The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This is an overview paper that describes methods used in graphics recognition from the stage of the initial scanned image to that of the graphics features. The objective is to give context and background to the papers in this section — and, because it is introductory material — to the rest of the papers in this book. Methods are described under the categories of: pixel-level processing, line-level...
It is proposed that the performance of thinning algorithms be evaluated with reference to a task which is especially relevant in connection with the use of these algorithms in the application domain of document processing: decomposition of digital lines into meaningful parts. The stability of the decompositions obtained according to simple rules, within given classes of lines, is assumed as a performance...
Though many methods have been proposed for the detection of dominant points from digital curves, comparisons of general performance have seldom attempted, nor the advantages and disadvantages of each method have been investigated. As a case study of performance evaluation of image processing algorithms, this report describes the results of comparing 11 dominant point detection methods, from two aspects:...
We present a fast method for finding horizontal lines in run length encoded images. The method was motivated by the need for quick and reliable detection of horizontal lines in an interactive drawing conversion system for telephone company drawings. At the core of the algorithm are the processes of filtering run lengths, assembling filtered run lengths, generating top silhouette, and thresholding...
We consider the problem of recognizing line drawings like cadastral maps or technical drawings. We examine the vectorization (raster-to-vector process) of systems for solving this type of recognition problem and propose a solution that identifies and localizes graphical primitives. We claim that geometric constraints should be brought into the vectorization process and we give details on how we combine...
This paper presents a methodology for measuring the performance of application-specific raster-to-vector conversion algorithms. In designing and building image analysis systems, comparison of several algorithms is often required. Unfortunately, many methods of comparison do not give quantitative performance measurements, but rather qualitative, and often subjective, evaluations. Our key observation...
This paper presents an item searching method which has been applied to various kinds of forms. This approach is based on line detection through the Hough transform. After obtaining the straight lines, Hough directions are used to detect the real segments in the image. Segments can correspond either to continuous line, or to black parts of dashed or dotted lines. So, the segments are grouped together...
We discuss our system of model-based analysis of printed tables. The goal of our system is to extract and associate parts of a table's image into related segments. For example, we can locate columns, rows, column and table headings of a table's image. The location of these segments are based on features of the table image and on a model of the table. This is a stepwise, top-down approach to table...
New directional morphological operators that have accurate selectivity and controllable strictness, are defined and applied to dashed lines detection and labeling. The proposed approach is based on adaptation of the directions and dimensions of newly defined tube-directional morphological operators to local characteristics of the data. The separation of maps and line drawings, into four images containing...
The field of diagram recognition faces many challenges, including the great diversity in diagrammatic notations, and the presence of noise and ambiguity during the recognition process. To help address these problems, research is needed into methods for acquiring, representing, and exploiting notational conventions. We review several frameworks for diagram recognition: blackboard systems, schema-based...
In this paper, we propose a system for the recognition and the automatic learning of hand-drawn graphic symbols in engineering drawings. The graphic symbols and the drawings are represented by attributed relational graphs. The recognition process is formulated as a search process for error-tolerant subgraph isomorphisms from the symbol graphs to the drawing graph. In the beginning, there is a limited...
This paper addresses the problem of locating and recognizing graphic items in document images. The proposed approach allows us to recognize such items also in the presence of high noise, scaling, and rotation. This is accomplished by a hybrid model which performs graphic item location by morphological operations and connected component analysis, and item recognition by a proper connectionist model...
Chemical structure diagrams, just as in engineering drawings, maps, and other technical diagrams, consist of solid and dashed lines (bonds), characters (atom symbols), and other symbols such as brackets, parentheses, wedges (stereo-up bonds) or dashed wedges (stereo-down bonds). In addition to recognizing these low-level elements of such drawings, other artifacts may be present — bonds intersections...
In this paper, a knowledge-based framework for the top-down interpretation and segmentation of maps is presented. The interpretation is based on a priori knowledge about map objects, their mutual spatial relationships and potential segmentation problems. To reduce computational costs, a global segmentation is used when possible, but an applicable top-down segmentation strategy is chosen when errors...
In this paper, we describe an automatic region labeling method, which identifies each region and recognizes region names. Before tracing the region boundaries, it extracts the region names which consist of characters, dots, dashes, and indication lines. It uses two recognition methods to recognize characters in the region name. In the case of recognizing the isolated characters, it uses the open and...
Existing systems for converting maps to an object-oriented form suitable for a geographic information system (GIS) are only partially automated. Most published approaches for automated interpretation of raster-scanned maps assume that the map is composed of various graphic entities, and that the vast majority of pixel positions on the map each belong to only one type of graphic entity and can therefore...
Recognition of dimensioning text in engineering drawings is an essential part of the dimension understanding process, since this text is an important component of the dimension-set. We first introduce the OPD expression of the structural relations among the dimension-set components and the illustration of ISO and ANSI drafting standards. We then present principles and implementation of a method of...
The effective computer interpretation of engineering drawing remains a desirable aim yet it continues to provide academic challenge. Much early work was concerned with the interpretation of low level vectorised data. For simple drawings, direct association and interpretation of the low level data often provides a very effective technique but drawing data, whether linework or higher level textual information,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.