A New Model for Automatic Raster-to-Vector Conversion

IEEE Computer, 1992

reating a cartographic database often involves the acquisition of huge amounts of data from paper drawings. The acquisition is usually per-C formed with hand-operated digitizing tablets, following procedures that --_ _ are tKe-consuming, costly, and error-prone. Effective techniques for the auto-matic input of drawings into a database are difficult to implement, and the many The semantics of land register maps drive this document conversion system. However, its methods of image representation, vectorization, and symbol recognition can be generalized to other classes of line drawings. efforts in this direction over the past 20 years have found limited success. Only recently have substantial advances been achieved in this We have developed a system for the automatic acquisition of land register maps. The system converts paper-based documents for the Italian Land Register Authority into digital form for integration into an existing database. Compliance with Land Register Authority standards was a basic design issue. These standards are strictly prescribed, and geometric entities (for example, areas relevant from the viewpoint of land taxation) must be computed within narrow tolerances.

Automatic Vectorisation of Historical Maps: International workshop organized by the ICA Commission on Cartographic Heritage into the Digital. Budapest – 13 March, 2020, 2020

The authors experimented with the open source GIS software QGIS to reveal its possibilities in automatic vectorisation. The target object was a 1 : 200 000 map sheet of the third Austro-Hungarian military survey. Although QGIS provides tools for the main steps of the vectorisation processsuch as colour segmentation of the raster image, skeletoning, vector extraction and vector post-processingusing them on an old map raises several challenges. This paper discusses the results of these experiments, and introduces a few simple python scripts that may help users in the vectorisation process.

2012

Summary This paper is concerned with classification of digitized old maps in the form of raster images. Examples of this classification and its utilization are presented. Web application of raster image classification is introduced as well. The web application can classify both individual images and raster data provided via Web Map Services (WMS) with respect to OGC standards (Open Geospatial Consortium).

Proceedings of the 1st International Workshop on Automatic Vectorization of Historical Maps, 2020

Libraries and researchers face a big challenge: sometimes thousands, millions of maps are being conserved in archives to retard deterioration, but this makes it hard to obtain specific knowledge of their content, sometimes even of their existence. In recent years, the efforts have increased to digitise historical documents and maps to preserve them digitally, make them accessible and allow researchers and the general public a less restricted access to their heritage. But maps are more than a cultural artifact: they are data. Data about the past that can very well be important for science and decision-making today. The problem is, the vast amount alone makes it hard to know what to look for. Maps are usually archived and catalogued with limited meta-information, sometimes obscuring their actual content. This makes it impossible to find specific information without expert knowl-edge on history and cartography. Extracting the content, i.e. data, of scanned historical maps is a necessity to make the content searchable and to use modern digital tools for automatic processing and analyses. To combine data from different maps and compare them with modern geospatial data, georeferencing is paramount. This is usually done by hand and needs a lot of time and spe-cialised training. We explore if and how usable GCP can be found automatically in historical maps with computer vision and document analysis methods of today. In this work-in-progress report, we use OCR on map labels and geocoding of persisting geographical feature designation for successful first experiments. This shows text recognition and vectorisation to be a promising research direc-tion for large-scale automated georeferencing of historical maps.

ISRS Annual Symposium, BMBSTC, Jaipur, INDIA, 2004

With the increasing use of GIS in all spheres of management and planning, it is a mammoth task to acquire the existing graphic knowledge in suitable form. Most of this information is available on paper maps, satellite images, sketches, drawings etc. The vector formats are the most suitable for storing maps and drawings in GIS. To import this information, the vectorisation of scanned maps/satellite maps/drawings is desired. In this paper, we report improved methods for interactive vectorisation using soft computing methods to make the process intelligent as compared to traditional vectorisation. The results of its successful deployment for real maps are provided.

2012

This paper presents a benchmark for evaluating the raster to vector conversion systems. The benchmark is designed for evaluating the performance of graphics recognition systems on images that contain polygons (solid) within the images. Our contribution is two-fold, an object mapping algorithm to spatially locate errors within the drawing and then a cycle graph matching distance that indicates the accuracy of the polygonal approximation. The performance incorporates many aspects and factors based on uniform units while the method remains non-rigid (thresholdless). This benchmark gives a scientific comparison at polygon level of coherency and uses practical performance evaluation methods that can be applied to complete polygonization systems. A system dedicated to cadastral map vectorization was evaluated under this benchmark and its performance results are presented in this paper. By stress testing a given system, we demonstrate that our protocol can reveal strengths and weaknesses of a system. The behavior of our set of indices was analyzed when increasing image degradation. We hope that this benchmark will help assessing the state of the art in graphics recognition and current vectorization technologies.

Graphics Recognition. Recent Advances and Perspectives, 2004

A method to separate and recognize the touching/overlapping alphanumeric characters is proposed. The characters are processed in raster-scanned color cartographic maps. The map is segmented first to extract all text strings including those that are touching other symbols, strokes and characters. Second, OCR-based recognition with Artificial Neural Networks (ANN) is applied to define the coordinates, size and orientation of alphanumeric character strings in each case presented in the map. Third, four straight lines or a number of "curves" computed as a function of primarily recognized by ANN characters are extrapolated to separate those symbols that are attached. Finally, the separated characters input into ANN again to be finally identified. Results showed high method's rendering in the context of raster-to-vector conversion of color cartographic images.

Document Recognition and Retrieval Xvii, 2010

Maps can be a great source of information for a given geographic region, but they can be difficult to find and even harder to process. A significant problem is that many interesting and useful maps are only available in raster format, and even worse many maps have been poorly scanned and they are often compressed with lossy compression algorithms. Furthermore, for many of these maps there is no meta data providing the geographic coordinates, scale, or projection. Previous research on map processing has developed techniques that typically work on maps from a single map source. In contrast, we have developed a general approach to finding and processing street maps. This includes techniques for discovering maps online, extracting geographic and textual features from maps, using the extracted features to determine the geographic coordinates of the maps, and aligning the maps with imagery. The resulting system can find, register, and extract a variety of features from raster maps, which can then be used for various applications, such as annotating satellite imagery, creating and updating maps, or constructing detailed gazetteers.

Journal of Geographic Information System, 2013

Addresses are important data for urban applications. About 80% of the information local authorities use have a geographic component that is generally related to addresses. Addressing systems efficiency depend on the quality of addresses locators. There are several methods to collect data. Surveys from the field are essential: GPS and pre-printed maps can be used to achieve this goal. GPS surveys from the field may be a solution, but it remains practical only for limited areas. To insure an accepted accuracy, GPS methods need special considerations that are time and money consuming. For Casablanca's addressing locators, an alternative approach was adopted to collect 400,000 points. It took two months, 200 operators and 3500 printed maps to cover a study area of 1226 km 2. This paper is to develop an optimized approach based on automated procedure for reintegrating printed maps in a geographic information system (GIS). It saves georeferencing time from 5 min to just seconds per document. It insures, more importantly, an accuracy that is between 20 cm to 1 m for scales that are between 1/500 and 1/2500. It ensures maps' integration, independently of base map and coordinates system by introducing the notion of Georeferencing Code (GC).

2012