• Smart Structures and Systems
• /
• v.28 no.6
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.939-944
• /
• 2007

Edge is a significant element to represent boundary information between objects in images. There are various edge detection methods, which are based on differential operation, such as Sobel, Prewitt, Roberts, Canny, Laplacian, and etc. However the conventional methods have drawbacks as follow : (i) insensitivity to edges with gentle curve intensity, (ii) detection of double edges for edges with one pixel width. For the detection of edges, not only development of the effective operators but also that of appropriate thresholding methods are necessary. But it is very complicate problem to find an appropriate threshold. In this paper, we propose an edge detection method based on the region separateness between objects to overcome the drawbacks of the conventional methods, and a thresholding method for the proposed edge detection method. We show the effectiveness of the proposed method through experimental results obtained by applying the proposed and the conventional methods to well-known test images.

• Journal of Sensor Science and Technology
• /
• v.25 no.4
• /
• pp.285-290
• /
• 2016

Human sensing is an important but challenging technology. Unlike other methods for sensing humans, a vision sensor has many advantages, and there has been active research in automatic human detection in camera images. The combination of Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) is currently one of the most successful methods in vision-based human detection. However, extracting HOG features from an image is computer intensive, and it is thus hard to employ the HOG method in real-time processing applications. This paper describes an efficient solution to this speed problem of the HOG method. Our method obtains edge information of an image and finds candidate regions where humans very likely exist based on the distribution pattern of the detected edge points. The HOG features are then extracted only from the candidate image regions. Since complex HOG processing is adaptively done by the guidance of the simpler edge detection step, human detection can be performed quickly. Experimental results show that the proposed method is effective in various images.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.454-458
• /
• 2001

Based on a fuzzy system representation of gray scale images, we derive and edge detection algorithm whose convolution kernel is different from the known kernels such as those of Robert's Prewitt's or Sobel's gradient. Our fuzzy system representation is an exact representation of the bicubic spline function which represents the gray scale image approximately. Hence the fuzzy system is a continuous function and it provides a natural way to define the gradient and the Laplacian operator. We show that the gradient at grid points can be evaluated by taking the convolution of the image with a 3$\times$3 kernel. We also that our gradient coupled with the approximate value of the continuous function generates an edge detection method which creates edge images clearer than those by other methods. A few examples of applying our methods are included.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2779-2785
• /
• 2014

Edge Detection is a technique that obtains the particular information of the image using the brightness variation of pixel values and utilized for preprocessing in various image processing sectors. The conventional edge detection methods such as Sobel, Prewitt and Roberts are processed by applying the same weighted value to the entire pixels regardless of pixel distrbution and provides somewhat insufficient edge detection results. therefore, this paper has proposed an edge detection method considering the direction and magnitute of pixels by applying a modified directional mask.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.283-286
• /
• 2001

Based on a fuzzy system representation of gray scale images, we derive an edge detection algorithm whose convolution kernel is different from the known kernels such as those of Roberts', Prewitt's or Sobel's gradient. Our fuzzy system representation is an exact representation of the bicubic spline function which represents the gray scale image approximately. Hence the fuzzy system is a continuous function and it provides a natural way to define the gradient and the Laplacian operator. We show that the gradient at grid points can be evaluated by taking the convolution of the image with a 3 3 kernel. We also show that our gradient coupled with the approximate value of the continuous function generates an edge detection method which creates edge images clearer than those by other methods. A few examples of applying our methods are included.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.207-212
• /
• 2015

We propose a noise estimation method using edge detection in moving pictures. Edge detection is to exclude structures and details which have an effect on the noise estimation. To detect edge, we use Sobel and morphological closing operators which are robust to details of images. The proposed noise estimation method is more efficiently applied to noise estimation in various types of moving images and has better results than those of existing noise estimation methods. Also, proposed algorithm can be efficiently applied to image and video applications.

• Journal of Sensor Science and Technology
• /
• v.20 no.6
• /
• pp.388-392
• /
• 2011

In this paper, a face detection method for interactive TV control system using a new feature, edge histogram feature, with a support vector machine(SVM) in the near-infrared(NIR) images is proposed. The edge histogram feature is extracted using 16-directional edge intensity and a histogram. Compared to the previous method using local binary pattern(LBP) feature, the proposed method using edge histogram feature has better performance in both smaller feature size and lower equal error rate(EER) for face detection experiments in NIR databases.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.809-817
• /
• 2002

This paper describes a new face detection method that is a pre-processing algorithm for on-line face recognition. To complement the weakness of using only edge or rotor features from previous face detection method, we propose the two types of face detection method. The one is a combined method with edge and color features and the other is a center area color sampling method. To prevent connecting the people's face area and the background area, which have same colors, we propose a new adaptive edge detection algorithm firstly. The adaptive edge detection algorithm is robust to illumination variance so that it extracts lots of edges and breakouts edges steadily in border between background and face areas. Because of strong edge detection, face area appears one or multi regions. We can merge these isolated regions using color information and get the final face area as a MBR (Minimum Bounding Rectangle) form. If the size of final face area is under or upper threshold, color sampling method in center area from input image is used to detect new face area. To evaluate the proposed method, we have experimented with 2,100 face images. A high face detection rate of 96.3% has been obtained.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.770-772
• /
• 2013

Edges on the images are widely used in preprocessing in various areas including recognition and detection of the object. As generally known edge detection methods, there is a method using mask and these methods are Sobel, Prewitt, Roberts, Laplacian operator and etc. Implementation of these existing edge detection methods is simple. However, when processing the impulse noise added images, the properties of edge detection is not sufficient. Accordingly, in order to compensate for the weakness of existing edge detection methods and to detect strong edges on the images which were damaged by impulse noise, the edge detection algorithm using transformed mask was proposed in this paper.