Nonlinear model and constrained ML for removing back-to-front interferences from recto–verso documents

In this paper, we approach the removal of back-to-front interferences from scans of double-sided documents as a blind source separation problem, and extend our previous linear mixing model to a more effective nonlinear mixing model. We consider the front and back ideal images as two individual patterns overlapped in the observed recto and verso scans, and apply an unsupervised constrained maximum likelihood technique to separate them. Through several real examples, we show that the results obtained by this approach are much better than the ones obtained through data decorrelation or independent component analysis. As compared to approaches based on segmentation/classification, which often aim at cleaning a foreground text by removing all the textured background, one of the advantages of our method is that cleaning does not alter genuine features of the document, such as color or other structures it may contain. This is particularly interesting when the document has a historical importance, since its readability can be improved while maintaining the original appearance.     

Nonlinear model identification and see-through cancelation from recto–verso data

The problem of see-through cancelation in digital images of double-sided documents is addressed. We show that a nonlinear convolutional data model proposed elsewhere for moderate show-through can also be effective on strong back-to-front interferences, provided that the recto and verso pure patterns are estimated jointly. To this end, we propose a restoration algorithm that does not need any classification of the pixels. The see-through PSFs are estimated off-line, and an iterative procedure is then employed for a joint estimation of the pure patterns. This simple and fast algorithm can be used on both grayscale and color images and has proved to be very effective in real-world cases. The experimental results we report in this paper demonstrate that our algorithm outperforms the ones based on linear models with no need to tune free parameters and remains computationally inexpensive despite the nonlinear model and the iterative solution adopted. Strategies to overcome some of the residual difficulties are also envisaged.     

文本页面图像的图文分割与分类算法

为了能对包含不规则图片区和表格的倾斜文本页面图像进行图文分割与分类，提出了一种新的图文分割和分类算法。该算法先采用数学形态学和分级霍夫变换来进行文本倾斜的检测和校正；然后为了使算法能够对包含不规则图片区的文本页面图像进行处理，提出在传统的投影轮廓切割算法中，引入中点切割的过程，以便利用一系列的矩形来近似地逼近不规则的图片区。对于分割后的图像，则提出利用黑白像素比(Rbw)和近邻像素间的交叉相关性(Rcc)两个特征来作为分类的判据。实验结果证明，算法速度快、可靠性高。该算法只适用于二值图像。     

Subpixel edge estimation

This paper compares several methods of computing the locations of edges (or lines) in an image to subpixel accuracy. It is found that methods taking the intensities of the edge pixels into account yield little or no improvement over a simple method of least-squares estimation based only on the locations of these pixels.     

Convex hull based skew estimation

Skew estimation and page segmentation are the two closely related processing stages for document image analysis. Skew estimation needs proper page segmentation, especially for document images with multiple skews that are common in scanned images from thick bound publications in 2-up style or postal envelopes with various printed labels. Even if only a single skew is concerned for a document image, the presence of minority regions of different skews or undefined skew such as noise may severely affect the estimation for the dominant skew. Page segmentation, on the other hand, may need to know the exact skew angle of a page in order to work properly. This paper presents a skew estimation method with built-in skew-independent segmentation functionality that is capable of handling document images with multiple regions of different skews. It is based on the convex hulls of the individual components (i.e. the smallest convex polygon that fully contains a component) and that of the component groups (i.e. the smallest convex polygon that fully contain all the components in a group) in a document image. The proposed method first extracts the convex hulls of the components, segments an image into groups of components according to both the spatial distances and size similarities among the convex hulls of the components. This process not only extracts the hints of the alignments of the text groups, but also separate noise or graphical components from that of the textual ones. To verify the proposed algorithms, the full sets of the real and the synthetic samples of the University of Washington English Document Image Database I (UW-I) are used. Quantitative and qualitative comparisons with some existing methods are also provided.     

