Jong Pil Yun

Bio: Jong Pil Yun is an academic researcher from KITECH. The author has contributed to research in topics: Gabor filter & Deep learning. The author has an hindex of 16, co-authored 53 publications receiving 614 citations. Previous affiliations of Jong Pil Yun include Pohang University of Science and Technology & POSCO.

Automatic detection of cracks in raw steel block using Gabor filter optimized by univariate dynamic encoding algorithm for searches (uDEAS)

Abstract: Recently, there has been an increase in the demand for quality control in the steel making industry. This paper proposes a vision-based method for detection of defects in the surfaces of scale-covered steel billets. Scales are formed on the surface of billets owing to the deposition of oxidized substances that are produced during manufacturing. Because of the presence of scales on the billet surface, its characteristics such as brightness and texture in the background region are inconsistent. Moreover, the similarities in the gray-levels of the defect and defect-free regions make it very difficult to accurately detect defects. In order to solve the abovementioned problems and to detect defects more effectively, we propose a new defect detection algorithm, which is based on Gabor filters. The Gabor filters are optimized using a new optimization algorithm known as univariate dynamic encoding algorithm for searches (uDEAS). The algorithm finds the minimum value of the cost function related to the energy separation criteria between the defect and the defect-free regions. Finally, the experimental results conducted on billet surface images from actual steel production line show the effectiveness of the proposed algorithm.

Real-time vision-based defect inspection for high-speed steel products

Abstract: In the steel-making industry, both the quality and quantity of the products are critical. This work presents a real-time defect detection method for high-speed steel bar in coil (BIC). For good performance characteristics, the detection algorithm must be robust to problems associated with the cylindrical shape of BICs, the presence of noise and nonuniform brightness distribution of images, the various types of defects, and so on. Furthermore, because the target speed is very high, it should have a fast processing time. Therefore, a defect detection algorithm should satisfy the two conflicting requirements of reducing the processing time and improving the efficiency of defect detection. This work proposes an effective real-time defect detection algorithm that can satisfy these conditions. Moreover, to reduce cost, the proposed algorithm is implemented on a PC-based real-time defect detection system without a professional digital signal processing (DSP) board. Experimental results show that the proposed algorithm guarantees both real-time processing and accurate detection.

Defect detection for corner cracks in steel billets using a wavelet reconstruction method

Abstract: Presently, automatic inspection algorithms are widely used to ensure high-quality products and achieve high productivity in the steelmaking industry. In this paper, we propose a vision-based method for detecting corner cracks on the surface of steel billets. Because of the presence of scales composed of oxidized substances, the billet surfaces are not uniform and vary considerably with the lighting conditions. To minimize the influence of scales and improve the accuracy of detection, a detection method based on a visual inspection algorithm is proposed. Wavelet reconstruction is used to reduce the effect of scales. Texture and morphological features are used to identify the corner cracks among the defective candidates. Finally, the experimental results show that the proposed algorithm is effective in detecting corner cracks on the surfaces of the steel billets.

Vision-based defect detection of scale-covered steel billet surfaces

Abstract: Vision-based inspection systems have been widely investigated for the detection and classification of defects in various industrial product. We present a new defect detection algorithm for scale-covered steel billet surfaces. Because of the availability of various kinds of steel, presence of scales, and manufacturing conditions, the features of billet surface images are not uniform. In particular, scales severely change the properties of defect-free surfaces. Moreover, the various kinds of possible defects make their detection difficult. In order to resolve these problems and to improve the detection performance, two methods are proposed. First, undecimated wavelet transform and vertical projection profile are presented. Second, a method for detecting the variations in the block features along the vertical direction is proposed. The former method can effectively detect vertical line defects, and the latter can efficiently detect the remaining defects, except the vertical line defects. The experimental results conducted on billet surface images obtained from actual steel production lines show that the proposed algorithm is effective for defect detection of scale-covered steel billet surfaces.

NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion

Abstract: Regular inspection of nuclear power plant components is important to guarantee safe operations. However, current practice is time consuming, tedious, and subjective, which involves human technicians reviewing the inspection videos and identifying cracks on reactors. A few vision-based crack detection approaches have been developed for metallic surfaces, and they typically perform poorly when used for analyzing nuclear inspection videos. Detecting these cracks is a challenging task since they are tiny, and noisy patterns exist on the components’ surfaces. This study proposes a deep learning framework, based on a convolutional neural network (CNN) and a Naive Bayes data fusion scheme, called NB-CNN, to analyze individual video frames for crack detection while a novel data fusion scheme is proposed to aggregate the information extracted from each video frame to enhance the overall performance and robustness of the system. To this end, a CNN is proposed to detect crack patches in each video frame, while the proposed data fusion scheme maintains the spatiotemporal coherence of cracks in videos, and the Naive Bayes decision making discards false positives effectively. The proposed framework achieves a 98.3% hit rate against 0.1 false positives per frame that is significantly higher than state-of-the-art approaches as presented in this paper.

Review of vision-based steel surface inspection systems

Abstract: Steel is the material of choice for a large number and very diverse industrial applications. Surface qualities along with other properties are the most important quality parameters, particularly for flat-rolled steel products. Traditional manual surface inspection procedures are awfully inadequate to ensure guaranteed quality-free surface. To ensure stringent requirements of customers, automated vision-based steel surface inspection techniques have been found to be very effective and popular during the last two decades. Considering its importance, this paper attempts to make the first formal review of state-of-art of vision-based defect detection and classification of steel surfaces as they are produced from steel mills. It is observed that majority of research work has been undertaken for cold steel strip surfaces which is most sensitive to customers' requirements. Work on surface defect detection of hot strips and bars/rods has also shown signs of increase during the last 10 years. The review covers overall aspects of automatic steel surface defect detection and classification systems using vision-based techniques. Attentions have also been drawn to reported success rates along with issues related to real-time operational aspects.

Automatic Defect Detection on Hot-Rolled Flat Steel Products

Abstract: Automatic defect detection on hot-rolled steel surface is challenging owing to its localization on a large surface, variation in appearance, and their rare occurrences. It is difficult to detect these defects either by physics-based models or by small-sample statistics using a single threshold. As a result, this problem is focused to derive a set of good-quality defect descriptors from the surface images. These descriptors should discriminate the various surface defects when fed to suitable machine learning algorithms. This research work has evaluated the performance of a number of different wavelet feature sets, namely, Haar, Daubechies 2 (DB2), Daubechies 4 (DB4), biorthogonal spline, and multiwavelet in different decomposition levels derived from 32 × 32 contiguous (nonoverlapping) pixel blocks of steel surface images. We have developed an automated visual inspection system for an integrated steel plant to capture surface images in real time. It localizes defects employing kernel classifiers, such as support vector machine and recently proposed vector-valued regularized kernel function approximation. Test results on 1000 defect-free and 432 defective images comprising of 24 types of defect classes reveal that three-level Haar feature set is more promising to address this problem than the other wavelet feature sets as well as texture-based segmentation or thresholding technique of defect detection.