-based color edge detection

A novel edge detection algorithm for color images was described in this paper. In the proposed method, smoothness of each pixel in color image is firstly calculated by means of similarity relation matrix and is normalized to maximum gray level. In other words, color image in three-dimensional color spaces is mapped into one dimension. Accordingly the edges are performed in such a way that pixels lower than thresholds are assigned to be edge. Thus with proposed method, edge pixels in a color image are detected simultaneously without any complex calculations such as gradient, Laplace and statistical calculations.     

基于模糊神经网络的红外图像边缘提取算法

针对现有图像边缘提取算法存在的噪声平滑能力与边缘精确定位之间的矛盾,以及红外图像自身信噪比低、视觉效果模糊和对比度差等缺陷,利用模糊神经网络的学习、自适应和模糊处理等优点,提出了一种基于模糊神经网络的红外图像边缘提取方法。计算各像素点8个方向的基本梯度、左关联梯度和右关联梯度,并将其组成梯度数组,把8个方向的梯度数组作为模糊神经网络的输入信号,通过学习和模糊处理最终可获得相对精确的红外图像边缘。实验结果表明,该方法抗噪能力强,边缘保留完整且为单像素宽,在处理红外图像边缘提取上要优于其他算法。     

基于显著性局部定向模式和深度学习的鲁棒人脸识别

针对传统人脸识别算法特征提取不充分和对噪声敏 感的问题,提出了一种基于显著性局部定向模式(SLDP)和深 度学习(DL)的人脸识别算法。首先基于信息的显著性提出一种改进的SLDP人脸描述方法,在 利用局部井型 领域梯度信息的基础上,使用两组梯度值中各自最大值和次大值的方向编码成二位八进制数 ,从而形成改进的 SLDP编码,通过统计选出最具有显著性的SLDP编码作为特征向量;然后将改进的SLDP编码作 为深度神经网 络(DBN)的输入,通过逐层贪婪训练网络,获得良好的网络参数,并用训练好的网络对测试 样本进行预测。仿真实验表明, 本文所提出的人脸识别算法相对于传统识别算法识别率高,并且在对抗噪声方面比其它算法 更具有鲁棒性。     

Morphological Image Enlargements

This paper presents a method based in mathematical morphology to enlarge images. It does not make the low pass assumption which is common to all linear interpolation methods and which does not often hold for images. Pixels in smooth areas are properly interpolated by linear methods while those at the edges are not. The method begins with a linear interpolation and a gradient computation. The gradient serves as a measure of confidence about the linear interpolation. Then, the proposed algorithm processes the pixels in a certain order: first pixels with high confidence (smooth zones) of the image and those with a low one (edges) at the end. By doing so, it preserves both slow variations and sharp edges. The method can be applied to other image processing problems, such as edge enhancement or motion vector estimation, where there is an image and confidence information about each pixel.     

Fractal feature analysis and classification in medical imaging

Following B.B. Mandelbrot's fractal theory (1982), it was found that the fractal dimension could be obtained in medical images by the concept of fractional Brownian motion. An estimation concept for determination of the fractal dimension based upon the concept of fractional Brownian motion is discussed. Two applications are found: (1) classification; (2) edge enhancement and detection. For the purpose of classification, a normalized fractional Brownian motion feature vector is defined from this estimation concept. It represented the normalized average absolute intensity difference of pixel pairs on a surface of different scales. The feature vector uses relatively few data items to represent the statistical characteristics of the medial image surface and is invariant to linear intensity transformation. For edge enhancement and detection application, a transformed image is obtained by calculating the fractal dimension of each pixel over the whole medical image. The fractal dimension value of each pixel is obtained by calculating the fractal dimension of 7x7 pixel block centered on this pixel.     

硅基非致冷混合式焦平面探测器阵列研究

本文报道一种32×48元高灵敏非致冷混合式焦平面探测器厚膜阵列.提出了一种采用掺杂钛酸锶钡厚膜作为敏感材料的硅基微机械加工电容式红外探测器像元结构,对其工作原理、器件性能优化设计与制作工艺流程进行了分析,得出了优化的结构参数.分析了影响器件性能的关键因素,给出了器件所用铁电材料的基本物理和电学特性参数以及器件的热隔离技术和相应参数.本结构的像元电容值增量接近相同敏感面的体材料红外探测器,减小了像元与衬底电极引线的寄生电容.采用这种结构的红外探测器阵列对电路的精度要求低,便于研制集成电路.该红外探测器阵列结构的设计思路,符合大阵列红外焦平面像元结构设计的发展趋势,为开展非致冷红外焦平面阵列探测器研究奠定了基础.     

Retinal blood vessel segmentation using line operators and support vector classification

In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. A line detector, previously used in mammography, is applied to the green channel of the retinal image. It is based on the evaluation of the average grey level along lines of fixed length passing through the target pixel at different orientations. Two segmentation methods are considered. The first uses the basic line detector whose response is thresholded to obtain unsupervised pixel classification. As a further development, we employ two orthogonal line detectors along with the grey level of the target pixel to construct a feature vector for supervised classification using a support vector machine. The effectiveness of both methods is demonstrated through receiver operating characteristic analysis on two publicly available databases of color fundus images.