• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.613-615
• /
• 2002

최근 디지털 이미지 사용이 급속도로 증가함에 있어 자동적인 이미지 데이터 색인과 검색에 관한 연구가 증가하고 있는 추세이나 특정한 분야에 속하지 않은 일반 이미지를 대상으로 하는 연구는 아직까지 만족스럽지 못한 실정이다. 내용기반 이미지 검색은 대량의 일반 이미지 집합에서 사용자가 원하는 이미지를 효율적으로 찾아내는 시스템이며 이에 본 논문에서는 이미지의 색상과 형태의 특징 정보들을 추출하여 자동으로 색인하고 검색하는 새로운 시스템을 제안하였다. 특징 추출은 인간의 이미지 인식 과정에 기반하여 전체적인 정보와 세부적인 정보로 구분하여 수행하는 새로운 기법을 사용하였고 추출된 특징 정보들은 전역 칼라, 부분 영역 칼라, 전역 형태, 부분 영역 형태 정보로 구분되어 데이터베이스에 저장하였으며 유사도 검색 시에는 사용자가 검색 목적에 알맞은 가중치를 적용하여 이미지를 검색하도록 하였다.

• Journal of Digital Convergence
• /
• v.14 no.12
• /
• pp.209-215
• /
• 2016

The quantity of image frames, the widths of transparent slits, and the black bars on the scanline are the three basic elements of scanimation. Besides, the size of scanimation, the color and contrast of scanimation, and the brightness of scanline, etc, can also influence the optical illusion of scanimation. Based on the recent principle of production of 2D scanimation, and through asking questions, and making corresponding experiment, this research finally gets to the conclusion. Based on the principle of production of 3D scanimation, and through various basic testing, this paper aims to verify how to bring out the best visual effects (optical illusion) of animated illusion scanimation in publications by using the 3D animation in the publications. And the future goal is to study and flexibly use Z-axis space in the scanimation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.959-966
• /
• 2017

Currently, the market of digital contents such as e-books, cartoons and webtoons is growing up, but the copyrights infringement are serious issue due to their distribution through illegal ways. However, the technologies for copyright protection are not developed enough. Therefore, in this paper, we propose the NSS-based publication classification method for copyright protection. Using histogram calculated by NSS, we propose classification method for digital contents using SVM. The proposed algorithm will be useful for copyright protection because it lets us distinguish illegal distributed digital contents more easily.

• Journal of Advanced Navigation Technology
• /
• v.8 no.2
• /
• pp.169-175
• /
• 2004

We analyzed about digital watermarking embedded transmission of still image in wireless multimedia communication environment. Also, we proposed improved watermark techniques. It effects that get in original image than method to use conventional image is less and shows robust watermark restoration ability from outside attack. Performance analysis achieved about still image and restoration of watermark information using OFDM/QPSK still image transmission system in wireless channel environment. Analysis result, VI watermark performance that influence in original image is very small. And it could know that show high restoration performance. Also, It showed superior copyright information extraction performance than image watermark in wireless channel environment of same transmission error condition.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.1
• /
• pp.70-76
• /
• 2003

Digital watermarking is a technique embedding hidden information into multimedia data imperceptibly such as images and sounds. Generally an original image is transformed and coded watermark data is embedded in frequency domain watermarking models. In this paper, We propose a new data embedding method using Fresnel transform. A watermark image is fresnel-transformed and the intensity of transformed pattern is embedded into original image. Our watermarking model has the flexibility In data embedding. It is possible to get many embedding patterns from a single watermark image by using various distance parameters with Fresnel transform. All kinds of image models such af shape, letter and photo ran be used as a watermark data. The watermarking experiments were conducted to show the validity of the proposed method, and the results show that our method has the robustness against lossy compression, filtering and geometric transformation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.36-44
• /
• 2022

Reversible data hiding techniques have been developed to hide confidential data in the image by shifting the histogram of the image. These techniques have a weakness in which the security of hidden confidential data is weak. In this paper, to solve this drawback, we propose a technique of triple encrypting confidential data using pixel value information and hiding it in the cover image. When confidential data is triple encrypted using the proposed technique and hidden in the cover image to generate a stego-image, since encryption based on pixel information is performed three times, the security of confidential data hidden by triple encryption is greatly improved. In the experiment to measure the performance of the proposed technique, even if the triple-encrypted confidential data was extracted from the stego-image, the original confidential data could not be extracted without the encryption keys. And since the image quality of the stego-image is 48.39dB or higher, it was not possible to recognize whether confidential data was hidden in the stego-image, and more than 30,487 bits of confidential data were hidden in the stego-image. The proposed technique can extract the original confidential data from the triple-encrypted confidential data hidden in the stego-image without loss, and can restore the original cover image from the stego-image without distortion. Therefore, the proposed technique can be effectively used in applications such as military, medical, digital library, where security is important and it is necessary to completely restore the original cover image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.841-844
• /
• 2015

