Euler vector for search and retrieval of gray-tone images.

A new combinatorial characterization of a gray-tone image called Euler Vector is proposed. The Euler number of a binary image is a well-known topological feature, which remains invariant under translation, rotation, scaling, and rubber-sheet transformation of the image. The Euler vector comprises a 4-tuple, where each element is an integer representing the Euler number of the partial binary image formed by the gray-code representation of the four most significant bit planes of the gray-tone image. Computation of Euler vector requires only integer and Boolean operations. The Euler vector is experimentally observed to be robust against noise and compression. For efficient image indexing, storage and retrieval from an image database using this vector, a bucket searching technique based on a simple modification of Kd-tree, is employed successfully. The Euler vector can also be used to perform an efficient four-dimensional range query. The set of retrieved images are finally ranked on the basis of Mahalanobis distance measure. Experiments are performed on the COIL database and results are reported. The retrieval success can be improved significantly by augmentiong the Euler vector by a few additional simple shape features. Since Euler vector can be computed very fast, the proposed technique is likely to find many applications to content-based image retrieval.     

Computational fractal geometry with WFA

We define two measures of “fractalness” of gray-tone images: the degree of self-similarity and the gray-tone fractal dimension as a generalization of Minkovski dimension of compact sets. We show how to compute both these measures from the WFA-representation of a gray-tone image. Since we have developed a WFA-inference algorithm which computes a good approximation of any gray-tone image we can compute a close approximation of both our measures of fractalness for any gray-tone image. Received: 15 November 1994 / 6 October 1995     

Adaptive Shape Diagrams for Multiscale Morphometrical Image Analysis

Shape diagrams are integral geometric representations in the Euclidean plane introduced to study 2D connected compact sets. Such a set is represented by a point within a shape diagram whose coordinates are morphometrical functionals defined as normalized ratios of geometrical functionals. In addition, the General Adaptive Neighborhoods (GANs) are spatial neighborhoods defined around each point of the spatial support of a gray-tone image, that fit with the image local structures. The aim of this paper is to introduce and study the GAN-based shape diagrams, which allow a gray-tone image morphometrical analysis to be realized in a local, adaptive and multiscale way. The GAN-based shape diagrams will be illustrated on standard images and also applied in the biomedical and materials areas.     

A unified approach to the change of resolution: space and gray-level

It is shown that by defining a suitable measure for the comparison of images, changes in resolution can be treated with the same tool as changes in color resolution. A gray-tone image, for example, can be compared to a half-tone image having only two colors (black and white), but of higher spatial resolution. A graph-theoretical definition of the basic measure used is introduced. This is followed by application to spatial resampling and gray-level requantization. This results in a hybrid treatment of resolution, and the possibility of trading spatial for gray-level resolution and vice versa.<>     

基于组合欧拉向量与边缘方向直方图的图像检索方法

在图像数据库中,如何有效检索和查询图像是一个重要的研究内容.文中提出一种结合组合欧拉向量与边缘方向直方图( EOH)的图像检索方法.首先,从边缘图像中提取组合欧拉向量特征进行图像检索(EEXO算法),其次,为更好地区分不同形状但欧拉特征相近的图像,将EEXO算法与EOH算法相结合提出EEXOEOH图像检索算法.实验结果表明,EEXOEOH算法与其它4种算法相比,具有较好的检索效率.     

AS-OCT图像下的自动皮质性白内障分类框架

白内障是一种主要导致视觉损伤的眼病. 早期干预和白内障手术是改善患者视力和生活质量的主要手段. 眼前节光学相干断层成像图像 (anterior segment optical coherence tomography, AS-OCT) 是一种新型眼科图像, 其具有非接触、高分辨率、检查快速等特点. 在临床上, 眼科医生已经逐渐采用AS-OCT图像进行眼科疾病如青光眼的诊断, 然而尚未有研究工作利用它进行皮质性白内障 (cortical cataract, CC) 自动分类. 为此, 提出了一个基于AS-OCT图像的自动皮质性白内障分类框架, 由图像预处理、特征提取、特征筛选和分类等4部分组成. 首先, 利用反光区域去除和对比度增强方法进行图像预处理; 紧接着使用灰度共生矩阵 (grey level co-occurrence matrix, GLCM)、灰度区域大小矩阵 (grey level size zone matrix, GLSZM) 和邻域灰度差矩阵 (neighborhood grey tone difference matrix, NGTDM) 方法从皮质区域提取了22个特征; 然后, 采用斯皮尔曼相关系数方法对提取的特征进行特征重要性分析并筛除冗余特征; 最后利用线性支持向量机方法进行分类. 在一个临床AS-OCT图像数据集上的实验结果表明, 所提出的皮质性白内障分类框架准确率、召回率、精确率和F1分别达到86.04%, 86.18%, 88.27%和86.35%, 取得与先进的深度学习算法接近的性能, 表明其具有作为辅助眼科医生进行皮质性白内障临床诊断工具的潜力.     

