• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.167-170
• /
• 2010

In this paper, we proposed a novel algorithm to detect the center of pupil in frontal view face. This algorithm, at first, extract an eye region from the face image using integral projection function and variance projection function. In an eye region, detect the center of pupil positions using circular hough transform with sobel edge mask. The experimental results show good performance in detecting pupil center from FERET face image.

• Proceedings of the KSR Conference
• /
• 2007.11a
• /
• pp.872-898
• /
• 2007

Pantograph sliding plate abrasion auto-detect system, one of the electric rail car auto-detecting devices, is a system that decides how much abrasion and when to replace without an inspector physically looking at the abrasion on the wet plate using machine vision, a cutting-edge technology. This paper covers the cause of deteriorating reliability that affects pantograph wet plate edge detection due to noise added to the video when it rains. In order to remove such noise, problems should be checked through Smoothing, Averaging mask and Median filter using filtering technique and stable edge detection without being affected by noise should be induced in video measurement used in machine vision technology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.735-741
• /
• 2014

Edge in images appears when a great difference shows up in light and shade between pixels and includes data of the subject's size, location direction and etc. The edge is generally detected by the methods such as Sobel, Roberts, Laplacian, LoG(Laplacian of Gaussian) and etc. However, in AWGN(additive white Gaussian noise) added images, quality of the edge becomes slightly uncertain. Therefore, this paper proposed edge detection algorithm using modified mask of weighting to improve the quality of the existing methods. And in order to verify the performance efficiency of the proposed method, processed image and PFOM(Pratt's figure of merit) has been used as valuation standard for a comparison with the existing methods.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.31-39
• /
• 2019

A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.275-284
• /
• 2023

Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.139-146
• /
• 2008

Masked fake face detection using ordinary visible images is a formidable task when the mask is accurately made with special makeup. Considering recent advances in special makeup technology, a reliable solution to detect masked fake faces is essential to the development of a complete face recognition system. This research proposes a method for masked fake face detection that exploits reflectance disparity due to object material and its surface color. First, we have shown that measuring of albedo can be simplified to radiance measurement when a practical face recognition system is deployed under the user-cooperative environment. This enables us to obtain albedo just by grey values in the image captured. Second, we have found that 850nm infrared light is effective to discriminate between facial skin and mask material using reflectance disparity. On the other hand, 650nm visible light is known to be suitable for distinguishing different facial skin colors between ethnic groups. We use a 2D vector consisting of radiance measurements under 850nm and 659nm illumination as a feature vector. Facial skin and mask material show linearly separable distributions in the feature space. By employing FIB, we have achieved 97.8% accuracy in fake face detection. Our method is applicable to faces of different skin colors, and can be easily implemented into commercial face recognition systems.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.4
• /
• pp.65-74
• /
• 2021

In order to efficiently inspect rapidly increasing old tunnels in many well-developed countries, many inspection methodologies have been proposed using imaging equipment and image processing. However, most of the existing methodologies evaluated their performance on a clean concrete surface with a limited area where other objects do not exist. Therefore, this paper proposes a 6-step framework for tunnel crack detection deep learning model development. The proposed method is mainly based on negative sample (non-crack object) training and Cascade Mask R-CNN. The proposed framework consists of six steps: searching for cracks in images captured from real tunnels, labeling cracks in pixel level, training a deep learning model, collecting non-crack objects, retraining the deep learning model with the collected non-crack objects, and constructing final training dataset. To implement the proposed framework, Cascade Mask R-CNN, an instance segmentation model, was trained with 1561 general crack images and 206 non-crack images. In order to examine the applicability of the trained model to the real-world tunnel crack detection, field testing is conducted on tunnel spans with a length of about 200m where electric wires and lights are prevalent. In the experimental result, the trained model showed 99% precision and 92% recall, which shows the excellent field applicability of the proposed framework.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.637-654
• /
• 2023

