• The Transactions of the Korea Information Processing Society
• /
• v.5 no.5
• /
• pp.1130-1139
• /
• 1998

This paper presents an integrated solution for the content-based news video indexing and the retrieval. Currently, it is impossible to automatically index a general video, but we can index a specific structural video such as news videos. Our proposed model extracts automatically the key frames by using the structured knowledge of news and consists of the news item segmentation, caption recognition and search browser modules. We present above three modules in the following: the news event segmentation module recognizes an anchor-person shot based on face recognition, and then its news event are divided by the anchor-person's frame information. The caption recognition module detects the caption-frames with the caption characteristics, extracts their character region by the using split-merge method, and then recognizes characters with OCR software. Finally, the search browser module could make a various of searching mechanism possible.

• Annual Conference of KIPS
• /
• 2005.11a
• /
• pp.743-746
• /
• 2005

본 논문에서는 디지털 비디오 인코딩 과정의 VLC(variable length coding) 영역에서 블록계층의 DC/AC 성분을 이용한 인증과 서명의 이중 비디오 워터마킹 시스템을 제안하였다. 제안한 기법은 블록계층의 DC 성분과 AC 성분에서 HVS(human visual system)의 특성을 고려한 것이다. 인증 워터마킹은 주요한 정보를 포함하는 저주파 영역과 윤곽선 정보를 포함하는 중간 주파수 영역을 이용하여 인트라 프레임의 DC 성분과 움직임 벡터의 부호를 변형시켰고, 서명 워터마킹은 모든 프레임의 AC 성분들 중에서 마지막 AC 성분의 Level이 '1'인 경우에만 워터마크를 삽입하였다. 서명 워터 마크 검출은 저작권자의 비밀 키에 의해서만 가능하고, 기술적인 면에서 저자권자의 판별 기준이 될 수 있다. 제안한 이중 비디오 워터마킹 시스템의 특징은 인증과 서명의 두 가지 기능을 선택적으로 수행할 수 있으며, 계산과정이 복잡하지 않으면서 비트 스트림(bit-stream)을 유지시킨다. 그리고 실험 결과에서 기존의 방법보다 화질 면에서 $2{\sim}3dB$ 더 높은 수치를 얻어 우수함을 보였고, 인코딩 수행 속도에 미치는 영향은 거의 없었으며, 향후 실시간 인코딩 처리에 응용될 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1086-1092
• /
• 2009

Stereoscopic conversion has been an important and challenging issue for many 3-D video applications. Usually, there are two different stereoscopic conversion approaches, i.e., image motion-based conversion that uses motion information and object-based conversion that partitions an image into moving or static foreground object(s) and background and then converts the foreground in a stereoscopic object. As well, since the input sequence is MPEG-1/2 compressed video, motion data stored in compressed bitstream are often unreliable and thus the image motion-based conversion might fail. To solve this problem, we present the utilization of key-motion that has the better accuracy of estimated or extracted motion information. To deal with diverse motion types, a transform space produced from motion vectors and color differences is introduced. A key-motion is determined from the transform space and its associated stereoscopic image is generated. Experimental results validate effectiveness and robustness of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.377-378
• /
• 2018

This paper introduce the improvement of the pupil motion recognition algorithm in the previously reported "Eye-Motion Communication System using FPGA and OpenCV". It is a system for generalized paralysis and Lou Gehrig patients who can not move their body naturally, recognizing the pupil's motion and selecting the text in the FPGA in real time. In this paper, we improve the speed of motion recognition by minimizing the operation of eye detection function based on the user being general paralysis patient.

• Journal of IKEEE
• /
• v.7 no.2 s.13
• /
• pp.210-217
• /
• 2003

A novel characteristic value extraction method based on mathematical morphology is proposed. Morphological spatial frequency defined by morphological pattern distribution function is introduced and applied to define a new feature called ‘average height.' The average height is used to define a characteristic value which is to be used to generate an index key value for content-based image retrieval. Superiority of the method was proved for various images by experiment. Furthermore the fact that the proposed method does not need threshold to obtain binary image provides its applicability to content-based image retrieval.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.1525-1528
• /
• 2008

이동 에이전트는 분산 컴퓨팅 환경에서 유용하게 쓰이는 컴퓨터 통신 분야의 새로운 응용기술이지만, 에이전트가 이동함으로써 발생하는 여러 가지 보안상의 문제점들을 가지고 있다. 특히, 악의적인 호스트로부터 이동 에이전트를 보호하는 방법의 중요성이 점점 높아지고 있으며, 타임 체킹 기술을 이용한 보호 기법 등이 기존에 제안되었다. 그러나 기존에 제안된 타임 체킹 기술은 데이터를 누적함으로써 네트워크 부하를 초래할 수 있다. 또한, 동일한 도메인 내에서는 동일한 세션키를 사용하여 에이전트를 암호화함으로써 타임 체킹 기법의 중요한 데이터인 에이전트 도착 및 출발 시간이 조작될 가능성이 있다. 본 논문에서는 기존에 제안된 타임 체킹 기술을 기반으로 에이전트의 누적 데이터 크기를 제한하여 네트워크 부하를 줄일 수 있는 기법과 RSA 암호화 기법을 사용하여 이미 기록된 에이전트의 도착 및 출발 시간 조작을 방지할 수 있는 기법을 제안한다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.416-428
• /
• 2001