A new approach of color images segmentation based on fusing region and edge segmentations outputs

Image segmentation requires processing of a huge volume of data. It is therefore necessary, for their implementation in industrial computer controlled systems, to search for straightforward algorithms. Presently, literature offers a lot of gray-tone image segmentation techniques, but few of them attend to color image segmentation. This paper presents a co-operative strategy within a multi-resolution color image segmentation, which attempt to extract the meaningful information (regions and boundaries), then fuse these two approaches in order to achieve an accurate, robust and suitable segmentation. A blob filling coloration algorithm allows to design, from the segmented image, a synthesis image which appears as a simplified but faithfull copy with a chosen resolution of the original image. This process is induced by approach of the human psychovisual system of perception, tender to the sharp edges, strong contrasts and large areas of color. It gives good results when applied on natural scenes, like a bunch of flowers, or on artificial scenes, like a set of building blocks. As possible, we use the coding vocabulary of R.M. Haralick.     

A new run-based algorithm for Euler number computing

The Euler number of a binary image is an important topological feature for many image processing, image analysis, pattern recognition, and computer vision applications. This paper proposes a new run-based Euler number computation algorithm. The conventional run-based algorithm processes rows of the given image one-by-one from top to bottom in a single phase. For each row, it finds the runs in the row and records the start and end locations of each run to compute neighbor runs. In contrast, our algorithm calculates the Euler number of an image in two phases. In the first phase, we process odd rows alternately to find runs and only record its end location. In the second phase, we process each of the remaining even rows to find runs and calculate neighboring runs between the current row and the rows immediately above and below using the recorded run data. Using this method, the number of accesses required to compute the Euler number decreases in almost all cases. Analysis of the time complexity and experimental results demonstrate that our algorithm outperforms conventional Euler number computation algorithms.     

A proof of image Euler Number formula

1 Introduction In digital image, topological invariant refers to the value, which can keep the image characteristics unchanged when the image flexes freely just like the elastic rubber. The Euler Number is one of the topological characteristics, which can…     

An Application of Fuzzy Mathematical Morphology to Interval-Valued Knowledge Representation: A Remark

Mathematical morphology is known by its useful tools for processing binary (black-and-white) and gray-tone images. Due to the success of mathematical morphology in processing binary images, there have been many successful attempts to generalize its methods to more general, i.e. gray-tone images. One of these attempts—the most intuitive one is based on replacing sets by fuzzy sets, thus defining so called fuzzy morphological operations. In this paper we show that these operations can be used successfully in nonimage applications. We can use methods developed in fuzzy mathematical morphology to compute the membership functions of different "approximate" statements. Also, an application to interval-valued knowledge representation is given.     

关于三维图像Euler数新公式的证明

图像欧拉数是数字拓扑学的重要特征参数之一,计算图像欧拉数的方法被不断探索更新。为了更好理解三维图像欧拉数的本质和方便计算三维图像的欧拉数,通过对三维图像连通性的深入研究,在定义三维图段和三维相邻数两个基本概念的基础上,提出局部计算三维图像欧拉数的公式和计算三维相邻数的方法,并用归纳法证明该公式与全局计算公式的等价性。不同于以往对像素和连通性的描述,为局部计算三维图像的欧拉数提供新途径。     

Improving Iris Recognition Performance Using Segmentation, Quality Enhancement, Match Score Fusion, and Indexing

This paper proposes algorithms for iris segmentation, quality enhancement, match score fusion, and indexing to improve both the accuracy and the speed of iris recognition. A curve evolution approach is proposed to effectively segment a nonideal iris image using the modified Mumford–Shah functional. Different enhancement algorithms are concurrently applied on the segmented iris image to produce multiple enhanced versions of the iris image. A support-vector-machine-based learning algorithm selects locally enhanced regions from each globally enhanced image and combines these good-quality regions to create a single high-quality iris image. Two distinct features are extracted from the high-quality iris image. The global textural feature is extracted using the 1-D log polar Gabor transform, and the local topological feature is extracted using Euler numbers. An intelligent fusion algorithm combines the textural and topological matching scores to further improve the iris recognition performance and reduce the false rejection rate, whereas an indexing algorithm enables fast and accurate iris identification. The verification and identification performance of the proposed algorithms is validated and compared with other algorithms using the CASIA Version 3, ICE 2005, and UBIRIS iris databases.      