In recent years, the number of users has been increasing with the rapid development of earth observation satellites. In response, the Committee on Earth Observation Satellites (CEOS) has been striving to provide user-friendly satellite images by introducing the concept of Analysis Ready Data (ARD) and defining its requirements as CEOS ARD for Land (CARD4L). In ARD, a mask called an Unusable Data Mask (UDM), identifying unnecessary pixels for land analysis, should be provided with a satellite image. UDMs include clouds, cloud shadows, terrain shadows, etc. Terrain shadows are generated in mountainous terrain with large terrain relief, and these areas cause errors in analysis due to their low radiation intensity. previous research on terrain shadow detection focused on detecting terrain shadow pixels to correct terrain shadows. However, this should be replaced by the terrain correction method. Therefore, there is a need to expand the purpose of terrain shadow detection. In this study, to utilize CAS500-4 for forest and agriculture analysis, we extended the scope of the terrain shadow detection to shaded areas. This paper aims to analyze the potential for terrain shadow detection to make a terrain shadow mask for South and North Korea. To detect terrain shadows, we used a Hill-shade algorithm that utilizes the position of the sun and a surface's derivatives, such as slope and aspect. Using RapidEye images with a spatial resolution of 5 meters and Sentinel-2 images with a spatial resolution of 10 meters over the Korean Peninsula, the optimal threshold for shadow determination was confirmed by comparing them with the ground truth. The optimal threshold was used to perform terrain shadow detection, and the results were analyzed. As a qualitative result, it was confirmed that the shape was similar to the ground truth as a whole. In addition, it was confirmed that most of the F1 scores were between 0.8 and 0.94 for all images tested. Based on the results of this study, it was confirmed that automatic terrain shadow detection was well performed throughout the Korean Peninsula.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.1
• /
• pp.30-44
• /
• 2022

The advent of deep learning-based algorithms has facilitated researches on target detection from synthetic aperture radar(SAR) imagery. While most of them concentrate on detection tasks for ships with open SAR ship datasets and for aircraft from SAR scenes of airports, there is relatively scarce researches on the detection of SAR ground vehicle targets where several adverse factors such as high false alarm rates, low signal-to-clutter ratios, and multiple targets in close proximity are predicted to degrade the performances. In this paper, a dataset of ground vehicle targets acquired from TerraSAR-X(TSX) satellite SAR images is presented. Then, both detection and instance segmentation are simultaneously carried out on this dataset based on the deep learning-based Mask R-CNN. Finally, this paper shows the future research directions to further improve the performances of detecting the SAR ground vehicle targets.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.183-183
• /
• 2012

In the era of 45 nm or beyond technology, conventional etch mask using photoresist showed its limitation of etch mask pattern collapse as well as pattern erosion, thus hard mask in etching became necessary for precise control of etch pattern geometry. Currently available hard mask materials are amorphous carbon and polymetric materials spin-on containing carbon or silicon. Amorphous carbon layer (ACL) deposited by PECVD for etch hard mask has appeared in manufacturing, but spin-on carbon (SOC) was also suggested to alleviate concerns of particle, throughput, and cost of ownership (COO) [1]. SOC provides some benefits of reduced process steps, but it also faced with wiggling on a sidewall profile. Diamond like carbon (DLC) was also evaluated for substituting ACL, but etching selectivity of ACL was better than DLC although DLC has superior optical property [2]. Developing a novel material for pattern hard mask is very important in material research, but it is also worthwhile eliminating a potential issue to continuously develop currently existing technology. In this paper, we investigated in-situ dry-cleaning (ISD) monitoring of ACL coated process chamber. End time detection of chamber cleaning not only provides a confidence that the process chamber is being cleaned, but also contributes to minimize wait time waste (WOW). Employing Challenger 300ST, a 300mm ACL PECVD manufactured by TES, a series of experimental chamber cleaning runs was performed after several deposition processes in the deposited film thickness of $2000{\AA}$ and $5000{\AA}$. Ar Actinometry and principle component analysis (PCA) were applied to derive integrated and intuitive trace signal, and the result showed that previously operated cleaning run time can be reduced by more than 20% by employing real-time monitoring in ISD process.