General Adaptive Neighborhood Choquet Image Filtering

A novel framework entitled General Adaptive Neighborhood Image Processing (GANIP) has been recently introduced in order to propose an original image representation and mathematical structure for adaptive image processing and analysis. The central idea is based on the key notion of adaptivity which is simultaneously associated with the analyzing scales, the spatial structures and the intensity values of the image to be addressed. In this paper, the GANIP framework is briefly exposed and particularly studied in the context of Choquet filtering (using fuzzy measures), which generalizes a large class of image filters. The resulting spatially-adaptive operators are studied with respect to the general GANIP framework and illustrated in both the biomedical and materials application areas. In addition, the proposed GAN-based filters are practically applied and compared to several other denoising methods through experiments on image restoration, showing a high performance of the GAN-based Choquet filters.

一种基于内容的图像自适应滤波算法

在数字成像设备中,高斯白噪声和椒盐噪声是两种常见的噪声源,对图像质量均有较大的影响.针对这两种噪声的特点,提出了一种基于内容的图像自适应滤波算法.该算法可以根据图像中各个块的特点自适应地调整滤波系数,从而达到最优的滤波效果.实验证明采用该算法对受到其中一种噪声源干扰的图像或者同时包含上述两种噪声的图像滤波,都能获得较好的结果.     

用于图像处理的自适应中值滤波

针对标准中值滤波方法存在的不足,提出自适应中值滤波方法．该方法通过噪声检测确定子图像中的脉冲噪声点及噪声干扰大小,根据噪声干扰程度选择滤波窗口的尺寸,并采用改进的中值滤波方法对检测出的噪声点进行滤波．计算机模拟实验结果表明：自适应中值滤波能在有效地去除噪声的同时,较好地保护图像细节,较标准中值滤波具有更优良的滤波性能,其滤波速度也较中值滤波具有明显优势．     

结合引导滤波的自适应多曝光图像融合

针对引导滤波产生的光晕、梯度反转现象，以及图像融合边缘细节丢失的现象，提出一种改进引导滤波的自适应多曝光图像融合算法。在引导滤波中根据梯度信息设定权重函数，并结合图像像素点和一定区域的均值创建函数，共同实现不同区域的纹理特性自适应；利用平均亮度与对比度、饱和度及曝光适中度的关系，设置权值函数，使加权平均融合过程中的权重值不再是固定的数值，而能够根据不同的图像亮度自适应调整，权重值也不同，使得融合后的图像质量更好；将原序列图的细节信息叠加到改进的引导滤波图像中，构建纹理细节层。实验结果削弱了光晕及梯度反转现象，使图像更加真实，细节更加清晰，并且对有小光源的图像处理效果更好。算法结果明显优于多曝光融合算法及引导滤波的多曝光图像融合，在信息熵、互信息和边缘信息评价中分别取得最高2.5%、30%和30%左右的质量提升。     

一种用于图像降噪的自适应均值滤波算法

图像中噪声的消除是图像处理与识别的重要环节,噪声滤除效果的好坏直接影响着后续图像处理与识别的质量.为此,提出一种用于图像降噪的空间域滤波算法,自适应均值滤波算法(Adaptive Averaging Filtering Algorithm,AAFA).该算法中局部窗口的系数(掩模系数)是根据局部窗口内各像素与中心像素间的灰度和空间关系计算的,即局部窗口中心像素灰度均值的计算既考虑了窗口内各像素与中心像素间的灰度值差异,又顾及了窗口内各像素与中心像素间的距离.利用该算法进行图像降噪的实验结果表明,相对于经典的空间域均值滤波算法和其它的均值滤波算法,该算法的噪声滤除效果更好.     

图像插值的自适应邻域滤波方法

图像待插像素用其邻域内连续方向上像素的Tyler展开可以得到较好的近似,但是沿着灰度连续和不连续方向(跨越图像边缘方向)的Tyler展开近似的线性平均会增加图像边缘宽度,引起图像边缘的视觉模糊以及产生锯齿边缘。为此,通过一个与灰度距离相关的权函数,自适应选择待插像素邻域内的Tyler展开,提出一个邻域滤波图像插值方法。与待插像素位于图像边缘同侧的像素权函数的值较大,像素的Tyler展开被选择为待插像素的近似;反之则权函数的值较小,像素的Tyler展开不用作待插像素的Tyler展开。实验结果表明,该方法避免了跨越图像边缘的Tyler展开的线性平均,可减小插值图像边缘的宽度,增加边缘斜坡坡度,从而获得清晰的插值图像边缘。     

