基于八方向卷积模板的边缘检测算法

针对传统图像边缘检测算法存在的边缘方向性不强及边缘较粗等问题,提出了一种基于八方向卷积模板的边缘检测算法。算法采用0°、22.5°、45°、67.5°、90°、112.5°、135°和157.5°八个方向的卷积模板进行边缘检测,模板权值根据中心像素点到邻域像素的距离及方向夹角的大小进行设定,充分考虑到了邻域内像素对中心点方向梯度的贡献大小,能够较好地检测出图像不同的方向边缘。对梯度图像采用了改进的非极大值抑制方法进行细化,可得到单像素的图像边缘。实验结果表明,该算法获取的边缘图像边缘较为完整,方向性强且边缘较细,整体效果明显优于传统Sobel算法。     

基于Sobel的多方向算子模板边缘检测算法

针对传统Sobel算子存在的边缘检测方向性不强及提取边缘较粗等问题,提出了一种改进的多方向算子模板的边缘检测算法。算法增加了22.5°,45°,67.5°,112.5°,135°和157.5°六个方向算子模板,能够较好地检测出图像不同的方向边缘。模板权值根据中心像素点到邻域像素的距离及方向夹角的大小进行设定,充分考虑到了邻域内像素对中心点方向梯度的贡献大小;算法对梯度图像采用了改进的非极大值抑制方法进行细化,得到了较细的图像边缘。实验结果表明,与传统Sobel算法相比,该算法提取的边缘图像具有边缘方向性强且边缘较细的优点,具有较高的应用价值。     

一种快速的半像素运动矢量搜索算法

提出了一种基于梯度预测的快速半像素运动矢量搜索算法.实验结果表明,在H.263编码器中使用该算法的运算量,比在相同量化阶下的半像素运动矢量搜索算法下降45%,并且图像的PSNR和码率变化很小.该算法可以很容易地应用到H.264的1/4像素运动矢量搜索中.     

基于相似像素选择的非局域SAR 图像相干斑抑制

该文提出了一种比值距离像素相关性模型与相似像素选择的非局域SAR 图像相干斑抑制算法。首先由两像素的联合概率密度函数得出了比值距离像素相关性模型,并按错误概率最小准则训练生成了不同情况下的像素相似性阈值表,然后进行非局域窗中像素的相似性计算,并用查表所得的像素相似性阈值进行非局域窗中相似像素的选择,最后用选中的像素进行当前像素真实后向散射系数的估计。对仿真与实测SAR 图像的相干斑抑制实验显示,与其它现有非局域抑斑算法相比,该文方法不仅能最大程度地去除同质区域的噪声,而且可以对边缘纹理等细节区域进行很好地重构,滤波结果显示了很好的视觉效果,并且具有较低的计算复杂度。      

基于图像分块和优化累积能量图的线裁剪算法

针对传统线裁剪方法对图像过度裁剪造成失真的问题,该文提出一种基于图像分块的线裁剪方法。该方法把分块的思想融入到线裁剪并优化累积能量图,能在一定程度上保护图像主体区域,又兼顾背景区域的裁剪效果。分块是根据显著图的平均列累加能量向量按照逐列标记的方式把图像分成保护区域和非保护区域,再根据每个区域的面积来分配裁剪线的数目。在裁剪过程中,优化了累积能量图,降低了小面积显著主体被裁剪掉的可能性。在MSRA数据库上与目前流行的线裁剪及其改进的方法进行对比,并把各种方法得到的缩放结果图在互联网上进行主观评价测试,实验结果表明该文方法具有更好的主观缩放效果,对各类图像的缩放具有普适性。     

双波段全极化SAR图像非监督分类方法及实验研究

该文首先采用H/分类对像素进行了初始猜测,然后进一步采用Bayes最大似然估计(ML）分类法对像素进行重新归类．不同波段电磁波对地物散射具有不同的属性,因而我们采用双波段全极化SAR数据结合的分类方法,得到了更好的分类结果．SAR图像的相干斑会影响图像的分类准确度和精度．在进行分类处理前,对双波段全极化SAR图像相干斑进行矢量滤波处理．该文使用NASA/JPL实验室在天山地区的实测数据对这些分类算法进行了实验研究．给出了单波段以及双波段全极化SAR分类结果的伪彩色图．其中双波段全极化SAR滤波后数据具有相对最优的分类结果．     

基于图像处理的建筑物振动位移测量算法

针对地震后高层建筑物结构损伤监测问题,该文提出一种基于方向码匹配(OCM)和边缘增强匹配(EEM)算法的微小位移测量算法。该算法先将原始图像梯度信息与像素强度融合,增强图像信息;采用相位相关法进行匹配运算,匹配速度比归一化互相关法提升了96.1%;最后使用亚像素插值法,使测量结果达到亚像素精度。实验结果表明,该文算法避免了OCM和EEM算法量化过程中图像梯度信息的损失,大大提高了模板匹配精度,匹配速度比OCM提升了43.3%,比EEM提升了19.6%。     