이미지 인식과 내용분석은 이미지 검색과 멀티미디어 데이터 활용 분야에서 핵심기술이라 할 수 있다. 특히 최근 스마트폰, 디지털 카메라, 블랙박스 등에서 수집되는 영상 데이터 양이 급격히 증가하고 있다. 이에 따라 이미지를 인식하고 내용을 분석하여 활용할 수 있는 기술에 대한 요구가 점차 증대되고 있다. 본 논문에서는 이미지 내용정보를 이용하여 자몽으로 이미지로부터 태그정보를 추출하는 방법을 제안한다. 이 방법은 기계학습 기법인 CNN(Convolutional Neural Network)에 ImageNet의 이미지 데이터와 라벨을 학습시킨 후, 새로운 이미지로부터 라벨정보를 추출하는 것이다. 추출된 라벨을 태그로 간주하고 검색에 활용한다면 기존 검색시스템의 정확도를 향상시킬 수 있다는 것을 실험을 통하여 확인하였다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.119-125
• /
• 2002

우리는 본 논문에서 디지털 영상에 대하여 Hash함수를 이용한 내용기반의 안전한 워터마킹 인증기술을 제시하려고 한다. 허가되지 않는 이미지의 내용변경을 막기 위해 안전한 워터마킹 시스템을 개발하기 위하여 비밀키를 가지고 있는 Hash 함수가 사용되었고, 각 블록의 워터마크신호는 Hash함수의 출력결과를 Seed로 사용하여 의사난수를 발생시킨 값에 따라 생성되어진다. 이미지 기술벡터들은 블록기반 에지 이미지로부터 측정되는데 이 값들은 해롭지 않는 조작 등에 대해서는 쉽게 변화하지 않지만 고의적인 내용변경 등의 조작에 대해서는 이들 값들이 바꾸어지는 성질을 갖고 있다. 워터마크신호의 삽입은 블록기반 스펙트럼 방법에 기초를 두고 있으며 워터마크신호의 크기는 인지성과 강인성이 조화를 이루도록 AC 부 밴드의 지그재그 스캔라인의 DCT 계수들의 지역적인 통계량에 따라 조정되어진다. 또한 저작권인증의 확인을 위한 경계 값의 선택은 통계학적으로 분석되어진다. 수치적인 실험의 결과는 제안된 기술이 강력한 저작권인증의 수행을 위해서 매우 효율적인 것을 보여주고 있다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.3
• /
• pp.220-228
• /
• 2001

Digital watermarking is a technique for the purpose of protecting the ownership of the image by embedding invisible watermarks in a digital imnge. To guarantee the security of the digital watermarking scheme for copyright protection, it is required to satisfy some requirements robustness and perceptual invisibility which provided by the location of embedded bits, the public watermarking algorithm, and the hidden use of the key, which can protect unauthorized accesses from illegal users. For this, in this paper we propose a new copyright watermarking scheme, which is based on one-way hash functions using RSA functions and modular operations. RSA functions are widely used in cryptographic systems. Our watermarking scheme is robust against LSB(Jeast significant bit) attacks and gamma corresction attack, and is also perceptually invisible. We demonstrate the characteristics of our proposed watermarking scheme through experiments.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1177-1183
• /
• 2018

Recent developments in machine learning have attracted a lot of attention for techniques such as machine learning and deep learning that implement artificial intelligence. In this paper, binary malicious code using deep learning based R-CNN is imaged and the feature is extracted from the image to classify the family. In this paper, two steps are used in deep learning to image malicious code using CNN. And classify the characteristics of the family of malicious codes using R-CNN. Generate malicious code as an image, extract features, classify the family, and automatically classify the evolution of malicious code. The detection rate of the proposed method is 93.4% and the accuracy is 98.6%. In addition, the CNN processing speed for image processing of malicious code is 23.3 ms, and the R-CNN processing speed is 4ms to classify one sample.