Series feature aggregation for content-based image retrieval

Feature aggregation is a critical technique in content-based image retrieval (CBIR) systems that employs multiple visual features to characterize image content. Most previous feature aggregation schemes apply parallel topology, e.g., the linear combination scheme, which suffer from two problems. First, the function of individual visual feature is limited since the ranks of the retrieved images are determined only by the combined similarity. Second, the irrelevant images seriously affect the retrieval performance of feature aggregation scheme since all images in a collection will be ranked. To address these problems, we propose a new feature aggregation scheme, series feature aggregation (SFA). SFA selects relevant images using visual features one by one in series from the images highly ranked by the previous visual feature. The irrelevant images will be effectively filtered out by individual visual features in each stage, and the remaining images are collectively described by all visual features. Experiments, conducted with IAPR TC-12 benchmark image collection (ImageCLEF2006) that contains over 20,000 photographic images and defined queries, have shown that the proposed SFA can outperform conventional parallel feature aggregation schemes.     

摄影测量特征点提取与匹配技术研究

本文重点研究了特征点提取与匹配相关理论及技术。制定了仿真实验方案,通过Matlab编制程序,分析了使用Moravec算子进行特征点提取的特点并证明了基于灰度的匹配算法的有效性。     

基于Word Spotting技术的蒙古文古籍图像检索中的特征选择

设计了一个基于word spotting技术的蒙古文《甘珠尔经》图像检索的系统框架。在充分分析了蒙古文《甘珠尔经》中手写单词图像特点的基础上,提出了采用轮廓特征、投影特征和笔划穿越数目来表示单词图像。在由5500个单词图像构成的数据集上进行对比实验,确定了最佳的特征组合,平均准确率（MAP）能达到78.79%,R-Precision能达到73.01%。实验结果表明,所选择的特征是合理的、有效的。     

基于区域特征提取的景像匹配新算法

提出了一种基于图像区域特征的模糊熵差景像匹配新算法：针对两幅不同时相图像,该方法先进行区域特征提取,然后通过构造模糊熵差匹配度量函数来实现图像的自动匹配。与传统的算法相比,该算法具有明显的抗几何失真和高斯噪声的能力,且实时性也较好,为飞行器实时景像匹配提供了一种可行方法。     

Constructing 3D human model from front and side images

Constructing 3D human model from 2D images provides a cost-effective approach to visualize digital human in virtual environment. This paper presents a systematic approach for constructing 3D human model using the front and side images of a person. The silhouettes of human body are first detected and the feature points on the silhouettes are subsequently identified. The feature points are further used to obtain the body dimensions that are necessary for identifying a template 3D human model. The shape of the template human model can be modified by the free-form deformation method. Moreover, the proposed approach has been applied for constructing the 3D human models of 30 subjects. The comparisons between the constructed 3D models and the 3D scanning models of the 30 subjects indicate that the proposed system is very effective and robust.     

Structural feature-based evaluation method of binarization techniques for word retrieval in the degraded Arabic document images

One of the most important and necessary steps in the process of document analysis and recognition is the binarization, which allows extracting the foreground from the background. Several binarization techniques have been proposed in the literature, but none of them was reliable for all image types. This makes the selection of one method to apply in a given application very difficult. Thus, performance evaluation of binarization algorithms becomes therefore vital. In this paper, we are interested in the evaluation of binarization techniques for the purpose of retrieving words from the images of degraded Arabic documents. A new evaluation methodology is proposed. The proposed evaluation methodology is based on the comparison of the visual features extracted from the binarized document images with ground truth features instead of comparing images between themselves. The most appropriate thresholding method for each image is the one for which the visual features of the identified words in the image are “closer” to the features of the reference words. The proposed technique was used here to assess the performances of eleven algorithms based on different approaches on a collection of real and synthetic images.     

Geometry and construction of straight lines in log-polar images

This paper investigates, how straight lines are mapped to the non-Euclidean log-polar image plane and how their properties in log-polar coordinates can be used to perform two fundamental measurement operations: the construction of straight lines of given orientation angle and the measurement of distances along these lines. It is shown, how the two operations can be efficiently implemented for discrete log-polar images. The usefulness of the developed theory is demonstrated by applying it to different image processing tasks. As a first example, it is used for line and circle detection in log-polar sampled images. As a second example, it is used to construct epipolar lines and perform disparity estimation in log-polar images. Experiments with both synthetic and real images are presented, and the feature detection results are quantitatively evaluated.     

