A statistical method for line segment detection*
Introduction
The Hough transform (HT) [1], [2], [3] is widely used for extracting geometric features in images. The standard HT is inefficient with respect to run time and storage requirements; it also suffers from the peak-spreading problem in the Hough space [4], [5].
In order to improve the computation and storage efficiency, many methods have been proposed, such as the fast HT [6], adaptive HT [7], special architectures HT [8], probabilistic HT [9], randomized HT [10], or generalized HT [11].
In order to locate accurately the peak, and to derive accurate normal parameters, various extensions to the standard HT have been proposed. Numerous methods put the emphasis on generating more distinct peaks by modifying the voting scheme of a Hough transform. Edge information [12], [13], [14] or image preprocessing techniques [15], [16], [17] are used to enhance the peak in the accumulator array. In addition, a continuous statistical kernel [18] is proposed for modeling the Hough votes instead of using a discrete accumulator array. This approach is computationally more expensive because it considers and models all pixels in the given image.
After finding a peak, there are three different ways for supporting the computation of accurate peak parameters:
- (1)
A peak cell (θ, ρ) is simply selected for specifying the normal parameters of the detected line.
- (2)
A weighted averaging [19], [20] is used by considering neighboring cells (θi, ρi) around a peak cell.
- (3)
A specially designed peak localization technique is employed. For example, two accurate peak localization methods are presented in [21], [22] using smoothing windows and weighted averaging, a two-stage method [23] is described by finding a median position in narrow strips passing through an initial peak, a high-accuracy HT, proposed in [24], is based on the theoretical symmetry of the butterfly pattern around a peak, and a subcell-accuracy method [25] locates the peak by using fitting and interpolation techniques while analyzing the butterflies.
The HT can also be used for extracting the endpoints of a detected line segment [26] although the standard HT only provides normal angle θ and normal distance ρ.
We classify HT-based methods for detecting line segments into two categories. One class of methods is based on projection [27], [28], [29]. After applying the standard HT, the detected line is cut into pairwise disjoint segments; the endpoints of one of those line segments are determined by analyzing the projection of the feature points on either the x- or y-axis in image space. Two thresholds are needed to control the length of a line segment and the width of a gap between line segments. But, how to determine these two thresholds defines then a new problem.
The second class of methods is motivated by the butterfly shape [30], [31] of a peak region in Hough space [32], [33], [34]. Butterfly features are used to extract parameters of a line segment. The first and last cell with non-zero voting values are identified and used to compute the endpoints of the line segment by solving two sets of simultaneous equations [35], [36], [37], [38]. However, how to obtain the first and the last cell containing a non-zero voting value is a difficult problem in the presence of image noise, pixel disturbance, and a wide line-segment.
In a recent publication [39], we described a method for detecting line segments based on minimum-entropy analysis. Direction and length of a line segment are simultaneously determined by analyzing the voting entropies. The midpoint is detected by fitting voting means. The endpoint coordinates are finally calculated based on the detected direction, length and midpoint.
This paper proposes a novel statistical method based on HT for extracting line segments. The vote in each column (around a peak) is considered to be a random variable. The normal angle and distance of a line segment are computed by fitting and interpolating statistical variances and means. Endpoint coordinates of a line segment are computed by fitting a sine curve to the statistical non-zero voting cells, computed from statistical means and variances. Thus, there is no need for searching non-zero cells and solving two equations generated from just two cells.
In distinction to [39], this paper does not apply any minimum-entropy analysis. It extracts the normal angle, the normal distance, and endpoint coordinates using statistical characteristics. This paper also proposes a solution to calculate the statistical non-zero cells instead of searching for the first and the last non-zero voting cells in each column of a butterfly.
The rest of the paper is organized as follows. Section 2 introduces a way for peak distribution analysis in Hough space. Section 3 defines the random variable and statistical characteristics. Section 4 describes our normal angle and distance detection method based on statistical characteristics. Section 5 outlines endpoint detection by fitting sine curves. Section 6 compares experimental results with simulate data and real images. Section 7 concludes.
Section snippets
Peak distribution
Our method for line segment detection focuses on the voting cells around a peak. After voting, we start with analyzing the voting value distribution in each column around a peak in the Hough space.
Statistical analysis of voting distributions
Around a peak, the voting in each column is considered to be a random variable. We analyze the statistical characteristics of this variable.
