基于Hough变换的倾斜文本图像的检测

在OCR图像扫描输入的过程中,扫描图像经常会出现某种程度的倾斜,这种倾斜会给下一个字符的切割造成困难,影响字符识别的精度。正是出于检测倾斜文本图像角度的目的,提出了一种基于Hough变换的检测图像倾斜度的方法,可以有效地克服几何失真对文字识别系统的影响,为了克服Hough变换计算量大的缺点,该方法采用了提取图像特征点的方法。实验结果表明,该方法能快速准确地测出各类文本图像的倾斜角度,并且具有很好的适应性。     

基于Radon变换的倾斜彩色图像自动矫正方法

在图像处理系统中,通过采集设备获得的图像如彩色扫描文档不可避免地会出现倾斜现象,虽然文档图像处理技术已经取得很多进展,但是,对于倾斜图像的矫正还存在困难.本文根据图像的结构特征 ,给出了基于Canny边缘检测和Radon变换相结合的算法,根据Radon变换取得的倾斜角度进行图像的倾斜矫正.实验表明,算法对彩色图像进行自动矫正是准确、高效的.     

Skew correction of business card images acquired in PDA

An efficient algorithm for rotational skew correction of business card images acquired in a PDA (personal digital assistant) camera is presented. The proposed method is composed of four parts: block adaptive binarisation (BAB), stripe generation, skew angle calculation and image rotation. In BAB, an input image is binarised block by block so as to lessen the effects of irregular illumination and shadow over the input image. In stripe generation, character string clusters are generated merging adjacent characters and their strings, and then only clusters useful for skew angle calculation are output as stripes. In skew angle calculation, the direction angles of the stripes are calculated using their central moments and then the skew angle of the input image is determined averaging the direction angles. In image rotation, the input image is rotated by the skew angle. Experimental results show that the proposed method yields root mean square error of 0.44/spl deg/ for test images of several types of business cards acquired by a PDA under various surrounding conditions.     

Skew characteristics of image fiber for high-speed 2-D paralleloptical data link

Skew of an image fiber, which has more than ten thousands of cores in a common cladding, was measured by a novel measurement method for the first time. This method can measure the time-of-flight difference between individual cores over the whole area of an image circle. The measurement result reveals that a test 100-m-long image fiber has skew of 5 ps/m, and the time-of-flight distributes randomly in the whole area of the image circle due to nonuniformity of the core dimension. It is also experimentally shown that the skew of an image fiber increases by bending. The theoretical analysis reveals that the bending-induced skew depends neither on the radius of curvature nor the shape of the curve but it depends only on the number of turns it is wound. The numerical calculation of skew by using typical parameters of image fibers shows that the winding have to be restricted to less than five turns to achieve a transmission speed of over 1 Gb/s/ch. Finally, we propose a twisted image fiber and an “8-shaped” bobbin to suppress the skew due to bending     

基于版面的拍照文档图像倾斜校正

文档图像版面十分复杂,建立一个较为通用的文档图像倾斜校正算法是很困难的。因此提出了基于版面的文档图像倾斜自动校正算法,并且对经典的霍夫变换检测直线的方法进行了改进,最后采用最小距离法对这些直线进行拟合,避免了因利用传统的最小二乘法拟合直线所带来的缺点。针对不同的文档版面采用相应的倾斜校正策略,实验表明该方法具有适应性强、倾斜校正速度快和精度高的特点。     

基于文本行基线的倾斜角检测算法

针对文本图像倾斜检测问题,提出了一种新的基于文本行基线的倾斜角检测算法。该算法用边界标记自动机对一组同行的字符进行轮廓（外边界）跟踪,并标记出字符的最小外接矩形（MER）和字符的边框。在此基础上通过相邻字符间的行高差和字符区域的面积来剔除字符的冗余部分,最后用剩余部分的字符边框底边中点来拟合一条直线,即行文本的基线,并确定文本的倾斜角度。实验结果表明,该方法有效,同时倾斜角检测的精确性得到了优化。     

采用SURF特征和局部互相关信息的图像配准算法

针对现有图像配准方法中存在的鲁棒性与配准精度难以兼容的问题,提出了一种采用SURF特征和局部互相关信息的图像配准算法。首先通过SURF特征提取方法进行初步粗配准以提升配准鲁棒性,然后利用图像中局部关键区域的互相关系数计算出单应矩阵,最后将单应矩阵应用于粗配准结果,对粗配准后的图像进行旋转变换,从而实现高精度和高鲁棒性的图像配准。实验结果表明:提出的配准方法与基于SIFT、ORB、SURF、互相关信息的图像配准方法在多组数据上进行了对比,不仅表现出了较高的配准精度和配准效率,也表现出了更优的鲁棒性。     

基于对数极坐标映射的图像倾斜检测

图像倾斜角的检测和校正是图像预处理中很重要的环节。本文推广了Fourier变换检测文本倾角的方法,并将其应用到更多类型的图像。算法将图像的Fourier谱映射到对数极坐标域,并分析计算Fourier谱在角度轴上的投影峰值,最终获得图像的倾斜角。实验结果表明,此算法适用范围广,计算量小,且具有很好的鲁棒性。     

一种快速稳定的倾斜文档校正方法

在文档扫描数字化过程中会出现倾斜,依据文档图像自身的线条和文字行特征,提出了一种快速而稳健的文档校正算法.该算法首先对文本进行数学形态学处理、边缘检测,然后利用直线拟合技术得到直线,从中筛选出有代表性的直线,通过直线与主轴方向的夹角检测出角度,最后对图像进行旋转校正.通过实验验证以及与目前具有相关代表性的方法对比,论证...     