基于小波多尺度分析的图像匹配

提出一种基于小波的多尺度分析的图像特征点提取方法,给出了一种多分辨率分块特征点匹配的图像检索方法,多分辨率的分块策略使得相关反馈的自适应性得到了更好的保证,从而实现图像的快速、准确匹配。实验表明该方法在计算时间和精度上都是十分有效的。     

A multi-plane approach for text segmentation of complex document images

This study presents a new method, namely the multi-plane segmentation approach, for segmenting and extracting textual objects from various real-life complex document images. The proposed multi-plane segmentation approach first decomposes the document image into distinct object planes to extract and separate homogeneous objects including textual regions of interest, non-text objects such as graphics and pictures, and background textures. This process consists of two stages—localized histogram multilevel thresholding and multi-plane region matching and assembling. Then a text extraction procedure is applied on the resultant planes to detect and extract textual objects with different characteristics in the respective planes. The proposed approach processes document images regionally and adaptively according to their respective local features. Hence detailed characteristics of the extracted textual objects, particularly small characters with thin strokes, as well as gradational illuminations of characters, can be well-preserved. Moreover, this way also allows background objects with uneven, gradational, and sharp variations in contrast, illumination, and texture to be handled easily and well. Experimental results on real-life complex document images demonstrate that the proposed approach is effective in extracting textual objects with various illuminations, sizes, and font styles from various types of complex document images.     

A knowledge-based system for extracting text-lines from mixed and overlapping text/graphics compound document images

This paper presents a new knowledge-based system for extracting and identifying text-lines from various real-life mixed text/graphics compound document images. The proposed system first decomposes the document image into distinct object planes to separate homogeneous objects, including textual regions of interest, non-text objects such as graphics and pictures, and background textures. A knowledge-based text extraction and identification method obtains the text-lines with different characteristics in each plane. The proposed system offers high flexibility and expandability by merely updating new rules to cope with various types of real-life complex document images. Experimental and comparative results prove the effectiveness of the proposed knowledge-based system and its advantages in extracting text-lines with a large variety of illumination levels, sizes, and font styles from various types of mixed and overlapping text/graphics complex compound document images.     

A powerful relevance feedback mechanism for content-based 3D model retrieval

The technique of relevance feedback has been introduced to content-based 3D model retrieval, however, two essential issues which affect the retrieval performance have not been addressed. In this paper, a novel relevance feedback mechanism is presented, which effectively makes use of strengths of different feature vectors and perfectly solves the problem of small sample and asymmetry. During the retrieval process, the proposed method takes the user’s feedback details as the relevant information of query model, and then dynamically updates two important parameters of each feature vector, narrowing the gap between high-level semantic knowledge and low-level object representation. The experiments, based on the publicly available 3D model database Princeton Shape Benchmark (PSB), show that the proposed approach not only precisely captures the user’s semantic knowledge, but also significantly improves the retrieval performance of 3D model retrieval. Compared with three state-of-the-art query refinement schemes for 3D model retrieval, it provides superior retrieval effectiveness only with a few rounds of relevance feedback based on several standard measures.

Document retrieval from compressed images

With the emergence of digital libraries, more and more documents are stored and transmitted through the Internet in the format of compressed images. It is of significant meaning to develop a system which is capable of retrieving documents from these compressed document images. Aiming at the popular compression standard-CCITT Group 4 which is widely used for compressing document images, we present an approach to retrieve the documents from CCITT Group 4 compressed document images in this paper. The black and white changing elements are extracted directly from the compressed document images to act as the feature pixels, and the connected components are detected simultaneously. Then the word boxes are bounded based on the merging of the connected components. Weighted Hausdorff distance is proposed to assign all of the word objects from both the query document and the document from database to corresponding classes by an unsupervised classifier, whereas the possible stop words are excluded. Document vectors are built by the occurrence frequency of the word object classes, and the pair-wise similarity of two document images is represented by the scalar product of the document vectors. Nine groups of articles pertaining to different domains are used to test the validity of the presented approach. Preliminary experimental results with the document images captured from students’ theses show that the proposed approach has achieved a promising performance.     