双边滤波的改进高光去除

目的 由于非均匀光照条件下,物体表面通常出现块状的强反射区域,传统的去高光方法在还原图像时容易造成颜色失真或者边缘的丢失。针对这些缺点,提出一种改进的基于双边滤波的去高光方法。方法 首先通过双色反射模型变换得到镜面反射分量与最大漫反射色度之间的转换关系,然后利用阈值将图像的像素点分为两类,将仅含漫反射分量的像素点与含有镜面反射分量的像素点分离开来,对两类像素点的最大漫反射色度分别做估计,接着以估计的最大漫反射色度的相似度作为双边滤波器的值域,同时以图像的最大色度图作为双边滤波的引导图保边去噪,进而达到去除镜面反射分量的目的。结果 以经典的高光图像作为处理对象,对含有镜面反射和仅含漫反射的像素点分别做最大漫反射色度估计,再以该估计图作为双边滤波的引导图,不仅能去除镜面反射分量还能有效的保留图像的边缘信息,最大程度的还原图像细节颜色,并且解决了原始算法处理结果中R、G、B三通道相似的像素点所出现的颜色退化问题。用改进的双边滤波去高光算法对50幅含高光的图像做处理,并将该算法与Yang方法和Shen方法分别作对比,结果图的峰值信噪比（PSNR）也分别平均提高4.17%和8.40%,所提算法的处理效果更符合人眼视觉,图像质量更好。结论 实验结果表明针对含镜面反射的图像,本文方法能够更有效去除图像的多区域局部高光,完成对图像的复原,可为室内外光照不匀情况下所采集图像的复原提供有效理论基础。     

Watermark location via back-lighting modelling and verso registration

We consider the location of paper watermarks in documents that present problems such as variable paper thickness, stain and other damage. Earlier work has shown success in exploiting a computational model of backlit image acquisition – here we enhance this approach by incorporating knowledge of surface verso features. Robustly removing recto features using established techniques, we present a registration approach that permits similarly robust removal of verso, leaving only features attributable to watermark, folds, chain lines and inconsistencies of paper manufacture. Experimental results illustrate the success of the approach.     

Adaptive hypergraph superpixels

Superpixel segmentation, which amounts to partitioning an image into a number of superpixels each of which is a set of pixels sharing common visual meanings, requires specific needs for different computer vision tasks. Graph based methods, as a kind of popular superpixel segmentation method, regard an image as a weighted graph whose nodes correspond to pixels of the image, and partition all pixels into superpixels according to the similarity between pixels over various feature spaces. Despite their improvement of the performance of segmentation, these methods ignore high-order relationship between them incurred from either locally neighboring pixels or structured layout of the image. Moreover, they measure the similarity of pairwise pixels using Gaussian kernel where a robust radius parameter is difficult to find for pixels which exhibit multiple features (e.g., texture, color, brightness). In this paper, we propose an adaptive hypergraph superpixel segmentation (AHS) of intensity images for solving both issues. AHS constructs a hypergraph by building the hyperedges with an adaptive neighborhood scheme, which explores an intrinsic relationship of pixels. Afterwards, AHS encodes the relationship between pairwise pixels using characteristics of current two pixels as well as their neighboring pixels defined by hyperedges. Essentially, AHS models the relationship of pairwise pixels in a high-order group fashion while graph based methods evaluate it in a one-vs-one fashion. Experiments on four datasets demonstrate that AHS achieves higher or comparable performance compared with state-of-the-art methods.     

基于图论的边缘提取方法

针对传统边缘方法提取的边缘具有不连续、不完整、倾斜、抖动和缺口等问题,提出基于图论的边缘提取方法。该方法视像素为节点,在水平或垂直方向上连接两个相邻的节点构成一个边,从而将图像看作无向图。它包括三个阶段：在像素相似性计算阶段,无向图的边上被赋予权值,权值代表了像素间的相似性;在阈值确定阶段,将所有权值的均值（整幅图像的相似度）确定为阈值;在边缘确定阶段,只保留权值小于阈值的水平边的左边节点与垂直边的上边节点,从而获得了图像的边缘。实验表明,该方法适用于具有明显目标与背景的图像的边缘提取,能够克服不连续、不完整、倾斜、抖动和缺口等缺陷,并且对Speckle噪声和高斯噪声具有抗噪性能。     

