• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.443-446
• /
• 2000

인간은 일상 생활에서 제스처, 표정과 같은 비언어적인 수단을 이용하여 수많은 정보를 전달한다. 따라서 자연스럽고 지적인 인터페이스를 구축하기 위해서는 제스처 인식에 관한 연구가 매우 중요하다. 본 논문에서는 영상 시퀸스의 각 영상들이 가지고 있는 정적인 양이 아닌, 영상과 이웃하는 영상들의 변화량을 수치적으로 측정하고 이를 주성분 분석법(PCA : Principal Component Analysis)과 은닉 마르코프 모델(HMM : Hidden Markov Model)을 이용하여 인식하는 방법을 소개한다.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.14 no.2
• /
• pp.1-20
• /
• 1996

we describes a method for realizing the color conversion from the tristimulus (X, Y, Z) values to the print ink signals (C, M, Y) by using neural networks. The realized nonlinear color conversion system consists of two hidden layers those have seventeen nodes. We determined the C, M, Y values of the input control signals to compensate the printer nonlinearity of real systems. Experimental results showed that the described method is useful and valid to realized the nonlinear color conversion.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1135-1139
• /
• 1989

Three layered neural network was applied for the pattern recognition problem of human spermatozoa in clinical test. The goodness of recognition rate was studied in relation to the number of hidden layer cells and of output layer cells. The proposed method provided better results than conventional template matching technique. Parallel processing of the back propagation learning algorithm was also studied using transputers and its performance was evaluated.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.28A no.5
• /
• pp.398-406
• /
• 1991

This paper presents a graphics accelerator for fast image generation. The accelarator has three major functional blocks: linear interpolator, multipliers and Edgee Painting Tree. Linear interpolator with coupled binary tree structure interpolates functional values of two end points. Two multipliers compute input values of interpolator in parallel. Mask pattern which removes out invalid data is generated by Edge Painting Tree. The proposed architecture in this paper is responsible for 64 pixels and can process about 5,900 10x10polygons per second.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.127-134
• /
• 2022

Steganography is a hidden technique in which secret messages are hidden in various multimedia files, and it is widely exploited for cyber crime and attacks because it is very difficult for third parties other than senders and receivers to identify the presence of hidden information in communication messages. Botnet typically consists of botmasters, bots, and C&C (Command & Control) servers, and is a botmasters-controlled network with various structures such as centralized, distributed (P2P), and hybrid. Recently, in order to enhance the concealment of botnets, research on Stego Botnet, which uses SNS platforms instead of C&C servers and performs C&C communication by applying steganography techniques, has been actively conducted, but image or video media-oriented stego botnet techniques have been studied. On the other hand, audio files such as various sound sources and recording files are also actively shared on SNS, so research on stego botnet based on audio steganography is needed. Therefore, in this study, we present the results of comparative analysis on hidden capacity by file type and tool through experiments, using a stego botnet that performs C&C hidden communication using audio files as a cover medium in Telegram Messenger.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.11
• /
• pp.1329-1340
• /
• 2016

Recently, Zhang proposed a scheme to hide information in encrypted images using synchronous stream ciphers. After the receiver decrypts the encrypted image and extracts data by calculating the spatial correlation property value using the fluctuation function which is designed to calculate spacial correlation between adjacent pixels in a decrypted image. Then, Hong improved the Zhang's data hiding scheme by introducing the side match technique. In this paper, a novel fluctuation function is proposed to reduce the recovery errors which arise during extracting hidden data. Then, we also demonstrated that the proposed fluctuation function outperforms the previous functions through computer simulations for sample images.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.41-43
• /
• 2019

Image-to-image 변환에서 인상적인 성능을 보이는 StarGAN 은 모델의 성능에 중요한 영향을 끼치는 adversarial weight, classification weight, reconstruction weight 라는 세가지 하이퍼파라미터의 결정을 전제로 하고 있다. 본 연구에서는 이 중 conditional GAN loss 인 adversarial loss 와 classification loss 를 대치할 수 있는 attribute loss를 제안함으로써, adversarial weight와 classification weight 를 최적화하는 데 걸리는 시간을 attribute weight 의 최적화에 걸리는 시간으로 대체하여 하이퍼파라미터 탐색에 걸리는 시간을 획기적으로 줄일 수 있게 하였다. 제안하는 attribute loss 는 각 특징당 GAN 을 만들 때 각 GAN 의 loss 의 합으로, 이 GAN 들은 hidden layer 를 공유하기 때문에 연산량의 증가를 거의 가져오지 않는다. 또한 reconstruction loss 를 단순화시켜 연산량을 줄인 simplified content loss 를 제안한다. StarGAN 의 reconstruction loss 는 generator 를 2 번 통과하지만 simplified content loss 는 1 번만 통과하기 때문에 연산량이 줄어든다. 또한 이미지 Framing 을 통해 배경의 왜곡을 방지하고, 양방향 성장을 통해 학습 속도를 향상시킨 아키텍쳐를 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.5
• /
• pp.841-849
• /
• 2001

The pixel information of the object was obtained sequentially and pixels were clustered to a label by the line labeling method. Feature points were determined by finding the slope for edge pixels after selecting the fixed number of edge pixels. The slope was estimated by the least square method to reduce the detection error. Once a matching point was determined by comparing the feature information of the object and the pattern, the parameters for translation, scaling and rotation were obtained by selecting the longer line of the two which passed through the matching point from left and right sides. Finally, modified Hausdorff Distance has been used to identify the similarity between the object and the given pattern. The multi-label method was developed for recognizing the patterns with more than one label, which performs the modified Hausdorff Distance twice. Experiments have been performed to verify the performance of the proposed algorithm and method for simple target image, complex target image, simple pattern, and complex pattern as well as the partially hidden object. It was proved via experiments that the proposed image matching algorithm for recognizing the object had a good performance of matching.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.