• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.1
• /
• pp.1-12
• /
• 2004

In this paper, we present an identificable face (n face) detection method robust to color degradation and partial veiling. This method is composed of three parts: segmentation of face candidate regions, extraction of face candidate windows, and decision of veiling. In the segmentation of face candidate regions, face candidate regions are detected by finding skin color regions and facial components such as eyes, a nose and a mouth, which may have degraded colors, from an input image. In the extraction of face candidate windows, face candidate windows which have high potentials of faces are extracted in face candidate regions. In the decision of veiling, using an eigenface method, a face candidate window whose similarity with eigenfaces is maximum is determined and whether facial components of the face candidate window are veiled or not is determined in the similar way. Experimental results show that the proposed method yields better the detection rate by about $11.4\%$ in test DB containing color-degraded faces and veiled ones than a conventional method without considering color degradation and partial veiling.

• 건강소식
• /
• v.3 no.2 s.17
• /
• pp.46-47
• /
• 1975

얼굴은 뇌에 가깝다. 그리고 얼굴은 마음의 창이다. 얼굴은 모든 병의 스크린이다. 때문에 얼굴에는 병색이 가장 먼저 나타난다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1998.10a
• /
• pp.521-524
• /
• 1998

• Hospice
• /
• s.67
• /
• pp.14-15
• /
• 2019

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.226-229
• /
• 2011

얼굴검출기술의 발전으로 인하여, 다양한 분야에 얼굴 검출을 활용한 기술이 이용되고 있다. 최근 Viola 와 Jones 의 얼굴검출 방법이 신뢰도 있는 검출률과 빠른 연산속도로 인하여 주로 이용되고 있다. 하지만 고해상도 이미지와 제한된 하드웨어를 사용하는 시스템의 경우, 실시간 처리가 어려워지는 문제가 있다. 본 논문에서는 이와 같은 문제를 해결하고자 거리 정보를 이용한 빠른 얼굴검출방법을 제안한다. 속도 개선을 위해 먼저 거리 정보를 이용하여 영상의 불필요한 부분을 제거하고, 피부색상정보를 이용하여 관심영역을 설정한다. 또 크기에 대응하기 위해 피라미드 이미지를 이용하는 방법 대신, 거리 정보를 이용하여 얼굴의 크기를 추정한다. 마지막으로 검색창 내의 거리 분산을 계산하여, 평평하거나 굴곡이 심한 영역을 제거함으로 얼굴 검출 속도를 개선하였다. 실험결과 기존 방법에 비해 더 빠른 검출속도와 유사한 검출성능을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.926-927
• /
• 2019

본 논문은 개방형 얼굴 인식 문제를 다룬다. 이 문제는 학습되지 않는 대상에 의해 발생하는 거짓 양성 오류문제를 포함하며, 이로 인해 얼굴인식 기술을 보안 시스템에 적용하는 것을 어렵게 만든다. 본 논문에서는 이러한 개방형 얼굴 인식 문제를 효과적으로 해결하기 위해 먼저 얼굴 검증 방법으로 식별력이 강한 특징 벡터를 생성하고, 이를 바탕으로 일반적인 분류기가 아닌 추가학습과 실시간 처리가 가능한 군집화 방식의 알고리즘을 제안한다. 이 방법을 적용한 실험 결과 80 명의 얼굴이 포함된 FaceScrub 데이터 세트에서 4 명을 제외하고 학습시켰을 때 98%의 정확도와 0%의 특이도를 얻을 수 있었다.