General Adaptive Neighborhood Image Processing

The so-called General Adaptive Neighborhood Image Processing (GANIP) approach is presented in a two parts paper dealing respectively with its theoretical and practical aspects. The General Adaptive Neighborhood (GAN) paradigm, theoretically introduced in Part I [20], allows the building of new image processing transformations using context-dependent analysis. With the help of a specified analyzing criterion, such transformations perform a more significant spatial analysis, taking intrinsically into account the local radiometric, morphological or geometrical characteristics of the image. Moreover they are consistent with the physical and/or physiological settings of the image to be processed, using general linear image processing frameworks. In this paper, the GANIP approach is more particularly studied in the context of Mathematical Morphology (MM). The structuring elements, required for MM, are substituted by GAN-based structuring elements, fitting to the local contextual details of the studied image. The resulting morphological operators perform a really spatially-adaptive image processing and notably, in several important and practical cases, are connected, which is a great advantage compared to the usual ones that fail to this property.     

数字影象增强的一类自适应滤波方法

本文提出一类新的数字影象增强的递推算法.该方法用新息序列对影象的不同纹理和结构进行检测,用Kalman估计对影象的灰度直接进行校正.电子计算机模拟试验结果表明本算法是有效的.     

基于自适应加权重复值滤波和同态滤波的MR图像增强

磁共振(Magnetic Resonance,MR)图像通常存在椒盐噪声(Salt and Pepper Noise,SPN)以及对比度低的问题,为了增强MR图像,分别在空域和频域针对不同侧重点分步进行滤波.对于多数滤波算法去除高水平SPN不理想的情况,提出了自适应加权重复值滤波算法(Adaptive Weighted...     

General Adaptive Neighborhood Image Processing:

The so-called General Adaptive Neighborhood Image Processing (GANIP) approach is presented in a two parts paper dealing respectively with its theoretical and practical aspects. The Adaptive Neighborhood (AN) paradigm allows the building of new image processing transformations using context-dependent analysis. Such operators are no longer spatially invariant, but vary over the whole image with ANs as adaptive operational windows, taking intrinsically into account the local image features. This AN concept is here largely extended, using well-defined mathematical concepts, to that General Adaptive Neighborhood (GAN) in two main ways. Firstly, an analyzing criterion is added within the definition of the ANs in order to consider the radiometric, morphological or geometrical characteristics of the image, allowing a more significant spatial analysis to be addressed. Secondly, general linear image processing frameworks are introduced in the GAN approach, using concepts of abstract linear algebra, so as to develop operators that are consistent with the physical and/or physiological settings of the image to be processed.     

A Pretopological Approach for Image Segmentation and Edge Detection

We present an approach based on a pretopological formalism that allows the mathematical modeling of image segmentation by region growing. The choice of pretopology is motivated by the fact that it has less axioms than the topology which facilitates its adaptation to discrete spaces and in particularly image processing. In our approach, the pretopological adherency function associated to the pretopological structure is defined by a criterion of homogeneity. We apply our approach to the extraction of handwritten information on check background with images of scene and to edge detection. The aggregation from chosen initial germ ends to a closed part of the image composed by a stroke (a line of handwriting) or a line of contours. The evaluation, undertaken on 60 checks with various background images and different images, gives 92% of good results for the extracted handwriting with a complete elimination of the background and good results for edge detection.     

基于模型的远红外序列图像自适应增强算法及其分析

在深入分析Ｈｉｇｈｎａｍ和Ｂｒａｄｙ提出的基于成像模型的远红外图像增强方法的基础上,设计了一种新的基于模型和远红外序列图像自适应增强算法,并进行了自适应参数对算法性能影响的实验研究,新算法可以通过适当选取自适应参数来体现对增强质量和增强时间的折衷考虑,以便满足不同的应用需求。     

结合导向滤波与自适应算子的水下图像增强

针对水下图像存在的颜色失真、对比度低及图像模糊等现象,提出一种结合导向滤波与自适应算子的水下增强算法。首先根据水体对光线吸收的差异,对水下图像的三通道进行自适应算子颜色补偿,融合三通道,得到颜色补偿后的水下图像,有效提升水下图像色彩真实性;再将水下图像放入导向滤波改进的Retinex模型中,有效去除水下图像产生的模糊现象;最后分别计算增强后水下图像的三种权重,根据三种权重进行多尺度融合,获得最终增强后的水下图像。选取不同的水下图像进行客观评价实验与主观评价实验,再与现阶段的水下图像增强算法进行对比,实验结果说明该算法在修正水下图像颜色及增强水下图像对比度等方面具有较好的效果,符合人眼视觉特征,视觉效果优于现有的水下图像增强算法。     