In order to build a news archive system. the news video stream should be first segmented into several articles, ad their contents are abstracted effectively. This abstraction helps the users to understand the contents of the article without playing the whole video stream. This paper proposes a new article boundary detection scheme for the news video streams together with a new news article abstraction scheme using the shot types of the news video data. The shots in the news video are classified into anchor person shots, interview shots, speech shots, reporting shots, graphic shots, and others. Since the news article starts with an anchor shot whose duration is relatively longer than other shots with special screen structure, the article boundary in detected by the computing the length of the shot and checking the screen structure in the proposed scheme. For the effective abstraction of the article video, the graphic image located in the right-top of the anchor shot frames is primarily used in the proposed abstraction scheme since it is the abstraction of the article made by the producer of the news according to its contents so that it contains a lot of meaningful information. The key frames of the other shots except interview and report shots are also used to abstract the contents of the articles in the proposed scheme. Upon experimental results, the precision and recall values of the proposed article boundary detection scheme could be 92% and 96%, respectively. This paper also presents a design and implementation of a prototype news archive system on WWW that consists of an indexing tool, an authoring tool, a database for meta-data of the news, and a browsing tool.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2427-2432
• /
• 2014

Color-$X^2$ is used as a method for scene change detection. It extracts a violent scene in an elevator and then could be used for real-time surveillance of criminal acts. The scene could be also used to secure after-discovered evidences and to prove analysis processes. Video Forensic is defined as a research on various methods to efficiently analyze evidences upon crime-related visual images in the field of digital forensic. The method to use differences of color-histogram detects the difference values of histogram for RGB color from two frames respectively. Our paper uses Color-$X^2$ histogram that is composed of merits of color histogram and ones of $X^2$ histogram, in order to efficiently extract violent scenes in elevator. Also, we use a threshold so as to find out key frame, by use of existing Color-$X^2$ histogram. To increase the probability that discerns whether a real violent scene or not, we take advantage of statistical judgments with 20 sample visual images.

• Journal of radiological science and technology
• /
• v.39 no.2
• /
• pp.199-208
• /
• 2016

$^{99}mTc-MAG_3$ Renal scan is a method that acquires dynamic renal scan image by using $^{99}mTc-MAG_3$ and dynamically visualizes process of radioactive agent being absorbed to kidney and excreted continuously. Once the test starts, ratio in both kidneys in 1~2.5 minutes was measured to obtain split renal function and split renal function can be expressed in ratio based on overall renal function. This study is based on compares split renal function obtained from data acquired from posterior detector, which is a conventional renal function test method, with split renal function acquired from the geometric mean of values obtained from anterior and posterior detectors, and studies utility of attenuation compensation depending on difference in geometric mean kidney depth. From July, 2015 to February 2016, 33 patients who undertook $^{99}mTc-MAG_3$ Renal scan(13 male, 20 female, average age of 44.66 with range of 5~70, average height of 160.40cm, average weight of 55.40kg) were selected as subjects. Depth of kidney was shown to be 65.82 mm at average for left and 71.62 mm at average for right. In supine position, 30 out of 33 patients showed higher ratio of deep-situated kidney and lower ratio of shallow-situated kidney. Such result is deemed to be due to correction by attenuation between deep-situated kidney and detector and in case where there is difference between the depth of both kidneys such as, lesions in or around kidney, spine malformation, and ectopic kidney, ratio of deep-situated kidney must be compensated for more accurate calculation of split renal function, when compared to the conventional test method (posterior detector counting).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2C
• /
• pp.156-165
• /
• 2006

In this paper, a new intelligent moving target tracking and surveillance system basing on the pan/tilt-embedded stereo camera system is suggested and implemented. In the proposed system, once the face area of a target is detected from the input stereo image by using a YCbCr color model and phase-type correlation scheme and then, using this data as well as the geometric information of the tracking system, the distance and 3D information of the target are effectively extracted in real-time. Basing on these extracted data the pan/tilted-imbedded stereo camera system is adaptively controlled and as a result, the proposed system can track the target adaptively under the various circumstance of the target. From some experiments using 480 frames of the test input stereo image, it is analyzed that a standard variation between the measured and computed the estimated target's height and an error ratio between the measured and computed 3D coordinate values of the target is also kept to be very low value of 1.03 and 1.18$\%$ on average, respectively. From these good experimental results a possibility of implementing a new real-time intelligent stereo target tracking and surveillance system using the proposed scheme is finally suggested.