基于非局部先验的雾线优化图像去雾算法

针对非局部先验去雾算法中雾线端点像素位置精确度不足的问题,提出了雾线优化的非局部先验图像去雾算法。首先分析雾线理论,结合暗通道理论确定最大聚类雾线真实端点,以其为已知条件补偿小聚类雾线端点与大气光之间的距离,根据类内不同像素与雾线对应夹角预估单个像素雾线端点进而求得像素级优化后的透射率,最后根据图像局部灰度值差异融合暗通道先验(dark channel prior, DCP)和非局部先验透射率得最终透射率图。将本文算法与其余3种去雾算法在多幅户外雾图下通过主观及客观两方面分析比较,实验结果表明该算法能取得更好的去雾效果,尤其在天空区域图像复原效果较为突出。     

一种基于TV模型的快速图像修复算法

在研究TV修复算法的基础上,提出了一种快速修复算法.利用图像梯度的大小与方向信息对损坏像素直接加权合成,同时按照待修复点邻域内已知像素的梯度方差确定修复次序.实验证明快速修复算法显著减小了运算时间,并且修复后图像纹理更加清晰,达到了较好效果.     

基于多光谱数据和融合像素差卷积的壁画线稿提取

使用现有边缘检测方法提取古代壁画的线稿,存在噪声干扰大且丢失信息较多的问题。本文提出一种融合像素差卷积的壁画最优波段线稿提取方法,利用最小噪声分离方法将壁画多光谱数据的有效信息和噪声分离,选择最优主成分波段进行线稿的提取。针对传统卷积提取图像梯度信息的问题,引入像素差卷积提高边缘检测的图像梯度信息。在侧输出网络加入尺度增强模块（SEM）丰富多尺度特征,同时针对像素级别不平衡引起的像素错误分类问题,设计了基于图像相似度的Dice损失函数策略,逐级最小化像素距离获得清晰图像边缘,并利用壁画数据集先验知识微调模型解决数据集不足的问题。实验结果表明,本文方法可以在壁画褪色和噪声较多的场景下提取出较为清晰的线稿,线稿图像的SSIM和RMSE均优于其他算法,分别提高了2%～10%和2%～4%;在公开数据集BIPED上对模型进行验证,所提方法的ODS和OIS较PiDiNet分别提高0.005和0.007。该方法对褪色及具有病害的壁画可以提取出清晰完整的线稿图像。     

Optimal bi-directional seam carving for compressibility-aware image retargeting

A novel compressibility-aware image retargeting method based on seam carving is introduced in this paper. We propose a new significance detection method, with both the edge information and visual saliency taken into consideration. A wall-seam model is constructed to evaluate the image compressibility and assign the right number of seams for each direction. By repeatedly carving out or inserting seams we can retarget the image to a new size while preserving the important content. Finally, our algorithm is completed with the supplement of uniformly scaling, the stretched image is resized to the target size with the least structure distortion brought. Experimental results on images show that those improvements are effective and our approach can preserve image content better compared to several state-of-the-art image retargeting methods.     

Sparse Seam-Carving for Structure Preserving Image Retargeting

The seam carving technique is one of the most popular techniques for content-aware image retargeting. There have been many attempts to improve existing methods of seam carving to provide more aesthetic retargeting results. However, most previous methods focus on developing an energy map for preserving important image regions while retargeting. Commonly, the existing seam carving based techniques tends to produce discontinuity artifacts when retargeting straight structures. We observe that it occurs when a bunch of seams are assigned across straight structures (i.e., lines or edges). In this paper, we propose a modified seam carving method not only preserving important parts, but also maintaining the prominent structure of the image. To this end, we put a constraint that seams are sparsely assigned each other. Experimental results show that the proposed sparse seam carving yields more plausible retargeting results than previous retargeting approaches and it is very robust to images containing prominent lines or edges.     

图像自适应中基于形变控制的细缝剪裁方法

为了降低图像自适应过程中图像内容缺失和图像扭曲变形,文章中提出了一种基于形变控制的图像自适应细缝裁剪方法,将融合局部和全局显著性的显著图作为细缝裁剪参考的能量图,对需要剪裁的细缝按照这个能量图进行排序,以更好地保护图像中感兴趣区域（ROI）,保留图像的主要内容信息;同时,利用SIFT流矢量场来衡量剪裁图像的形变程度,每移除一定数量的细缝就计算剪裁图像与原始图像之间的形变,一旦形变达到某一阈值,就停止细缝裁剪,转换为均匀缩放使图像到达目标尺寸。实验结果表明,文章中提出的方法更好地平衡了均匀缩放和非均匀剪裁,更有利于保留图像主要内容和避免主要内容的变形。      

Detecting image seam carving with low scaling ratio using multi-scale spatial and spectral entropies

