Granulometry based detection of junction and end points in patent drawings (original) (raw)

Detection and classification of local primitives in line drawings

2011

The local primitives found in binary images are useful in the analysis and recognition of document and patent images. In this paper, an optimum detection of end points and junction points is obtained using morphological spurring and the granulometric curve of the image. A distance based algorithm is proposed to classify the local primitives found at the detected points. The size of the local region to classify a local primitive is determined granulometrically using the average thickness of lines found in the image. The classified primitives are quantized using a variant of local binary patterns. Ground truth is created and an analysis of the classification accuracy is performed. The values for all the parameters used in the proposed method are determined granulometrically which makes it scale invariant.

Morphology based spatial relationships between local primitives in line drawings

2011

Local primitives and their spatial relationships are useful in the analysis, recognition and retrieval of document and patent binary images. In this paper, a morphology based approach is proposed to establish the connections between the local primitives found at the optimally detected junction points and end points. The grayscale geodesic dilation is employed as the basic technique by taking a marker image with gray values at the local primitives and the skeleton of the original image as the mask image. The geodesic paths along the skeleton between the local primitives are traversed and their points of contact are protected by updating the mask image after each geodesic dilation iteration. By scanning the final marker image for the contact points of the traversed geodesic paths, connections between the local primitives are established. The proposed approach is robust and scale invariant.

A Thinning-based Junction Detection And Resolution Algorithm for Document Images

2020

Junction detection plays a significant role in document image recognition. High recognition rate of graphical primitives is correlated with the proper detection of junctions. In this paper, a junction detection algorithm is presented in thinning-based raster to vector conversion process. The method has three stages that leverage junction representation from pixels to features (i.e. junctions). The input image is thinned to its skeleton. Edges were found next and pixels with many neighbours are designated as a low level junction. Polygonal approximation on edges is used to detect L-junctions while connected component analysis is used to find intermediate junctions. Intermediate junctions with a distance less than a threshold are combined to form a high level X-and Y-junctions. Performance evaluation on mechanical engineering drawings shows precision rate of 82.38% and a recall rate of 97.29%.

Three-stage Junction Detection in Document Images

2020 International Conference on Computer Science and Software Engineering (CSASE), 2020

Engineering drawings contain many curves that intersect at a complex junction. Detection of these junctions is vital for correct recognition of line drawings. In this paper we study the detection of junctions in document images. A threestage junction detection is proposed to detect junctions in document images. The first stage works at the pixel level. Any pixel with more than two neighbors is labeled as low-level-junction. The second stage works at connected component level. All low-level-junctions adjacent to other low-level-junctions are merged into mid-level-junctions. The third stage combines mid-level-junction at a distance less than a threshold into a high-level-junction. Experimental results on real scanned images of mechanical engineering drawings show a precision rate of 82.38% and a recall rate of 97.29%.

Detection of line junctions in gray-level images

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2000

This paper describes an efficient approach for the detection of line junctions in gray-level images. The algorithm is divided into two steps. First, given the lines extracted from the original image, local line curvature is estimated. For this purpose, two different measures of curvature are proposed: The rate of change of direction of the orientation vector along the line and the mean of the dot products of orientation vectors within a given neighborhood. The second step involves the localization of junctions. Examples are provided based on experiments with synthetic and real images.

Detection of lines, line junctions and line terminations

International Journal of Remote Sensing, 2004

This paper describes an optimal line detector for the one-dimensional case which is derived from Canny's criteria, and an efficient approach for the detection of line junctions and line terminations. The line detector is extended to the two-dimensional case by operating separately in the x and y directions. An efficient implementation using an infinite impulse response (IIR) filter is provided. This implementation has the additional advantage that increasing the filter scale affects neither temporal nor spatial complexity. The detection algorithm for junctions and terminations is divided into two steps. First, given the lines extracted from the original image, a local measure of line curvature is estimated using the mean of the dot products of orientation vectors within a given neighbourhood. The second step involves the localization of junctions and terminations. Experimental results using several synthetic and real images demonstrate the validity of the two methods.

Thickness-based binary morphological improvement of distorted digital line intersections

This paper describes a discrete geometrical approach to improve the quality of line/curve intersections in the skeletonized image. A proper geometrical foundation is presented to be able to measure the degree of the distortion of the intersections caused by skeletonization. An improvement to reduce this distortion is suggested based on the separation of thick and thin lines/curves in the original image. This step assures the appropriate skeletonization of the thick elements which is consequently connected by the skeletons of the thin elements by direction estimation. The approach can be applied in improving the skeletonization of the retinal vascular system which step is often considered in the detection of several vascular diseases of the eye. Corresponding experimental results are also reported based on a publically available database.

Detection of Vertices in Sketched Drawings of Polyhedral Shapes

Lecture Notes in Computer Science, 2019

In this paper, visual perception principles were used to build an artificial perception model aimed at developing an algorithm for detecting junctions in line drawings of polyhedral objects that are vectorized from hand-drawn sketches. The detection is performed in 2D, before any 3D model is available and minimal information about the shape depicted by the sketch is used. The goal of this approach is to not only detect junctions in careful sketches created by skilled engineers and designers, but also detect junctions when skilled people draw casually to quickly convey rough ideas. Current approaches for extracting junctions from digital images are mostly incomplete, as they simply merge endpoints that are near each other, thus ignoring the fact that different vertices may be represented by different (but close) junctions and that the endpoints of lines that depict edges that share a common vertex may not necessarily be close to each other, particularly in quickly sketched drawings. We describe and validate a new algorithm that uses these perceptual findings to merge tips of line segments into 2D junctions that are assumed to depict 3D vertices.

A Robust Approach for Local Interest Point Detection in Line-Drawing Images

2012 10th IAPR International Workshop on Document Analysis Systems, 2012

In this paper, we propose a new method to detect local interest points as junctions in line-drawing images. Our approach takes advantages of different aspects. Firstly, we extract skeleton of image and then construct a Skeleton Connective Graph with the expectation that it provides a first level of junction detection from shapes. Secondly, instead of employing low-level operators to detect junctions as described in many traditional techniques, our method works at path level taking different skeleton branches into account to gain robustness. Thirdly, we exploit the benefits of wavelet transform (e.g. multiresolution analysis, discontinuity detection, fast computation, less sensitive to noises) to efficiently detect the dominant points from 1D representations of the paths. Finally, a post-process of pruning and connecting the skeleton segments is performed to discard false detected points and to refine the skeleton. We present in experiments interesting results compared to different methods.

Contours, Corners and T-Junctions Detection Algorithm

Image Processing On Line, 2018

This article describes the implementation of the method proposed by Buades, Grompone and Navarro in 2017 for the detection of line segments, contours, corners and T-junctions. The method is inspired by the mammal visual system. The detection of corners and T-junctions plays a role as part of the process in contour detection. An a contrario validation is applied to select the most meaningful contours without the need of fixing any critical parameter. Source Code The reviewed source code and documentation for this algorithm are available from the web page of this article 1. Compilation and usage instruction are included in the README.txt file of the archive.