航拍图像中运动车辆的检测与定位

提出了一种利用Huber函数和均匀稀疏采样估计仿射变换参数的方法，更加准确快速地进行背景运动补偿,为了克服噪声和和伪运动区域对运动目标定位的干扰，利用形态学滤波方法去除法照变化带来的伪运动区域及噪声。最后，采用仿射运动矢量聚类方法对运动目标进一步可靠定位，结合这3种方法，可以对航拍图像序列中的运动目标快速准确地检测与定位。     

Detection of moving foreground objects in videos with strong camera motion

In this paper, we propose a novel method for moving foreground object extraction in sequences taken by a wearable camera, with strong motion. We use camera motion compensated frame differencing, enhanced with a novel kernel-based estimation of the probability density function of background pixels. The probability density functions are used for filtering false foreground pixels on the motion compensated difference frame. The estimation is based on a limited number of measurements; therefore, we introduce a special, spatio-temporal sample point selection and an adaptive thresholding method to deal with this challenge. Foreground objects are built with the DBSCAN algorithm from detected foreground pixels.     

A new document representation using term frequency and vectorized graph connectionists with application to document retrieval

This paper presents a new document representation with vectorized multiple features including term frequency and term-connection-frequency. A document is represented by undirected and directed graph, respectively. Then terms and vectorized graph connectionists are extracted from the graphs by employing several feature extraction methods. This hybrid document feature representation more accurately reflects the underlying semantics that are difficult to achieve from the currently used term histograms, and it facilitates the matching of complex graph. In application level, we develop a document retrieval system based on self-organizing map (SOM) to speed up the retrieval process. We perform extensive experimental verification, and the results suggest that the proposed method is computationally efficient and accurate for document retrieval.     

一种具有抗噪性的图像分割方法

基于图论的图像分割方法对有噪声污染的图像必须先进行预处理,算法自身不能抑制噪声。针对该问题,提出一种具有抗噪性的图像分割方法。该方法将图谱划分测度作为划分目标与背景的阈值分割准则,采用基于灰度值的权值矩阵代替基于图像像素个数的权值矩阵,描述像素之间的关联,并在图权计算中增加像素点与其邻域的空间相关信息,以提高算法的抗噪性。实验结果表明,使用该方法进行图像分割具有较好的分割效果,抑制噪声能力较强。     

专家证据文档识别无向图模型

专家证据文档识别是专家检索的关键步骤.融合专家候选文档独立页面特征以及页面之间的关联关系,提出了一个专家证据文档识别无向图模型.该方法首先分析各类专家证据文档中的词、URL 链接、专家元数据等独立页面特征以及候选专家证据文档间的链接和内容等关联关系;然后将独立页面特征以及页面之间的关联关系融入到无向图中构建专家证据文档识别无向图模型;最后利用梯度下降方法学习模型中特征的权重,并利用吉布斯采样方法进行专家证据文档识别.通过对比实验验证了该方法的有效性.实验结果表明,该方法有较好的效果.     

Hyperspectral image classification using graph-based wavelet transform

ABSTRACT

Graph-based methods are developed to efficiently extract data information. In particular, these methods are adopted for high-dimensional data classification by exploiting information residing on weighted graphs. In this paper, we propose a new hyperspectral texture classifier based on graph-based wavelet transform. This recent graph transform allows extracting textural features from a constructed weighted graph using sparse representative pixels of hyperspectral image. Different measurements of spectral similarity between representative pixels are tested to decorrelate close pixels and improve the classification precision. To achieve the hyperspectral texture classification, Support Vector Machine is applied on spectral graph wavelet coefficients. Experimental results obtained by applying the proposed approach on Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) datasets provide good accuracy which could exceed 98.7%. Compared to other famous classification methods as conventional deep learning-based methods, the proposed method achieves better classification performance. Results have shown the effectiveness of the method in terms of robustness and accuracy.     