Seam carving is the most popular content-aware image retargeting technique. However, it may also be used to correct poor photo composition in photography competition or to remove object from image for malicious purpose. A blind detection approach is presented for seam carved image with low scaling ratio (LSR). It exploits spatial and spectral entropies (SSE) on multi-scale images (candidate image and its down-sampled versions). We observe that when a few seams are deleted from an original image, its SSE distribution is greatly changed. Forty-two features are designed to unveil the statistical properties of SSE in terms of centralized tendency, dispersion tendency and distribution tendency. They are combined with the local binary pattern (LBP)-based energy features to form ninety-six features. Finally, support vector machine (SVM) is exploited as classifier to determine whether an image is original or suffered from seam carving. Experimental results show that the proposed approach achieves superior detection accuracy over the state-of-the-art works, especially for resized image by seam carving with LSRs. Moreover, it is robust against JPEG compression and seam insertion.     

Seam carving based aesthetics enhancement for photos

Recently people are becoming more and more interested in the quality of photographs with the growing interest of image aesthetics. Many previous works start to focus on aesthetically enhancing the quality of images. In this paper, we come up with a novel approach to enhance image aesthetics. An aesthetically beautiful image usually has a clever composition of objects, the optimal positions of which have been deeply discussed by previous methods and reached good performance. After getting the optimal position of the object in images, we try to rearrange all the objects. Instead of picking the object out and pasting it on the suggested place, we propose an improved seam carving approach to change the relative positions of the objects in the image, which is able to move the object to a better place. We adopt the energy function to measure the saliency of each pixel and then find out the seams that should be cut off and inserted. After cutting off unimportant seams by pixel-removing and inserting seams by inpainting, we are able to maintain the resolution of the image as well as enhance the aesthetics in composition. In order to test the effectiveness of our method, we compare the performance of our approach with other state-of-the-art techniques, which well illustrates the satisfying performance of our method.     

Cluster-Based Saliency-Guided Content-Aware Image Retargeting

Straightforward image resizing operators without considering image contents (e.g., uniform scaling) cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content-aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.     

基于最小位移可视差的连续Seam Carving算法在图像缩放中的研究

图像缩放技术要求对图像缩放的同时保证重要信息不丢失且物体边缘不发生扭曲。近年来,Seam Carving及其改进算法得到了广泛的关注和研究。由于采用了离散式最小能量线迭代搜索策略,缩放信息无法在迭代过程中传递导致扭曲现象普遍存在。该文针对上述问题提出最小位移可视差(JND)检测算法,能够有效地检测每一次迭代中出现的潜在扭曲信息。能量权重$ {E}_{w} $能够将JND信息累加传递给后续的迭代过程,从而抑制缩放过程中的边缘扭曲现象。通过JND算法和能量权重,该文首次将离散的Seam Carving模型转变为连续缩放模型。最后,在公共数据集RetargetMe上与最新的图像缩放算法进行多组对比实验,验证了所提方法的有效性和先进性。     

基于最小位移可视差的连续Seam Carving算法在图像缩放中的研究

图像缩放技术要求对图像缩放的同时保证重要信息不丢失且物体边缘不发生扭曲。近年来,Seam Carving及其改进算法得到了广泛的关注和研究。由于采用了离散式最小能量线迭代搜索策略,缩放信息无法在迭代过程中传递导致扭曲现象普遍存在。该文针对上述问题提出最小位移可视差(JND)检测算法,能够有效地检测每一次迭代中出现的潜在扭曲信息。能量权重\begin{document}$ {E}_{w} $\end{document}能够将JND信息累加传递给后续的迭代过程,从而抑制缩放过程中的边缘扭曲现象。通过JND算法和能量权重,该文首次将离散的Seam Carving模型转变为连续缩放模型。最后,在公共数据集RetargetMe上与最新的图像缩放算法进行多组对比实验,验证了所提方法的有效性和先进性。     

Saliency detection in the compressed domain for adaptive image retargeting

Saliency detection plays important roles in many image processing applications, such as regions of interest extraction and image resizing. Existing saliency detection models are built in the uncompressed domain. Since most images over Internet are typically stored in the compressed domain such as joint photographic experts group (JPEG), we propose a novel saliency detection model in the compressed domain in this paper. The intensity, color, and texture features of the image are extracted from discrete cosine transform (DCT) coefficients in the JPEG bit-stream. Saliency value of each DCT block is obtained based on the Hausdorff distance calculation and feature map fusion. Based on the proposed saliency detection model, we further design an adaptive image retargeting algorithm in the compressed domain. The proposed image retargeting algorithm utilizes multioperator operation comprised of the block-based seam carving and the image scaling to resize images. A new definition of texture homogeneity is given to determine the amount of removal block-based seams. Thanks to the directly derived accurate saliency information from the compressed domain, the proposed image retargeting algorithm effectively preserves the visually important regions for images, efficiently removes the less crucial regions, and therefore significantly outperforms the relevant state-of-the-art algorithms, as demonstrated with the in-depth analysis in the extensive experiments.