• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.180-186
• /
• 2013

The primary goal of attack on steganographic images, termed steganalysis, is to detect the presence of hidden data by finding statistical abnormality of a stego-media caused by data embedding. This paper proposes a novel steganographic scheme based on improving the (7, 4) Hamming code for digital images. The proposed scheme embeds a segment of six secret bits into a group of nine cover pixels at a time. The experimental results show that the proposed scheme achieves a 0.67bpp embedding payload and a slightly higher visual quality of stego images compared with the previous arts.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.5-7
• /
• 2019

열화상 시스템은 물체로부터 발산되는 적외선을 영상화하여 물체를 탐지하는 장점으로 인해 군사 분야는 물론 현재 민수 분야(자동차, Security 시스템)에 활용분야가 넓어지고 있다. 기존에는 대부분 FPGA 기반으로 열화상 열상 모듈을 개발하였지만 민수 분야에 다양한 요구사항 및 범용성에 유연한 대처가 힘든 실정이다. 따라서 다양한 요구사항과 범용성을 만족하기 위한 시스템의 필요성이 대두되었다. 본 논문에서는 상용 이미지 프로세서를 이용한 열화상 영상 처리 시스템을 제안한다. 제안된 시스템은 기존 FPGA 기반 시스템이 아닌 상용 이미지 프로세서를 사용함으로써 범용 영상 입·출력 인터페이스 및 각종 디바이스를 지원함에 따라 다양한 요구사항과 범용성을 만족한다. 따라서 시스템이 구축이 되면 뛰어난 접근성으로 인하여 시스템 추가/변경 시 기존의 시스템에 비해 개발 비용 및 기간을 단축할 수 있으며 그로 인하여 다양한 고객 요구사항 만족, 개발 비용 및 시간 단축, 제품 출시일 등 다양한 이점을 얻을 것으로 예상한다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.1
• /
• pp.117-126
• /
• 2022

Currently, the number of bridge structures in Korea is continuously increasing and enlarged, and the number of old bridges that have been in service for more than 30 years is also steadily increasing. Bridge aging is being treated as a serious social problem not only in Korea but also around the world, and the existing manpower-centered inspection method is revealing its limitations. Recently, various bridge damage detection studies using deep learning-based image processing algorithms have been conducted, but due to the limitations of the bridge damage data set, most of the bridge damage detection studies are mainly limited to one type of crack, which is also based on a close set classification model. As a detection method, when applied to an actual bridge image, a serious misrecognition problem may occur due to input images of an unknown class such as a background or other objects. In this study, five types of bridge damage including crack were defined and a data set was built, trained as a deep learning model, and an open set recognition-based bridge multiple damage recognition model applied with OpenMax algorithm was constructed. And after performing classification and recognition performance evaluation on the open set including untrained images, the results were analyzed.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.535-543
• /
• 2022

A drone is used to diagnose crop growth and to provide information through images in the agriculture field. In the case of using high spatial resolution drone images, growth information for each object can be produced. However, accurate object detection is required and adjacent objects should be efficiently classified. The purpose of this study is to develop a Chinese cabbage object detection algorithm using multispectral reflectance images observed from drone and computer vision techniques. Drone images were captured between 7 and 15 days after planting a Chinese cabbage from 2018 to 2020 years. The thresholds of object detection algorithm were set based on 2019 year, and the algorithm was evaluated based on images in 2018 and 2019 years. The vegetation area was classified using the characteristics of spectral reflectance. Then, morphology techniques such as dilatation, erosion, and image segmentation by considering the size of the object were applied to improve the object detection accuracy in the vegetation area. The precision of the developed object detection algorithm was over 95.19%, and the recall and accuracy were over 95.4% and 93.68%, respectively. The F1-Score of the algorithm was over 0.967 for 2 years. The location information about the center of the Chinese cabbage object extracted using the developed algorithm will be used as data to provide decision-making information during the growing season of crops.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.11
• /
• pp.1104-1113
• /
• 2014

Future combat systems can be represented as the NCW (Network Centric Warefare), which is based on the concept of Sensor-to-Shooter. A wireless video sensor networking technology, one of the core components of NCW, has been actively applied for the purpose of tactical surveillance. In such a surveillance sensor network, multi-composite sensors, especially consisting of image sensors are utilized to improve reliability for intrusion detection and enemy tracing. However, these sensors may cause a problem of requiring very high network capacity and energy consumption. In order to alleviate this problem, this paper proposes an image data transmission scheme based on resource reservation. The proposed scheme can make it possible to have more reliable image data transmission by choosing proper multiple interfaces, while trying to control resolution and compression quality of image data based on network resource availability. By the performance analysis using NS-3 simulation, we have confirmed the transmission reliability as well as energy efficiency of the proposed scheme.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.403-410
• /
• 2019

Image de-snowing aims at eliminating the negative influence by snow particles and improving scene understanding in images. In this paper, a perceptual generative adversarial network based a single image snow removal method is proposed. The residual U-Net is designed as a generator to generate the snow free image. In order to handle various sizes of snow particles, the inception module with different filter kernels is adopted to extract multiple resolution features of the input snow image. Except the adversarial loss, the perceptual loss and total variation loss are employed to improve the quality of the resulted image. Experimental results indicate that our method can obtain excellent performance both on synthetic and realistic snow images in terms of visual observation and commonly used visual quality indices.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.121-126
• /
• 2020

Sound-based machine fault diagnosis is the automatic detection of abnormal sound in the acoustic emission signals of the machines. Conventional methods of using mathematical models were difficult to diagnose machine failure due to the complexity of the industry machinery system and the existence of nonlinear factors such as noises. Therefore, we want to solve the problem of machine fault diagnosis as a deep learning-based image classification problem. In the paper, we propose a CNN-based automatic machine fault diagnosis method using Spectrogram images. The proposed method uses STFT to effectively extract feature vectors from frequencies generated by machine defects, and the feature vectors detected by STFT were converted into spectrogram images and classified by CNN by machine status. The results show that the proposed method can be effectively used not only to detect defects but also to various automatic diagnosis system based on sound.