The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the... more
The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the recognition of domain dependent symbols according to a symbol database. In this work we first review the most outstanding symbol recognition methods from two different points of view: application domains and pattern recognition methods. In the second part of the paper, open and unaddressed problems involved in symbol recognition are described, analyzing their current state of art and discussing future research challenges. Thus, issues such as symbol representation, matching, segmentation, learning, scalability of recognition methods and performance evaluation are addressed in this work. Finally, we discuss the perspectives of symbol recognition concerning to new paradigms such as user interfaces in handheld computers or document database and WWW indexing by graphical content.
This paper presents a method for vectorizing the graphical parts of paper-based line drawings. The method consists of separating the input binary image into layers of homogeneous thickness, skeletonizing each layer, segmenting the... more
This paper presents a method for vectorizing the graphical parts of paper-based line drawings. The method consists of separating the input binary image into layers of homogeneous thickness, skeletonizing each layer, segmenting the skeleton by a method based on random sampling, and simplifying the result. The segmentation method is robust with a best bound of 50 percent noise reached for indefinitely long primitives. Accurate estimation of the recognized vector's parameters is enabled by explicitly computing their feasibility domains. Theoretical performance analysis and expression of the complexity of the segmentation method are derived. Experimental results and comparisons with other vectorization systems are also provided.
In this paper we present an innovative approach to automatically generate adjacency grammars describing graphical symbols. A grammar production is formulated in terms of rule sets of geometrical constraints among symbol primitives. Given... more
In this paper we present an innovative approach to automatically generate adjacency grammars describing graphical symbols. A grammar production is formulated in terms of rule sets of geometrical constraints among symbol primitives. Given a set of symbol instances sketched by a user using a digital pen, our approach infers the grammar productions consisting of the ruleset most likely to occur. The performance of our work is evaluated using a comprehensive benchmarking database of on-line symbols
This paper presents analyses of different methods of postprocessing lines that have resulted from the raster-to-vector conversion of black and white line drawing. Special attention was paid to the borders of connected components of maps.... more
This paper presents analyses of different methods of postprocessing lines that have resulted from the raster-to-vector conversion of black and white line drawing. Special attention was paid to the borders of connected components of maps. These methods are implemented with compression and smoothing algorithms. Smoothing algorithms can enhance accuracy, so using both smoothing and compression algorithms in succession gives a more accurate result than using only a compression algorithm. The paper also shows that a map in vector format may require more memory than a map in raster format. The Appendix contains a detailed description of the new smoothing method (continuous local weighted averaging) suggested by the authors.
Optical music symbol recognition facilitates to transcribe the music sheet into machine-readable format so that it can be used for various applications by converting it into midi format. Most of the works in the past have focused on the... more
Optical music symbol recognition facilitates to transcribe the music sheet into machine-readable format so that it can be used for various applications by converting it into midi format. Most of the works in the past have focused on the recognition of printed music symbols and a few on online music symbols. Earlier methods work very well for printed music symbol recognition. However, their performance is limited to clean and binarized documents. Handwritten music symbol recognition is explored a little as it has several challenges such as variation in writing styles, document degradation, noise etc. In this paper, we have investigated the performance of well-known texture descriptor namely Histogram of Oriented Gradients (HOG) for the Old Handwritten Music Symbol Recognition on the publicly available dataset. Support Vector Machine and K-Nearest Neighbor Classifiers were employed for the music symbol classification with K –Fold Cross Validation Technique. We have achieved encouraging results and shown the comparative analysis of various sizes of cell of computing HOG
In this paper, we review some ideas which emerged in the early years of research on symbol recognition and we show how these ideas evolved into a large variety of contributions. We then propose some interesting challenges for symbol... more
In this paper, we review some ideas which emerged in the early years of research on symbol recognition and we show how these ideas evolved into a large variety of contributions. We then propose some interesting challenges for symbol recognition research in the present years, including symbol spotting methods, recognition procedures for complex symbols, and a systematic approach to performance
This article describes a sketch-based framework for semi-automatic annotation of historical document collections. It is motivated by the fact that fully automatic methods, while helpful for extracting metadata from large collections, have... more
This article describes a sketch-based framework for semi-automatic annotation of historical document collections. It is motivated by the fact that fully automatic methods, while helpful for extracting metadata from large collections, have two main drawbacks in a real-world application:(i) they are error-prone and (ii) they only capture a subset of all the knowledge in the document base, both meaning that manual intervention is always required. Therefore, we have developed a practical framework for allowing experts to extract ...
