• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.157-160
• /
• 2022

딥러닝이 각광받기 시작하면서 인간의 자세와 행동을 인식하고 분류하기 위한 인공지능 기술 또한 급속도로 발전하게 되었다. 영상에서 인간의 자세를 디지털 데이터로 표현할 때 인체의 주요 관절점의 위치와 연결관계를 나타내는 스켈레톤 표현 방식을 주로 사용한다. 본 논문에서는 스켈레톤 데이터에 비밀 메시지를 은닉할 수 있는 스테가노그라피 알고리즘에 대해 소개하고, 스켈레톤을 구성하는 주요 관절점 키포인트를 조작했을 때 행동 인식 인공지능 모델이 어떻게 반응하는지 살펴봄으로써 스켈레톤 데이터에 대한 스테가노그라피 알고리즘의 특성과 보안성에 대해 논의한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.94-101
• /
• 2012

This paper proposes an improved image steganalysis scheme to raise the detection rate of stego images out of cover images. To improve the detection rate of stego image in the steganalysis, tiny variation caused by data hiding should be amplified. For this, we extract feature vectors of cover image and stego image by two steps. First, we separate image into upper 4 bit subimage and lower 4 bit subimage. As a result, stego noise is expanded more than two times. We decompose separated subimages into twelve subbands by applying 3-level Haar wavelet transform and calculate co-occurrence probabilities of two different subbands in the same scale. Since co-occurrence probability of the two wavelet subbands is affected by data hiding, it can be used as a feature to differentiate cover images and stego images. The extracted feature vectors are used as the input to the multilayer perceptron(MLP) classifier to distinguish between cover and stego images. We test the performance of the proposed scheme over various embedding rates by the LSB, S-tool, COX's SS, and F5 embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• The Journal of the Korea Contents Association
• /
• v.8 no.5
• /
• pp.29-37
• /
• 2008

To transmit video bit stream over low bandwidth such as wireless channel, high compression algorithm like H.264 codec is exploited. In transmitting high compressed video bit-stream over low bandwidth, packet loss causes severe degradation in image quality. In this paper, a new algorithm for recovery of missing or erroneous motion vector is proposed. Considering that the missing or erroneous motion vectors in blocks are closely correlated with those of neighboring blocks. Motion vector of neighboring blocks are clustered according to average linkage algorithm clustering and a representative value for each cluster is determined to obtain the candidate motion vector sets. As a result, simulation results show that the proposed method dramatically improves processing time compared to existing H.264/AVC. Also the proposed method is similar to existing H.264/AVC in terms of visual quality.

• Journal of Digital Contents Society
• /
• v.17 no.5
• /
• pp.433-439
• /
• 2016

In this paper, we propose a optimized steganography how to improve the image degradation of the existing data hiding techniques. This method operates in the compressed domain(JPEG) of an image. Most of the current information concealment methods generally change the coefficients to hide information. And several methods have tried to improve the performance of a typical steganography method such as F5 including a matrix encoding. Those papers achieved the object of reducing the distortion which is generated as hiding data in coefficients of compressed domain. In the proposed paper we analyzed the effect of the quantization table for hiding the data in the compressed domain. As a result, it found that can decrease the distortion that occur in the application of steganography techniques. This paper provides a little (Maximum: approximately 6.5%) further improved results in terms of image quality in a data hiding on compressed domain. Developed algorithm help improve the data hiding performance of compressed image other than the JPEG.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.2C
• /
• pp.49-58
• /
• 2005

For the improvement of coding efficiency, the H.264 standard uses new coding tools. Using these coding tools, H.264 has achieved significant improvements from rate-distortion point of view. The adoption of these tools enables a macroblock in H.264 to have more information, sixteen motion vectors, four reference frames and a macroblock mode. In this paper, we present an efficient temporal error concealment algorithm by using not only motion vectors and reference frames but also macroblock mode of neighbor macroblocks. Our algorithm conceals the macroblock error with variable sizes, $16{\times}16,\;16{\times}8,\;8{\times}16,\;8{\times}8$ depending on the macroblock modes of neighbor macroblocks. Simulation results show that the proposed method increase the objective quality regardless of bit-rate and block error rate.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.845-853
• /
• 2022