Normal angle and distance detection
We aim at detecting a final peak accurately and robustly by considering various uncertainty. We compute θpeak and ρpeak of the peak by using fitting and interpolation techniques. Regarding fitting, we fit a second-order curve with the variances of the columns in the chosen peak region; the θpeak-value is defined by minimizing the fitted function. We also fit a sine-curve with the means of those columns in the peak region; the ρpeak value is computed by interpolating the sine-curve at the
Endpoint detection
We calculate the endpoint coordinates of a line segment, called left endpoint and right endpoint. Left and right can be defined by viewing toward the origin at the perpendicular point; see Fig. 6.
According to the equation of the HT, if the left endpoint votes for two different cells (θ1, ρ1) and (θ2, ρ2), the coordinates of the left endpoint can be computed directly by solving the equational system Taking the appearance of image noise,
Experimental results
We test the proposed line-segment detection method on a set of simulated data for evaluating the accuracy of line-segment detection, and on real-world images to verify the performance of line-segment detection.
Conclusions and discussions
This paper proposes a novel method for line segment detection in Hough space. The image center is selected as the origin of image coordinates. By analyzing the voting distribution around a peak in Hough space, a line-segment detection method is proposed by fitting and interpolating statistical characteristics of voting distributions in Hough space.
The voting in each column is considered to be a random variable, and voting values are considered as forming a probabilistic distribution. The normal
Acknowledgment
The first author thanks Jiangsu Overseas Research & Training Program for University Prominent Young & Middle-aged Teachers and Presidents for granting a scholarship to visit and undertake research at The University of Auckland.
References (44)
- et al.
A survey of the Hough transform
CVGIP
(1988) Survey: which Hough transform?
CVGIP
(1993)- et al.
Fast Hough transform: a hierarchical approach
Comput. Vis. Graphics Image Process.
(1986) - et al.
Benchmarking Hough transform architectures for real-time
Real-Time Imag.
(2000) - et al.
A probabilistic Hough transform
Pattern Recognit.
(1991) - et al.
A new curve detection method: randomized Hough transform (RHT)
Pattern Recognit. Lett.
(1990) Generalizing the Hough transform to detect arbitrary shapes
Pattern Recognit.
(1981)- et al.
Real-time line detection through an improved Hough transform voting scheme
Pattern Recognit.
(2008) - et al.
An improved Hough transform voting scheme utilizing surround suppression
Pattern Recognit. Lett.
(2009) - et al.
An optimizing line finder using a Hough transform algorithm
Comput. Vis. Image Underst.
(1997)
Antialiasing the Hough transform
Graph. Models Image Process.
An improved generalized Hough transform for the recognition of overlapping objects
Image Vis. Comput.
Accurate and robust line segment extraction by analysing distribution around peaks in Hough space
Comput. Vis. Image Underst.
A novel Hough transform method for line detection by enhancing accumulator array
Pattern Recognit. Lett.
Complete line segment description using the Hough transform
Image Vis. Comput.
A robust Hough transform technique for complete line segment description
Real-Time Imag.
Complete description of multiple line segments using the Hough transform
Image Vis. Comput.
Use of the Hough transformation to detect lines and curves in pictures
Commun. ACM
A formal definition of the Hough transform: properties and relationships
J. Math. Imag. Vis.
The adaptive Hough transform
IEEE Trans. Pattern Anal. Mach. Intell.
Bias error analysis of the generalised Hough transform
J. Math. Imag. Vis.
Cited by (28)
Predictive RANSAC: Effective model fitting and tracking approach under heavy noise and outliers
2017, Computer Vision and Image UnderstandingCitation Excerpt :Many applications require model fitting, regression, and parameter estimation given noisy measurements. Many approaches seek the solution that minimizes the distance between the model and the measurement data (Cohen and Cohen, 1996; Kay, 1993; Rousseeuw and Leroy, 2005; Stewart, 1999; Wong et al., 2013; Xu et al., 2015). Classical estimators, such as Least Square Estimator, work robustly to estimate the model parameters under the assumption that the measurement data is affected by a WSS zero mean Gaussian random process.
Automatic correction of perspective and optical distortions
2017, Computer Vision and Image UnderstandingCitation Excerpt :Segment detection is one of the basic tools to estimate vanishing points. In Xu et al. (2015) and Grompone et al. (2012) some segment detection methods are proposed. In Andaló et al. (2015) the authors use line segment detection to estimate vanishing points.
Guided Scale Space Radon Transform for linear structures detection
2024, Signal, Image and Video ProcessingLine Segment Detection Based on False Peak Suppression and Local Hough Transform and Application to Nuclear Emulsion
2023, IEICE Transactions on Information and SystemsQuadratic Curve Fitting-Based Image Edge Line Segment Detection: A Novel Methodology
2023, Applied Sciences (Switzerland)
- *
This paper has been recommended for acceptance by J.-O. Eklundh.