Enhancing echo cancellation via estimation of delay

The advent of packetized audio transmission, such as voice over IP (VoIP), has resulted in challenging requirements for echo cancellation technology. One key aspect of this technology is the need to characterize, quickly and accurately, the echo paths in the transmission media. Echo paths consist of a constant time delay with no echo signal and active regions in which the echo signal is present. When an adaptive filter echo cancellation algorithm is used, its performance can be greatly increased, and its complexity can be reduced if it is only applied to the active regions. This requires an algorithm to estimate the constant delay and locate the active regions. Traditionally, delay estimation has been based on direct application of cross-correlation. This method has poor performance because the input signals are highly correlated and has a high implementation cost because many cross-correlation lags have to be computed for longer time delays. The delay estimation addressed in this paper has two major advantages over the traditional methods. The first is that it has improved performance because the input signals are processed to have less correlation. The second is that the implementation cost is significantly reduced because fewer cross-correlation lags are computed, and an efficient method to estimate lags is created.     

A correlation-based approach to calculate rotation and translation of moving cells.

We present a noniterative image cross-correlation approach to track translation and rotation of crawling cells in time-lapse video microscopy sequences. The method does not rely on extracting features or moments, and therefore does not impose specific requirements on the type of microscopy used for imaging. Here we use phase-contrast images. We calculate cell rotation and translation from one image to the next in two stages. First, rotation is calculated by cross correlating the images' polar-transformed magnitude spectra (Fourier magnitudes). Rotation of the cell about any center in the original images results in translation in this representation. Then, we rotate the first image such that the cell has the same orientation in both images, and cross correlate this image with the second image to calculate translation. By calculating the rotation and translation over each interval in the movie, and thereby tracking the cell's position and orientation in each image, we can then map from the stationary reference frame in which the cell was observed to the cell's moving coordinate system. We describe our modifications enabling application to nonidentical images from video sequences of moving cells, and compare this method's performance with that of a feature extraction method and an iterative optimization method.     

基于多尺度多方向Gabor模板的光学/SAR景象匹配

合成孔径雷达(SAR)成像制导通常采用光学基准图和SAR实时图进行特征提取和景象匹配.提出了一种光学/SAR异类影像匹配方法,利用多尺度多方向Gabor模板提取图像的Gabor特征后进行特征匹配,首先对SAR图像进行方向Frost滤波预处理,然后分别计算光学图像和SAR图像的高斯梯度图像,再利用多尺度多方向二维Gabor滤波器模板分别对两幅高斯梯度图像进行特征提取,最后对两组特征矩阵进行归一化互相关匹配.该方法直接利用光学图像和SAR实时图进行景象匹配,实验表明,该异类影像匹配方法较其他传统方法具有较高的鲁棒性和准确性.     

基于粒子群优化的文本图像倾斜检测

文中提出一种基于粒子群优化算法和Fourier变换的无限制文本倾斜检测方法,首先对扫描的文本图像进行Fourier变换,然后利用Fourier变换的幅度谱水平投影的方差作为算法的适应度函数,最后利用粒子群优化算法在-90°-90°之间搜索,得到准确的倾斜角度。     

Structural image retrieval using automatic image annotation and region based inverted file

Image retrieval has lagged far behind text retrieval despite more than two decades of intensive research effort. Most of the research on image retrieval in the last two decades are on content based image retrieval or image retrieval based on low level features. Recent research in this area focuses on semantic image retrieval using automatic image annotation. Most semantic image retrieval techniques in literature, however, treat an image as a bag of features/words while ignore the structural or spatial information in the image. In this paper, we propose a structural image retrieval method based on automatic image annotation and region based inverted file. In the proposed system, regions in an image are treated the same way as keywords in a structural text document, semantic concepts are learnt from image data to label image regions as keywords and weight is assigned to each keyword according to spatial position and relationship. As the result, images are indexed and retrieved in the same way as structural document retrieval. Specifically, images are broken down to regions which are represented using colour, texture and shape features. Region features are then quantized to create visual dictionaries which are similar to monolingual dictionaries like English or Chinese dictionaries. In the next step, a semantic dictionary similar to a bilingual dictionary like the English–Chinese dictionary is learnt to mapping image regions to semantic concepts. Finally, images are then indexed and retrieved using a novel region based inverted file data structure. Results show the proposed method has significant advantage over the widely used Bayesian annotation models.     