基于显著图的可变模板形态学去雾方法

针对暗通道先验去雾中存在的光晕现象和天空区域颜色失真现象,提出了一种基于自适应可变形结构元（Adaptive deformable structuring element,ADSE）中值滤波结合灰度形态学重构精细化透射率的方法.该方法利用透射率与图像细纹理结构的无关性,由有雾图像的灰度图计算显著图（Salience map,SM）,将SM作为导向图计算ADSE,用生成的ADSE对最小颜色通道图像进行自适应中值滤波运算;其次,以粗估计暗通道图像为标记图像,以自适应中值滤波后的图像作为模板图像进行灰度形态学重构运算,获得精细化暗通道图像,继而得到精细化透射率;最后,针对天空区域,引入最优化透射率方法,对天空和非天空区域做统一的运算得到最终透射率,完成图像去雾.本文算法对真实场景具有很好的去雾效果,同时,基于形态学的运算易于并行化和硬件实现.     

实时彩色图像自适应中值滤波算法的FPGA实现

图像在采集、压缩、传输和接收的过程中,会受到脉冲噪声的影响,给后续的边缘检测、图像分割或目标识别等造成干扰;传统中值滤波将图像的RGB分量转为YCbCr分量进行滤波,该转换方法会损失一定的色度信息,且未将彩色信息完全分离,导致滤波后的图像产生色彩偏移;针对上述问题,利用HSI彩色空间中的I和S色彩分量对椒盐噪声进行检测,并通过自适应中值滤波将椒盐噪声滤除,图像还原度更高;利用FPGA对算法进行了硬件加速,在xc7a100tfgg484-2芯片上运行频率达222 MHz,可实现2k@60 Hz视频的实时处理。     

一种基于小波变换和自适应滤波的图像拼接算法

图像拼接技术其关键在于解决拼接图像配准问题,以及如何针对多幅相关图像,进行无缝接合形成连贯的没有拼接痕迹的图像.本文针对上述问题,提出了一种算法.首先对小波域的图像信息采用灰度相关法进行匹配搜索,使用RANSAC算法对匹配点进行提纯;然后在小波域生成自适应滤波器,并在图像的拼缝处作滤波处理,得到拼接后的小波系数矩阵;对小波系数矩阵进行小波逆变换还原图像.实验结果表明:在小波域对图像进行拼接,而且在接缝处根据两幅图像的自身信息进行自适应滤波(即时改变滤波器形态),故它很好地平滑了拼接中出现的接缝.     

基于自适应空域滤波的图像去块效应算法

分块有损压缩图像忽略了块间相关性,重构时会产生块效应,该文提出一种空域自适应去块效应算法。对块边缘采用方向自适应有理滤波,以弱化块效应。根据块的内部活动性将图像块分成平坦块和纹理块2类,利用基于方差的空域检测方法检测出平坦块,并对平坦块进行邻块边缘自适应平滑。实验结果表明,该算法有效去除了块效应,一定程度上提高了信噪比,算法简单且鲁棒性较好。     

基于HVS特性的图像自适应中值滤波算法

通过考虑宿主图像亮度、纹理、边缘等特征,提出一种图像自适应中值滤波算法。该算法利用基于人眼视觉特性的临界噪声阈值确定噪声点,根据噪声密度自适应调整滤波窗口大小,采用改进的中值滤波对检测出的噪声点进行处理,从而在去除噪声的同时较好地保护图像细节。实验结果表明,该算法比传统中值滤波及其改进算法有更好的滤波性能,对于噪声污染严重的图像,滤波效果更好。     

Multiplierless Adaptive Filtering

Bose, T., Venkatachalam, A., and Thamvichai, R., Multiplierless Adaptive Filtering, Digital Signal Processing12 (2002) 107–118When digital filters are designed with power-of-2 coefficients, the multiplications can be implemented by simple shifting operations. For VLSI implementations, multiplierless filters are faster and more compact than filters with multipliers. In this paper, an algorithm for finding and updating the power-of-2 coefficients of an adaptive filter is designed. The new method uses the well-known Genetic Algorithm (GA) for this purpose. The GA is used in a unique way in order to reduce computations. Small blocks of data are used for the GA and only one new generation is produced per sample of data. This, coupled with the fact that the coefficients are power-of-2, yields a computational complexity of O(N) additions and no multiplications. The algorithm is investigated for applications in adaptive linear prediction and system identification. The results are very promising and illustrate the performance of the new algorithm.