基于同形变换的航空倾斜影像自动匹配方法

针对仿射尺度不变变换提取(ASIFT)算法计算效率低的问题,提出了一种大倾角航空倾斜影像自动匹配方法H-SIFT。该方法利用影像粗略外方位元素计算两幅待匹配影像之间的单应变换矩阵,对左影像进行二维射影变换得到其纠正影像以消除两幅影像之间的几何变形、尺度和旋转问题,再对左影像的纠正影像和右影像进行尺度不变特征变换(SIFT)。匹配时,为了适当提高正确匹配点对的数量,利用不严格的比值提纯法和左右一致性检验得到粗匹配点对,并利用随机一致性检验剔除误匹配。最后将左影像其纠正影像上的匹配点反算到左影像上。通过对国产五倾斜相机平台(SWDC-5)获取的三组典型城区航空倾斜影像数据进行实验,对于三组数据,该算法获得的正确匹配点对数量分别为ASIFT算法的2.18、1.31、1.70倍,该算法匹配耗时分别为ASIFT算法的0.93%、0.88%、0.97%。实验结果表明,与ASIFT算法相比,该算法获得的匹配点对在计算效率、数量和分布情况上都得到了显著提高。     

Coronal loop detection from solar images

In this paper, we make an overview of a methodology for the automatic retrieval of images with coronal loops from the solar image data captured by the extreme-ultraviolet imaging telescope (EIT) onboard the spacecraft SOHO (Solar and Heliospheric Observatory). Our image retrieval system provides relevant data to astrophysicists who need such data to study the coronal heating problem. As part of building this system, we investigated various image preprocessing techniques, image based features, and classifiers to automatically detect coronal loops and to indicate their locations on the images. Despite many challenges related to the coronal loop characteristic, we obtained promising results, namely, 78% precision and 80% recall in loop retrieval.     

一种软／硬模板相结合的定义抽取算法

术语定义抽取是信息抽取研究领域的重要内容之一。文中提出了一种结合硬模板匹配和软模板匹配技术的综合术语定义自动抽取方法。文中首先使用硬模板库对待抽取文本进行了初步的定义句匹配抽取。接着,通过使用基于N元语言模型的软模板匹配模型来计算待匹配文本中每个句子与软模板之间的匹配度,并通过设定匹配得分阈值来抽取定义句或过滤掉错误召回的非定义句。实验结果表明文中的术语定义抽取方法远远优于单纯的硬模板匹配或软模板匹配方法。     

A hybrid probabilistic framework for content-based image retrieval with feature weighting

In this paper, we propose a probabilistic framework for efficient retrieval and indexing of image collections. This framework uncovers the hierarchical structure underlying the collection from image features based on a hybrid model that combines both generative and discriminative learning. We adopt the generalized Dirichlet mixture and maximum likelihood for the generative learning in order to estimate accurately the statistical model of the data. Then, the resulting model is refined by a new discriminative likelihood that enhances the power of relevant features. Consequently, this new model is suitable for modeling high-dimensional data described by both semantic and low-level (visual) features. The semantic features are defined according to a known ontology while visual features represent the visual appearance such as color, shape, and texture. For validation purposes, we propose a new visual feature which has nice invariance properties to image transformations. Experiments on the Microsoft's collection (MSRCID) show clearly the merits of our approach in both retrieval and indexing.     

VISTO: A new CBIR system for vector images

In this paper, we present the main features of VISTO (Vector Image Search TOol), a new content-based image retrieval (CBIR) system for vector images. Though unsuitable for photo-realistic imagery, vector graphics are continually becoming more advanced and diffused. Vector images are fully scalable, resolution independent, not restricted to rectangular shape, allowing layering and editable/searchable text. Notwithstanding this increasing interest, the research area concerning CBIR systems for vectorial images is quite new, and our research on a vector based CBIR system actually derives from a precise request of vector based application experts that did not find appropriate solutions to their retrieval problems in customary shape-based CBIR system. To the best of our knowledge, VISTO is the first CBIR system for vector images proposed in the literature, and it supports the retrieval of images in SVG (scalable vector graphics) format.