You-Suk Bae

You-Suk Bae

Auto-generated profile, based on publicly available information

You-Suk Bae

Department of Computer Engineering, Korea Polytechnic University, Siheung 15073, Korea

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 November 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DKDongbeom Ko
Dongbeom Ko
SKSungjoo Kang
Sungjoo Kang
HKHyunsuk Kim
Hyunsuk Kim
WLWongok Lee
Wongok Lee
YBYousuk Bae
Yousuk Bae
JPJeongmin Park
Jeongmin Park
This paper introduces and implements an efficient training method for deep learning–based anomaly area detection in the depth image of a tire. A depth image of 16 bit integer size is used in various fields, such as manufacturing, industry, and medicine. In addition, the advent of the 4th Industrial Revolution and the development of deep learning require deep learning–based problem solving in various fields. Accordingly, various research efforts use deep learning technology to detect errors, such as product defects and diseases, in depth images. However, a depth image expressed in grayscale has limited information, compared with a three-channel image with potential colors, shapes, and brightness. In addition, in the case of tires, despite the same defect, they often have different sizes and shapes, making it difficult to train deep learning. Therefore, in this paper, the four-step process of (1) image input, (2) highlight image generation, (3) image stacking, and (4) image training is applied to a deep learning segmentation model that can detect atypical defect data. Defect detection aims to detect vent spews that occur during tire manufacturing. We compare the training results of applying the process proposed in this paper and the general training result for experiment and evaluation. For evaluation, we use intersection of union (IoU), which compares the pixel area where the actual error is located in the depth image and the pixel area of the error inferred by the deep learning network. The results of the experiment confirmed that the proposed methodology improved the mean IoU by more than 7% and the IoU for the vent spew error by more than 10%, compared to the general method. In addition, the time it takes for the mean IoU to remain stable at 60% is reduced by 80%. The experiments and results prove that the methodology proposed in this paper can train efficiently without losing the information of the original depth data.

3 April 2008
Verified
Conference Paper
Closed access
KYKyung-Hee Yu
Kyung-Hee Yu
HLHyunsuk Lee
Hyunsuk Lee
YBYou-Suk Bae
You-Suk Bae
The fingerprint recognition is the most developed field in the biometrics recognition and it can apply to the various applications. So the various studies are in progress for an enhancement of fingerprint recognition performance. In this paper, we will study the fingerprint recognition sensor. The fingerprint becomes input using fingerprint sensor to the fingerprint recognition system and the performance of the sensor has an effect on the fingerprint quality. Therefore, the improvement of system performance is possible by improving the performance of sensor. In this paper, we will study sensors which can be protected or unprotected from artificial fingerprint attack. We make various artificial fingerprints, and test sensors to overcome artificial fingerprint attack. We will analyze results of scanning test according to the various sensors and propose the method using the histogram of the normal image in order to measure the performance of these sensors. The measured characteristics are the resolution, shift, gradient, contrast, and rotation. The purpose of this paper is to propose the ways of the performance measurement which can be a criterion to evaluate the sensor performance.