ABSTRACT In the context of graphics recognition, arc detection consist in the extraction of circles and arcs from the image of a graphics document or from the segments yielded by its vectorization. Several methods have been proposed for... more
ABSTRACT In the context of graphics recognition, arc detection consist in the extraction of circles and arcs from the image of a graphics document or from the segments yielded by its vectorization. Several methods have been proposed for this purpose, and we briefly survey them. Then, we describe an improved algorithm inspired by two existing methods, and including a fitting step for better precision
Dov Dori and Liu WenYin September 1999. ... The goal of the graphics recognition framework is to abstract and model such similar procedure and supply generic code for graphics recognition algorithms to be used as ready made and easily... more
Dov Dori and Liu WenYin September 1999. ... The goal of the graphics recognition framework is to abstract and model such similar procedure and supply generic code for graphics recognition algorithms to be used as ready made and easily extendible components in the graphics ...
The aim of writer identification is determining the writer of a piece of handwriting from a set of writers. In this paper, we present an architecture for writer identification in old handwritten music scores. Even though an important... more
The aim of writer identification is determining the writer of a piece of handwriting from a set of writers. In this paper, we present an architecture for writer identification in old handwritten music scores. Even though an important amount of music compositions contain handwritten text, the aim of our work is to use only music notation to determine the author. The main contribution is therefore the use of features extracted from graphical alphabets. Our proposal consists in combining the identification results of two different approaches, based on line and textural features. The steps of the ensemble architecture are the following. First of all, the music sheet is preprocessed for removing the staff lines. Then, music lines and texture images are generated for computing line features and textural features. Finally, the classification results are combined for identifying the writer. The proposed method has been tested on a database of old music scores from the seventeenth to nineteenth centuries, achieving a recognition rate of about 92% with 20 writers.
Numerous raster maps are available on the Internet, but the geographic coordinates of the maps are often unknown. In order to determine the precise location of a raster map, we exploit the fact that the layout of the road intersections... more
Numerous raster maps are available on the Internet, but the geographic coordinates of the maps are often unknown. In order to determine the precise location of a raster map, we exploit the fact that the layout of the road intersections within a certain area can be used to determine the map's location. In this paper, we describe an approach to automatically extract road intersections from arbitrary raster maps. Identifying the road intersections is difficult because raster maps typically contain multiple layers that ...
This paper proposes a 3D space distance measuring method to accomplish non-contact 3D space distance measuring by using a digital camera or digital video camera. The measuring principle of the proposed method in this paper is to learn the... more
This paper proposes a 3D space distance measuring method to accomplish non-contact 3D space distance measuring by using a digital camera or digital video camera. The measuring principle of the proposed method in this paper is to learn the present camera shooting distance and the horizontal or vertical distance between the given points according to the number of pixels of the image in horizontal motion corresponding to the moving digital video camera or digital camera. The measuring structure proposed in this paper does not employ image graphic recognition or image signal analysis method to accomplish distance measuring, therefore, high-speed micro-computer and Digital Signal Processor are not used. All the distance measuring data come from a single horizontal scanning line. Only by modifying the system software of the digital video cameras (digital cameras), all makes of digital video cameras or digital cameras can have the feature of measuring 3D space distance.
In this paper we propose recognizing logo images by using an adaptive model referred to as recursive artificial neural network. At first, logo images are converted into a structured representation based on contour trees. Recursive neural... more
In this paper we propose recognizing logo images by using an adaptive model referred to as recursive artificial neural network. At first, logo images are converted into a structured representation based on contour trees. Recursive neural networks are then learnt using the contourtrees as inputs to the neural nets. On the other hand, the contour-tree is constructed by associating a node with each exterior or interior contour extracted from the logo instance. Nodes in the tree are labeled by a feature vector, which describes the contour by means of its perimeter, surrounded area, and a synthetic representation of its curvature plot. The contour-tree representation contains the topological structured information of logo and continuous values pertaining to each contour node. Hence symbolic and sub-symbolic information coexist in the contour-tree representation of logo image. Experimental results are reported on 40 real logos distorted with artificial noise and performance of recursive neural network is compared with another two types of neural approaches.
