ON THE RECONSTRUCTION OF SEMANTIC DATA IN RASTER MAP IMAGES

2001

Semantic analysis of cartographic images is interpreted as a separate representation of cartographic patterns (alphanumeric, punctual, linear, and area). We present an approach to map interpretation exploring the idea of synthesis of invariant graphic images at low level processing (vectorization and segmentation). This means that we ran “vectorization-recognition” and “segmentation-interpretation” systems simultaneously. Although these systems can generate some errors in interpretation, they are much more useful for the following understanding algorithms because its output is nearly recognized objects of interest.

Lecture Notes in Computer Science, 2010

A colour image segmentation (CIS) process for scanned historical maps is presented to overcome common problems associated with segmentation of old documents such as (1) variation in colour values of the same colour layer within one map page, (2) differences in typical colour values between homogeneous areas and thin line-work, which belong both to the same colour layer, and (3) extensive parameterization that results in a lack of robustness. The described approach is based on a two-stage colour layer prototype search using a constrained sampling design. Global colour layer prototypes for the identification of homogeneous regions are derived based on colour similarity to the most extreme colour layer values identified in the map page. These global colour layer prototypes are continuously adjusted using relative distances between prototype positions in colour space until a reliable sample is collected. Based on this sample colour layer seeds and directly connected neighbors of the same colour layer are determined resulting in the extraction of homogeneous colour layer regions. In the next step the global colour layer prototypes are recomputed using a new sample of colour values along the margins of identified homogeneous coloured regions. This sampling step derives representative prototypes of map layer sections that deviate significantly from homogeneous regions of the same layers due to bleaching, mixed or false colouring and ageing of the original scanned documents. A spatial expansion process uses these adjusted prototypes as start criterion to assign the remaining colour layer parts. The approach shows high robustness for map documents that suffer from low graphical quality indicating some potential for general applicability due to its simplicity and the limited need for preliminary information. The only input required is the colours and number of colour layers present in the map.

2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System, 2007

We propose a statistical filter using a context tree modeling. The idea of context tree is to perform selective context expansion including only those pixel combinations that really appear in the image. This makes it possible to use much larger spatial neighborhood. The proposed context tree filtering is evaluated for a set of indexed-color raster map images corrupted with generated impulsive and content-dependent noise. The objective evaluation shows improvement of 15% for content-dependent noise and up to 30% for impulsive noise comparing to the closest competitor. Visual comparisons show that the spatial structures are preserved better than by vector median, morphological and peer group averaging filter.

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.

IEEE Transactions on Image Processing, 2007

Significant lossless compression results of color map images have been obtained by dividing the color maps into layers and by compressing the binary layers separately using an optimized context tree model that exploits interlayer dependencies. Even though the use of a binary alphabet simplifies the context tree construction and exploits spatial dependencies efficiently, it is expected that an equivalent or better result would be obtained by operating directly on the color image without layer separation. In this paper, we extend the previous context-tree-based method to operate on color values instead of binary layers. We first generate an n-ary context tree by constructing a complete tree up to a predefined depth, and then prune out nodes that do not provide compression improvements. Experiments show that the proposed method outperforms existing methods for a large set of different color map images

An algorithm for lossy compression of scanned map images is proposed. The algorithm is based on color quantization, efficient statistical context tree modeling and arithmetic coding. The ratedistortion performance is evaluated on a set of scanned maps and compared to JPEG2000 lossy compression algorithm, and to ECW, which is a commercially available solution for compression of satellite and aerial images. The proposed algorithm outperforms these competitors in rate-distortion sense for the most part of the operational rate-distortion curve.

IEEE Transactions on Geoscience and Remote Sensing, 1994

In a standard image coding scenario, pixel-to-pixel correlation nearly always exists in the data, especially if the image is a natural scene. This correlation is what allows predictive coding schemes (e.g., DPCM) to perform efficient compression. In a color-mapped image, the values stored in the pixel array are no longer directly related to the pixel intensity. Two color indices which are numerically adjacent (close) may point to two very different colors. The correlation still exists, but only via the colormap. This fact can be exploited by sorting the color map to reintroduce the structure. In this paper we study the sorting of colormaps and show how the resulting structure can be used in both lossless and lossy compression of images.

2011

There is a growing need for automatic digitizing, or so called automated raster to vector conversion (ARVC) for maps. The benefit of ARVC is the production of maps that consume less space and are easy to search for or retrieve information from. In addition, ARVC is the fundamental step to reusing old maps at higher level of recognition. In this paper, a new model for an ARVC is developed. The proposed model converts the "paper maps" into electronic formats for Geographic Information Systems (GIS) and evaluates the performance of the conversion process. To overcome the limitations of existing commercial vectorization software packages, the proposed model is customized to separate textual information, usually the cause of problems in the automatic conversion process, from the delimiting graphics of the map. The model retains the coordinates of the textual information for a later merge with the map after the conversion process. The propose model also addresses the localization problems in ARVC through the knowledge-supported intelligent vectorization system that is designed specifically to improve the accuracy and speed of the vectorization process. Finally, the model has been implemented on a symmetric multiprocessing (SMP) architecture, in order to achieve higher speed up and performance.

2009

Abstract Raster maps are widely available and contain useful geographic features such as labels and road lines. To extract the geographic features, most research work relies on a manual step to first extract the foreground pixels from the maps using the distinctive colors or grayscale intensities of the pixels. This strategy requires user interaction for each map to select a set of thresholds.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003

This paper presents a method for the extraction of contour lines and other geographic information from scanned color images of topographical maps. Although topographic maps are available from many suppliers, this work focuses on United States Geological Survey (USGS) maps. The extraction of contour lines, which are shown with brown color on USGS maps, is a difficult process due to aliasing and false colors induced by the scanning process and due to closely spaced and intersecting/overlapping features inherent to the map. These difficulties render simple approaches such as clustering ineffective. The proposed method overcomes these difficulties using a multistep process. First, a color key set, designed to comprehend color aliasing and false colors, is generated using an eigenvector line-fitting technique in RGB space. Next, area features, representing vegetation and bodies of water, are extracted using RGB color histogram analysis in order to simplify the next stage. Then, linear features corresponding to roads and rivers including contours, are extracted using a valley seeking algorithm operating on a transformed version of the original map. Finally, an A* search algorithm is used to link valleys together to form linear features and to close the gaps caused by intersecting features. The performance of the algorithm is tested on a number of USGS topographic map samples.