An Algorithm for Connected-Component Labeling, Hole Labeling and Euler Number Computing

Labeling connected components and holes and computing the Euler number in a binary image are necessary for image analysis, pattern recognition, and computer (robot) vision, and are usually made independently of each other in conventional methods. This paper proposes a two-scan algorithm for labeling connected components and holes simultaneously in a binary image by use of the same data structure. With our algorithm, besides labeling, we can also easily calculate the number and the area of connected components and holes, as well as the Euler number. Our method is very simple in principle, and experimental results demonstrate that our method is much more efficient than conventional methods for various kinds of images in cases where both labeling and Euler number computing are necessary.     

Generating cubical complexes from image data and computation of the Euler number

A number of tasks in image processing and computer vision require the computation of certain topological characteristics of objects in a given image. In this paper, we introduce a new method based on the notion of the algebraic topology complex to compute the Euler number of a given object. First, we attach a cubical complex to the object of interest, then we associate an algebraic structure on which a number of simplifying operations preserving the topology but not necessarily the geometric nature of the complex are possible. This is a unifying dimension independent approach. We show that the Euler number can be obtained directly from the cubical structure or one can perform a collapsing operation that allows to reduce the given image to a lower dimension structure with equivalent topological properties. This reduced structure can be used in a further process, in particular, for the computation of the Euler number.     

A fast algorithm for integrating connected-component labeling and euler number computation

This paper proposes a fast algorithm for integrating connected-component labeling and Euler number computation. Based on graph theory, the Euler number of a binary image in the proposed algorithm is calculated by counting the occurrences of four patterns of the mask for processing foreground pixels in the first scan of a connected-component labeling process, where these four patterns can be found directly without any additional calculation; thus, connected-component labeling and Euler number computation can be integrated more efficiently. Moreover, when computing the Euler number, unlike other conventional algorithms, the proposed algorithm does not need to process background pixels. Experimental results demonstrate that the proposed algorithm is much more efficient than conventional algorithms either for calculating the Euler number alone or simultaneously calculating the Euler number and labeling connected components.     

A new approach to computing the Euler characteristic

In this paper we describe a new approach to computing the Euler characteristic of a three dimensional digital image. Our approach is based on computing the change in numbers of black components, tunnels and cavities in 3 × 3 × 3 neighborhood of an object (black) point due to its deletion. The existing algorithms to computing the Euler characteristic of a 3D digital image are based on counting the numbers of all k-dimensional elements (0 ≤ k ≤ 3) in a polyhedral representation of the image. Our approach can be modified for (6,26), (18,6), (6,18) and other connectivity relations of grid points. A parallel implementation of the algorithm is described using the concept of sub-fields.     

High-quality images on electrophoretic displays

Abstract— High-resolution micro-encapsulated active-matrix electrophoretic displays showing 2-bit gray-tone images and text with high contrast and high reflectance are commercially available. Methods of realizing high-quality images on these displays will be covered in this paper.     

一种二值图象欧拉数的并行快速算法

本文给出了一个求方格(square grid)上二值化图象欧拉数的并行快速算法,并通过将方格上的二值图象转化成数字图来引用图论方法对该算法进行了证明,且给出了若干实例以说明算法的有效性.     

Fabrication of relief-topographic surfaces with a one-step UV-lithographic process

This paper reports on a study of a methodology for fabrication of arbitrarily shaped silicon structures using technologies common to standard IC manufacturing processes. Particular emphasis is put on the design and use of halftone transmission masks for the lithography step required in the fabrication process of mechanical, optical or electronics components. The design and experimental investigation of gray-tone masks was supported by lithography simulation. Results are presented for both, simulated gray-tone patterns as well as experimental profiles.     

A fast algorithm to calculate the Euler number for binary images

A parallel localized algorithm to calculate the Euler number of a given binary image on a square grid, is presented. The algorithm is proven by employing graph theory. Examples are given to show the validity of the algorithm.