Mean-Shift segmentation and PDE-based nonlinear diffusion: toward a common variational framework for foreground/background document image segmentation

The presence of noise in images of degraded documents limits the direct application of segmentation approaches and can lead to the presence of a number of different artifacts in the final segmented image. A possible solution is the integration of a pre-filtering step which may improve the segmentation quality through the reduction of such noise. This study demonstrated that combining the Mean-Shift clustering algorithm and the tensor-driven diffusion process into a joint iterative framework produced promising results. For instance, this framework generates segmented images with reduced edge and background artifacts when compared to results obtained after applying each method separately. This improvement is explained by the mutual interaction of global and local information, introduced, respectively, by the Mean-Shift and the anisotropic diffusion. Another point of note is that the anisotropic diffusion process smoothed images while preserving edge continuities. The convergence of this framework was defined automatically under a stopping criterion not previously defined when the diffusion process was applied alone. To obtain a fast convergence, the common framework utilizes the speedup algorithm of the Fukunaga and Hostetler Mean-Shift formulation already proposed by Lebourgeois et al. (International Conference on Document Analysis and Recognition (ICDAR), pp 52–56, 2013). This new variant of the Mean-Shift algorithm produced similar results to the original one, but ran faster due to the application of the integral volume. The first application of this framework was document ink bleed-through removal where noise is stemmed from the interference of the verso side on the recto side, thus perturbing the legibility of the original text. Other categories of images could also be subjected to the proposed framework application.     

Abstractive Text Summarization based on Improved Semantic Graph Approach

The goal of abstractive summarization of multi-documents is to automatically produce a condensed version of the document text and maintain the significant information. Most of the graph-based extractive methods represent sentence as bag of words and utilize content similarity measure, which might fail to detect semantically equivalent redundant sentences. On other hand, graph based abstractive method depends on domain expert to build a semantic graph from manually created ontology, which requires time and effort. This work presents a semantic graph approach with improved ranking algorithm for abstractive summarization of multi-documents. The semantic graph is built from the source documents in a manner that the graph nodes denote the predicate argument structures (PASs)—the semantic structure of sentence, which is automatically identified by using semantic role labeling; while graph edges represent similarity weight, which is computed from PASs semantic similarity. In order to reflect the impact of both document and document set on PASs, the edge of semantic graph is further augmented with PAS-to-document and PAS-to-document set relationships. The important graph nodes (PASs) are ranked using the improved graph ranking algorithm. The redundant PASs are reduced by using maximal marginal relevance for re-ranking the PASs and finally summary sentences are generated from the top ranked PASs using language generation. Experiment of this research is accomplished using DUC-2002, a standard dataset for document summarization. Experimental findings signify that the proposed approach shows superior performance than other summarization approaches.     

Label relaxation using a linear mixture model

Abstract

A label relaxation method with a proportional estimation of mixed pixels (mixels) which is based on inversion problem solving techniques with a previously estimated proportion of neighbouring mixels is proposed. The method allows us to check the connectivity of separated road segments which arc observed frequently in the remote sensing satellite imagery. The experimental results with simulation data including observation noise show 73·5-98·8 per cent of improvement in terms of proportional estimation accuracy (RMS error), compared to the results from the previously proposed method with a generalized inverse matrix. Also the usefulness of the proposed label relaxation method with the proposed proportional estimation was confirmed for the investigation of the connectivity of the roads in the remote sensing satellite imagery.     

NERank+: a graph-based approach for entity ranking in document collections

Most entity ranking research aims to retrieve a ranked list of entities from a Web corpus given a user query. The rank order of entities is determined by the relevance between the query and contexts of entities. However, entities can be ranked directly based on their relative importance in a document collection, independent of any queries. In this paper, we introduce an entity ranking algorithm named NERank+. Given a document collection, NERank+ first constructs a graph model called Topical Tripartite Graph, consisting of document, topic and entity nodes. We design separate ranking functions to compute the prior ranks of entities and topics, respectively. A meta-path constrained random walk algorithm is proposed to propagate prior entity and topic ranks based on the graph model.We evaluate NERank+ over real-life datasets and compare it with baselines. Experimental results illustrate the effectiveness of our approach.