• Journal of architectural history
• /
• v.21 no.3
• /
• pp.73-92
• /
• 2012

This study mainly inquired characteristics and changes of 'Chang-aelgool' through 38 cases(with 161 Ssang-chang) of annex and pavillion buildings in Yeong-nam region which are built during the Chosun dynasty. The method of inquiry included actual survey of windows along with bibliographical research, and the results are as below. First, through the discovery of the term 'Chang-aelgool' as an indication of the window-forming frame in 'YeongGeonUiGwe'(1680 A.D), it is apparent that the term 'Chang-aelgool' was widely used in Korea from the late 17th century. Second, the 'Chang-aelgool' of study objects are classified into 4 categories. Type I and II are comprised of mitre-joints which cover the 4 corners of 'Chang-aelgool' and mainly used in building annex and pavillion buildings during the early period of the Chosun dynasty. Type III was widely used during the early and middle period of the Chosun dynasty and drastically dropped in number during the late period of the dynasty. Type IV is comprised of mitre-joint of the upper-half, tenon-jointing of the lower-half and widely used in annex and pavillion building during the late period of the Chosun dynasty. Third, the form of 'Chang-aelgool' has changed from rectangular form with longer width during the early period of Chosun dynasty to square form during the middle period and eventually ended up as a rectangular form with longer height during the late period of the dynasty. Fourth, it is considered that while mullion which is located in the center of 'Chang-aelgool' was mainly used around the main floored room during the early period of the Chosun dynasty, became commonly used in main floored room and 'ondol' rooms during the middle period and drastically dropped in number from then and ended up being not in use after the mid 18th century.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.163-172
• /
• 2005

When tracking a human face in the moving pictures with complex background under irregular lighting conditions, the detected face can be larger including background or smaller including only a part of the face. Even background can be detected as a face area. To solve these problems, this paper proposes a new face tracking method using a block difference image and a Kalman estimator. The block difference image allows us to detect even a small motion of a human and the face area is selected using the skin color inside the detected motion area. If the pixels with skin color inside the detected motion area, the boundary of the area is represented by a code sequence using the 8-neighbor window and the head area is detected analysing this code. The pixels in the head area is segmented by colors and the region most similar with the skin color is considered as a face area. The detected face area is represented by a rectangle including the area and its four vertices are used as the states of the Kalman estimator to trace the motion of the face area. It is proved by the experiments that the proposed method increases the accuracy of face detection and reduces the fare detection time significantly.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.11a
• /
• pp.112-113
• /
• 2013

서브 홀로그램 디스플레이는 디지털 홀로그래피 디스플레이의 제한된 시역을 관찰자의 동공 크기로 맞게 구현하여 사용자가 더 넓은 범위에서 더 큰 영상을 느끼도록 만드는 홀로그래픽 디스플레이이다. 본 논문에서는 서브홀로그램 방식에서 시야 창 문제를 해결하기 위해, Depth 카메라와 스테레오 카메라의 하이브리드 구성을 이용하여 정밀한 사용자 동공 추적 기법에 대해서 제안한다. 저해상도의 깊이 카메라의 얼굴 인식 정보를 바탕으로 고해상도 스테레오 카메라에서의 얼굴 및 눈의 후보영역을 찾고, 고해상도 스테레오 카메라에서 후보 영역 내의 동공 위치를 잦아서 빠르면서도 정밀한 동공 추적이 가능하도록 하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.116-128
• /
• 2011

In this paper, we propose the structure of a high-performance face-detection engine that responds well to facial rotating changes using rotation transformation which minimize the required memory usage compared to the previous face-detection engine. The validity of the proposed structure has been verified through the implementation of FPGA. For high performance face detection, the MCT (Modified Census Transform) method, which is robust against lighting change, was used. The Adaboost learning algorithm was used for creating optimized learning data. And the rotation transformation method was added to maintain effectiveness against face rotating changes. The proposed hardware structure was composed of Color Space Converter, Noise Filter, Memory Controller Interface, Image Rotator, Image Scaler, MCT(Modified Census Transform), Candidate Detector / Confidence Mapper, Position Resizer, Data Grouper, Overlay Processor / Color Overlay Processor. The face detection engine was tested using a Virtex5 LX330 FPGA board, a QVGA grade CMOS camera, and an LCD Display. It was verified that the engine demonstrated excellent performance in diverse real life environments and in a face detection standard database. As a result, a high performance real time face detection engine that can conduct real time processing at speeds of at least 60 frames per second, which is effective against lighting changes and face rotating changes and can detect 32 faces in diverse sizes simultaneously, was developed.