As the memory capacity of smartphone increases, the type and amount of privacy stored in the smartphone is also increasing. but recently there is an increasing possibility that various personal information such as photos and videos of smartphones may be leaked due to malicious apps by malicious attackers or other people such as repair technicians. This paper analyzed and studied the security and vulnerability of these vault apps by analyzing the cryptography algorithm and data protection function. We analyzed 5.3.7(June 13, 2022) and 3.3.2(December 30, 2020) versions of AppLock, the most downloaded information-hidding apps registered with Google Play, and found various vulnerabilities. In the case of access control, there was a vulnerability in that values for encrypting patterns entered by users were hardcoded into plain text in the source code, and encrypted pattern values were stored in xml files. In addition, in the case of the vault function, there was a vulnerability in that the files and log files for storing in the vault were not encrypted.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.422-424
• /
• 1999

본 논문에서는 질감 특징과 신경회로망을 이용한 유방암조직영상의 분할 방법을 제안한다. 신경회로망의 입력 노드에 사용될 질감 특징을 얻기 위해 10개의 영상에 대해 각 영역(양성세포핵, 음성세포핵, 배경)에서 10개씩의 화소를 선택하고, 그 화소를 중심으로 하는 5$\times$5 영역 30개를 획득, 총 300개의 영역에 대해 R, G, B 각각의 밴드에서 18개의 질감특징을 추출한다. 54개의 입력노드, 28개의 은닉노드, 3개의 출력노드의 구조를 가진 신경회로망을 구성하고, 역전파 학습 알고리즘을 사용하여 신경회로망을 최대오차율이 10-3보다 작을 때까지 학습시킨다. 학습에 의해 획득되어진 분류기를 이용하여 유방암 조직 세포영상을 양성세포핵, 음성세포핵, 배경부분으로 자동 분할한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.2
• /
• pp.314-321
• /
• 2003

Recently, many studies about digital watermarking have been doing, and their purpose is to protect copyright of multimedia data. In this paper, the performances of digital watermarkings, in order to hide information of copyright into digital images, are analyzed. The watermarks embedded in subbands on wavelet transform domain are transformed by the processing such as image compression, and the degree of the transformation in each subband depend on its statistical characteristics. That says, we must consider the characteristics of subbands for better watermarking.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1948-1951
• /
• 2003

본 논문에서는 디지털 멀티미디어 방송 및 양방향 인터넷 방송 등에서 효율적인 객체기반 방송 서비스를 제공하기 위한 비선형 비디오 편집 시스템을 구현하였다. 구현된 시스템은 실시간으로 카메라를 통해 입력되는 영상 데이터에 대해 자동으로 움직이는 객체를 추출하는 자동분할과 HDD(hard Disk) 등에 저장되어 있는 동영상을 사용자의 조력에 의해 분할하는 반자동분할 기능을 제공한다. 그리고 추출된 객체를 저장매체에 저장되어 있는 그래픽 및 실사 배경영상과 합성하고 MPEG으로 부호화 할 수 있다. 또한 정보 유출을 원치 않는 객체에 대한 은닉 기능을 가지고 있다. 따라서 구현된 시스템은 비디오 정보제공자가 편리하게 객체를 분할하고 편집할 수 있으며 비디오 정보를 단기간에 효율적으로 비디오 정보 사용자에게 공급할 수 있는 기능을 제공한다.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.2
• /
• pp.25-32
• /
• 2000

Digital watermarking has been recently proposed as the means of intellectual property right protection of multimedia data. We present a novel watermarking scheme to hide a copyright information in a digital image. The method Is based on the 2D DWT(Discrete Wavelet Transform) and image statistics. Gaussian and Laplacian noises as the watermarks are added to the large wavelet coefficients at the high and middle frequency bands in the wavelet domain. Experimental results show that the proposed Laplacian watermark is stronger to several common image distortions, such as noises, JPEG coding as different qualities, Gaussian blurring, and edge enhancement.