结合文字核心区域和扩展生长的藏文古籍文本行切分

藏文古籍文档图像中相邻文本行之间通常存在黏连和重叠的情况,这使得文本行切分成为一项艰巨的任务。因此,提出了一种结合文字核心区域和扩展生长的藏文古籍文档图像的行切分方法。首先,根据二值藏文古籍文档图像中连通域的面积和真圆度去除非音节点,获得音节点图像。其次,通过水平投影音节点图像和垂直投影二值原图,得到文本行基线所处的范围和文本行数,生成文字核心区域;通过像素值的或运算将文字核心区域和二值原图结合,得到伪文本连通区域。最后,基于广度优先搜索算法将文字核心区域扩展为伪文本连通区域,获得伪文本行连通区域,通过去掉其中的非文字区域来获得伪文本行,利用有效的断裂笔画行归属方法获得最终的文本行。实验结果表明,所提方法取得了较好的文本行切分结果,有效解决了文本行之间的重叠、部分行黏连以及笔画断裂等藏文古籍文本行切分的问题。     

Skew evaluation using two-dimensional refractive-index profile insingle-mode fiber ribbons

The skew of fiber ribbons must be small for high bit rate parallel optical transmission systems. Accurate skew evaluation using fiber parameters is important for this purpose. A simple method, based on the calculus of variations, is proposed for evaluating the skews of fiber ribbons. This method employs only one mode field (LP₀₁ mode) of an ideal step-index fiber as a trial function and a two-dimensional (2-D) refractive index profile. The measured skews of a 16-fiber ribbon composed of fibers with different parameters are compared with calculated values and are found to be in good agreement. The influence on the skew of several refractive index profile deviations (including asymmetric profile deviations) are evaluated using the proposed method. It is found that the asymmetric core profile has a large influence on skew whereas that of the asymmetric core-cladding boundary is relatively small     

A Document Image Model and Estimation Algorithm for Optimized JPEG Decompression

The JPEG standard is one of the most prevalent image compression schemes in use today. While JPEG was designed for use with natural images, it is also widely used for the encoding of raster documents. Unfortunately, JPEG's characteristic blocking and ringing artifacts can severely degrade the quality of text and graphics in complex documents. We propose a JPEG decompression algorithm which is designed to produce substantially higher quality images from the same standard JPEG encodings. The method works by incorporating a document image model into the decoding process which accounts for the wide variety of content in modern complex color documents. The method works by first segmenting the JPEG encoded document into regions corresponding to background, text, and picture content. The regions corresponding to text and background are then decoded using maximum a posteriori (MAP) estimation. Most importantly, the MAP reconstruction of the text regions uses a model which accounts for the spatial characteristics of text and graphics. Our experimental comparisons to the baseline JPEG decoding as well as to three other decoding schemes, demonstrate that our method substantially improves the quality of decoded images, both visually and as measured by PSNR.     

自适应调节滤波强度的SAR图像非局部平均抑斑算法

为提升对SAR图像乘性相干斑的抑制水平与边缘保护性能,该文提出了一种可自适应调节滤波强度(AFS)的SAR图像非局部平均(NLM)抑斑新算法(AFS-NLM)。该算法利用Frost滤波图像计算的局部均值与方差来改善SAR图像场景参量的估计,形成了一种能更好刻画SAR图像同质区与边缘区的改进Kuan滤波系数。利用局部均值比与改进Kuan滤波系数分别作为新的相似性测量参量与自适应衰减因子,构建了一种更适应SAR图像乘性噪声特性的改进NLM滤波。利用偏平滑参数与偏边缘保护参数控制下的改进NLM滤波,分别替代经典Kuan滤波模型中的像素局部均值与自身灰度值作为加权项,并采用由改进Kuan滤波系数构建的自适应调节因子对二者进行加权平均,从而形成了一种可自适应调节滤波强度的加权滤波新模型。实验表明,该文算法与近期多种先进算法相比,具有更好的相干斑抑制与边缘保护性能。     

Frequency-domain motion estimation using a complex lapped transform

A frequency-domain algorithm for motion estimation based on overlapped transforms of the image data is developed as an alternative to block matching methods. The complex lapped transform (CLT) is first defined by extending the lapped orthogonal transform (LOT) to have complex basis functions. The CLT basis functions decay smoothly to zero at their end points, and overlap by 2:1 when a data sequence is transformed. A method for estimating cross-correlation functions in the CLT domain is developed. This forms the basis of a motion estimation algorithm that calculates vectors for overlapping, windowed regions of data. The overlapping data window used has no block edge discontinuities and results in smoother motion fields. Furthermore, when motion compensation is performed using similar overlapping regions, the algorithm gives comparable or smaller prediction errors than standard models using exhaustive search block matching, and computational load is lower for larger displacement ranges and block sizes.