• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.444-447
• /
• 2022

In recent years, computer vision image classification tasks have become faster and better due to deeper neural network architectures. But while most image classification tasks are designed to classify images based on specific image features (such as distinguishing between cats and dogs), there are not many classification models that have been trained to distinguish between time periods such as day and night or different seasons of the year. And while some research has been done into distinguishing between seasons in images of the same location, this paper presents a varied approach to the problem of seasonal classification of generic images. Three methods for seasonal image classification, from simple feature extraction, to building a convolutional neural network, to transfer learning were studied and the accuracy results were compared and analyzed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.727-730
• /
• 2021

이미지와 비디오 합성 기술에 대한 수요가 늘어남에 따라, 인간의 손에만 의존하여 이미지나 비디오를 합성하는데에는 시간과 자원이 한정적이며, 전문적인 지식을 요한다. 이러한 문제를 해결하기 위해 최근에는 스타일 변환 네트워크를 통해 이미지를 변환하고, 믹싱하여 생성하는 알고리즘이 등장하고 있다. 이에 본 논문에서는 GAN을 이용한 스타일 변환 네트워크를 통한 자연스러운 스타일 믹싱에 대해 연구했다. 먼저 애니메이션 토이 스토리의 등장인물에 대한 데이터를 구축하고, 모델을 학습하고 두 개의 모델을 블렌딩하는 일련의 과정을 거쳐 모델을 준비한다. 그 다음에 블렌딩된 모델을 통해 타겟 이미지에 대하여 스타일 믹싱을 진행하며, 이 때 이미지 해상도와 projection 반복 값으로 스타일 변환 정도를 조절한다. 최종적으로 스타일 믹싱한 결과 이미지들을 바탕으로 하여 스타일 변형, 스타일 합성이 된 인물에 대한 동영상을 생성한다.

• Journal of Platform Technology
• /
• v.12 no.1
• /
• pp.128-140
• /
• 2024

'Deepfake' refers to a video synthesis technique that utilizes various artificial intelligence technologies to create highly realistic fake content, causing serious confusion to individuals and society by being used for generating fake news, fraud, malicious impersonation, and more. To address this issue, there is a need for methods to detect malicious images generated by deepfake accurately. In this paper, we extract and analyze saliency features from deepfake and real images, and detect candidate synthesis regions on the images, and finally construct an automatic deepfake detection model by focusing on the extracted features. The proposed saliency feature-based model can be universally applied in situations where deepfake detection is required, such as synthesized images and videos. To demonstrate the performance of our approach, we conducted several experiments that have shown the effectiveness of the deepfake detection task.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.111-121
• /
• 2021

As the main carrier of information, digital image is becoming more and more important. However, with the popularity of image acquisition equipment and the rapid development of image editing software, in recent years, digital image counterfeiting incidents have emerged one after another, which not only reduces the credibility of images, but also brings great negative impacts to society and individuals. Image copy-paste tampering is one of the most common types of image tampering, which is easy to operate and effective, and is often used to change the semantic information of digital images. In this paper, a method to protect the authenticity and integrity of image content by studying the tamper detection method of image copy and paste was proposed. In view of the excellent learning and analysis ability of deep learning, two tamper detection methods based on deep learning were proposed, which use the traces left by image processing operations to distinguish the tampered area from the original area in the image. A series of experimental results verified the rationality of the theoretical basis, the accuracy of tampering detection, location and classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.6
• /
• pp.774-784
• /
• 2021

The object detection and recognition process is a very important task in the field of computer vision, and related research is actively being conducted. However, in the actual object recognition process, the recognition accuracy is often degraded due to the resolution mismatch between the training image data and the test image data. To solve this problem, in this paper, we designed and developed an integrated object recognition and super-resolution framework by proposing an image super-resolution technique to improve object recognition accuracy. In detail, 11,231 license plate training images were built by ourselves through web-crawling and artificial-data-generation, and the image super-resolution artificial neural network was trained by defining an objective function to be robust to the image flip. To verify the performance of the proposed algorithm, we experimented with the trained image super-resolution and recognition on 1,999 test images, and it was confirmed that the proposed super-resolution technique has the effect of improving the accuracy of character recognition.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.129-132
• /
• 2022

Super-resolution is the process of converting a low-quality image into a high-quality image. This study was conducted using ESPCN. In a super-resolution deep neural network, different quality images can be output even when receiving the same input data according to the activation function that determines the weight when passing through each node. Therefore, the purpose of this study is to find the most suitable activation function for super-resolution by applying the activation functions ReLU, ELU, and Swish and compare the quality of the output image for the same input images. The CelebaA Dataset was used as the dataset. Images were cut into a square during the pre-processing process then the image quality was lowered. The degraded image was used as the input image and the original image was used for evaluation. As a result, ELU and swish took a long time to train compared to ReLU, which is mainly used for machine learning but showed better performance.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.297-302
• /
• 2012

In this paper, we present a object detection and tracking method based on image context analysis. It is robust from the image variations such as complicated background, dynamic movement of the object. Image context analysis is carried out using the hybrid network of k-means and RBF. The proposed object detection employs context-driven adaptive Bayesian framework to relive the effect due to uneven object images. The proposed method used feature vector generator using 2D Haar wavelet transform and the Bayesian discriminant method in order to enhance the speed of learning. The system took less time to learn, and learning in a wide variety of data showed consistent results. After we developed the proposed method was applied to real-world environment. As a result, in the case of the object to detect pass outside expected area or other changes in the uncertain reaction showed that stable. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.6
• /
• pp.601-605
• /
• 2020

In large ships with complex structures, it is difficult to locate workers. In particular, it is not easy to detect when a worker falls down, making it difficult to respond quickly. Thus, research is being conducted to detect fallen workers using a camera or by attaching a device to the body. Existing image-based fall detection systems have been designed to detect a person's body parts; hence, it is difficult to detect them in various ships and postures. In this study, the entire fall area was extracted and deep learning was used to detect the fallen shipworker based on the image. The data necessary for learning were obtained by recording falling states at the shipyard. The amount of learning data was augmented by flipping, resizing, and rotating the image. Performance evaluation was conducted with precision, reproducibility, accuracy, and a low error rate. The larger the amount of data, the better the precision. In the future, reinforcing various data is expected to improve the effectiveness of camera-based fall detection models, and thus improve safety.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1643-1656
• /
• 2010

It is necessary to develop a system to judge inferiority of goods to minimize the loss at small factories in which produces various kinds of goods with small amounts. That system can be developed based on HTM theory. HTM is a model to apply the operation principles of the neocortex in human brain to the machine learning. We have to build the trained HTM network to use the HTM-based machine learning system. It requires the knowledge for the HTM theory. This paper presents the design and implementation of the training system to support the development of HTM networks which recognize the molding parts to judge its badness. This training system allows field technicians to train the HTM network with high accuracy without the knowledge of the HTM theory. It also can be applied to any kind of the HTM-based judging systems for molding parts.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2016

Nowadays, there are many research for recognizing face of people using the machine vision. the machine vision is classification and analysis technology using machine that has sight such as human eyes. In this paper, we propose algorithm for classifying human face using this machine vision system. This algorithm consist of Convolutional Neural Network and cascade face detector. And using this algorithm, we classified the face of subjects. For training the face classification algorithm, 2,000, 3,000, and 4,000 images of each subject are used. Training iteration of Convolutional Neural Network had 10 and 20. Then we classified the images. In this paper, about 6,000 images was classified for effectiveness. And we implement the system that can classify the face of subjects in realtime using USB camera.