Vectorization, i.e. raster-to-vector conversion, is a cen- tral part of graphics recognition problems. In this paper, we discuss the pros and the cons of basing one's vectoriza- tion process on... more
Vectorization, i.e. raster-to-vector conversion, is a cen- tral part of graphics recognition problems. In this paper, we discuss the pros and the cons of basing one's vectoriza- tion process on skeletonization. While distance skeletons have proven to be robust and precise, they tend to distort the results at line extremities and junctions. In these cases, contour-matching approaches yield better results,
A generic integrated line detection algorithm (GILDA) is presented and demonstrated. GILDA is based on the generic graphics recognition approach, which abstracts the graphics recognition as a stepwise recovery of the multiple components... more
A generic integrated line detection algorithm (GILDA) is presented and demonstrated. GILDA is based on the generic graphics recognition approach, which abstracts the graphics recognition as a stepwise recovery of the multiple components of the graphic objects and is specified by the object–process methodology. We define 12 classes of lines which appear in engineering drawings and use them to construct a class inheritance hierarchy. The hierarchy highly abstracts the line features that are relevant to the line detection process. Based on the “Hypothesis and Test” paradigm, lines are detected by a stepwise extension to both ends of a selected first key component. In each extension cycle, one new component which best meets the current line’s shape and style constraints is appended to the line. Different line classes are detected by controlling the line attribute values. As we show in the experiments, the algorithm demonstrates high performance on clear synthetic drawings as well as on noisy, complex, real-world drawings.
In this paper we present a method of robustly detect circles in a line drawing image. The method is fast, robust and very reliable, and is capable of assessing the quality of its detection. It is based on Random Sample Consensus... more
In this paper we present a method of robustly detect circles in a line drawing image. The method is fast, robust and very reliable, and is capable of assessing the quality of its detection. It is based on Random Sample Consensus minimization, and uses techniques that are inspired from object tracking in image sequences. Note: some details of the illustrations in this paper are in colour. Reading them on a greylevel printout will reduce their intelligibility. 1.
A typical paper based document consists of regions of text, graphics, and halftone images. Developing algorithms for automating the input of such documents is the goal of this research. The scope of this paper is the design of algorithms... more
A typical paper based document consists of regions of text, graphics, and halftone images. Developing algorithms for automating the input of such documents is the goal of this research. The scope of this paper is the design of algorithms to process raster oriented binary images of paper based graphics to obtain vector oriented description files. The image is preprocessed to suppress noise and other digitization artifacts. The graphical components are then represented as a union of maximal squares using the maximal square moving ...
We investigate a new approach for online handwritten shape recognition. Interesting features of this approach include learning without manual tuning, learning from very few training samples, incremental learning of characters, and... more
We investigate a new approach for online handwritten shape recognition. Interesting features of this approach include learning without manual tuning, learning from very few training samples, incremental learning of characters, and adaptation to the user-specific needs. The proposed system can deal with two-dimensional graphical shapes such as Latin and Asian characters, command gestures, symbols, small drawings, and geometric shapes. It can be used as a building block for a series of recognition tasks with many applications
A successful project in automated map generalization under-taken at the National Atlas of Canada made extensive use of the implicit perceptual information present in road and river networks as a means of analysing and understanding their... more
A successful project in automated map generalization under-taken at the National Atlas of Canada made extensive use of the implicit perceptual information present in road and river networks as a means of analysing and understanding their basic structure. Using the perceptual grouping principle of ‘good continuation’, a network is decomposed into chains of network arcs, termed ‘strokes’. The network strokes are then automatically ranked according to derived measures. Deleting strokes from the network following this ranking sequence provides a simple but very effective means of generalizing (attenuating) the network. This technique has practical advantages over previous methods. It has been employed in road network generalization, and applied in the selection of hydrologic data for a map covering Canada’s northern territories. The method may find further application in the interpretation of other forms of documents, such as diagrams or handwriting.
The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the... more
The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the recognition of domain dependent symbols according to a symbol database. In this work we first review the most outstanding symbol recognition methods from two different points of view: application domains and pattern recognition methods. In the second part of the paper, open and unaddressed problems involved in symbol recognition are described, analyzing their current state of art and discussing future research challenges. Thus, issues such as symbol representation, matching, segmentation, learning, scalability of recognition methods and performance evaluation are addressed in this work. Finally, we discuss the perspectives of symbol recognition concerning to new paradigms such as user interfaces in handheld computers or document database and WWW indexing by graphical content.