Extracting Major Lines by Recruiting Zero-Threshold Canny Edge Links along Sobel Highlights

Kim, Jae-Woong; Lee, Sukhan

doi:10.1109/lsp.2015.2400211

Cited by 28 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The index values computed for the three line extraction techniques are presented in Table 5. The proposed method exhibits a 21% improvement over LSD and a 24% improvement over the method in [17] for straight lines, whereas for curved lines this advantage increases to 30 and 31%, respectively. This illustrates the effectiveness of our method in delivering more stable and continuous lines.…”

Section: Comparison With Other State-of-the-art Methodsmentioning

confidence: 92%

“…To evaluate the performance of the proposed method in comparison with LSD [29] and the method described in [17], we conducted a series of line extraction experiments with the test images shown in Fig. 10 [30].…”

Section: Comparison With Other State-of-the-art Methodsmentioning

confidence: 99%

“…12 presents the lines extracted from the test images in Fig. 10 by LSD, the method described in [17], and the proposed method. Table 4 summarises the corresponding line segment data in terms of the total line count and length as measured by the total pixel count.…”

Section: Comparison With Other State-of-the-art Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Step‐by‐step pipeline processing approach for line segment detection

Shao

Ding

Luo

et al. 2017

IET Image Processing

View full text Add to dashboard Cite

This study proposes a line segment detection that can efficiently and effectively handle non-linear uniform intensity changes. The presented sketching algorithm applies the resistant to affine transformation and monotonic intensity change (RATMIC) descriptor to conduct binary translation in the image pre-processing step, which can remove the unwanted smoothing of the Canny detector in most line detections. The Harris corner detector is applied to catch regions of line segments for the purpose of simulating the composition of sketching and achieving a sense of unity within the picture. Furthermore, the RATMIC descriptor is employed to obtain binary images of the regions of interest (ROIs). Finally, small eigenvalue analysis is implemented to detect straight lines in the ROIs. The experiments conducted on various images with image rotation, scaling, and translation validate the effectiveness of the proposed method. The experimental results also demonstrate that about 30% in the overall coverage of major lines and 20% in the coverage per major line are increased compared with the state-of-the-art line detectors. Moreover, the performance of the proposed method produces a combined advantage of ∼17% in the coverage of line segments over the line segment detector with noisy images.

show abstract

Section: Comparison With Other State-of-the-art Methodsmentioning

confidence: 92%

Section: Comparison With Other State-of-the-art Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Step‐by‐step pipeline processing approach for line segment detection

Shao

Ding

Luo

et al. 2017

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Commonly used foreground object extraction methods are background difference method, image sequence modeling method, the body shape modeling method and the depth of information method and so on (Kim, 2015). Interrogation room is a relatively closed independent environment, the background is fixed, the camera position angle is fixed, and the illumination change is small.…”

Section: Human Foreground Object Extractionmentioning

confidence: 99%

Automatic Recognition of the Micro-Expressions of Human Torso Posture in the Environment of Interrogation

Wang¹,

Feng²

2017

Proceedings of the 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)

View full text Add to dashboard Cite

Abstract. In order to improve trial efficiency and realize the automatic recognition of the micro-expressions of criminal suspects in the interrogation process, according to the characteristics of the human torso micro-expressions posture, A 6 points human torso model which is used to describe the human torso micro-expressions posture is proposed. An automatic recognition algorithm of the micro-expressions of human torso posture is designed. First, the original image of the human torso posture is converted to a local binary pattern image. The edge of the human torso is detected on the local binary pattern image by the canny operator. Then, the human torso posture characteristics are described and calculated by 6 points human skeleton model. Compared with the traditional 20 points human skeleton model, the key points of the left and right chest are added to the skele-ton model, and the key point of waist is expanded to about two points. The 6 points model is more suitable for describing the micro-expressions characteristics of human torso posture. Finally, the different postures are classified and recognized by support vector machine. Experimental results indicate that the recognition results of the 8 different human torso pose are uniform, and are all in the 83.1~92.5%. The average correct recognition rate of 8 different human torso posture is 87.9%. The average correct recognition rate of the recognition algorithm using the traditional 20 points human skeleton model is only 67.3%. Compared with the traditional 20 points human skeleton model, the 6 points human torso model can be more accurate and reasonable description of the characteristics of the human torso microexpressions posture. The algorithm can satisfy the requirements of human torso micro-expressions posture automatic recognition, and effectively judge the different postures.

show abstract

“…Canny's method was used by [10] in 2004, [11] in 2007, [12] in 2013, [13] in 2015, [14] [22] using different methodological approaches that mostly aimed at the elimination of noise, the location of the eye, and location of the center of the pupil, using different techniques to achieve iris segmentation. In [18] and [19] the Hough transform was used to detect the center of the pupil and from it to project the iris.…”

Section: Introductionmentioning

confidence: 99%

Implementation of the Hough Transform for Iris Detection and Segmentation

Paulín-Martínez¹,

Lara-Guevara²,

Romero-González³

et al. 2019

AMI

View full text Add to dashboard Cite

The iris is used as a reference for the study of unique biometric marks in people. The analysis of how to extract the iris characteristic information represents a fundamental challenge in image analysis, due to the implications it presents: detection of relevant information, data coding schemes, etc. For this reason, in the search for extraction of useful and characteristic information, approximations have been proposed for its analysis. In this article, it is presented a scheme to extract the relevant information based on the Hough transform. This transform helps to find primitive geometries in the irises, which are used to characterize each one of these. The results of the implementation of the algorithm of the Hough transform applied to the location and segmentation of the iris by means of its circumference are presented in the paper. Two public databases of iris images were used: UBIRIS V2 and CASIA-IrisV4, which were acquired under the same conditions and controlled environments. In the pre-processing stage the edges are found from the noise elimination in the image through the Canny detector. Subsequently, to the images of the detected edges, the Hough transform is applied to the disposition of the geometries detected.

show abstract

Extracting Major Lines by Recruiting Zero-Threshold Canny Edge Links along Sobel Highlights

Cited by 28 publications

References 4 publications

Step‐by‐step pipeline processing approach for line segment detection

Step‐by‐step pipeline processing approach for line segment detection

Automatic Recognition of the Micro-Expressions of Human Torso Posture in the Environment of Interrogation

Implementation of the Hough Transform for Iris Detection and Segmentation

Contact Info

Product

Resources

About