• Journal of KIISE
• /
• v.43 no.5
• /
• pp.516-523
• /
• 2016

For old-age makeups, makeup artists first make a mold cast of an actor's face using plaster and then sculpt wrinkles in clay on the plaster mold. After finishing the clay sculpture, its negative plaster mold is fabricated and silicone skin patches are finally made for application to the actor's face. This process takes a few days and is tedious for actors and makeup artists. With recent advances in 3D printing and scanning technology, it is becoming easier to scan and fabricate 3D faces. This paper presents a new pipeline composed of facial scanning, interactive wrinkle modeling, and mold printing stages to easily and efficiently fabricate silicone masks for old-age makeups without the use of plaster and clay. An intuitive sketch interface based on a normal map is proposed for the creation of wrinkles in real time, even with a high-resolution face model. Then the geometry of the final wrinkles is reconstructed using a depth map and the negative mold of the wrinkled face is printed. We also show that the presented pipeline can fabricate a silicone mask more conveniently than the traditional one that consists of pouring silicone into the prepared negative mold and then overlapping the mold with the original positive one.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.4 s.310
• /
• pp.58-66
• /
• 2006

In this paper, we apply DCM(Dilation of Color and Motion information) mask and Active Contour Models(Snakes) to extract facial outline in moving pictures with complex background. First, we propose DCM mask which is made by applying morphology dilation and AND operation to combine facial color and motion information, and use this mask to detect facial region without complex background and to remove noise in image energy. Also, initial curves are automatically set according to rotational degree estimated with geometric ratio of facial elements to overcome the demerit of Active Contour Models which is sensitive to initial curves. And edge intensity and brightness are both used as image energy of snakes to extract contour at parts with weak edges. For experiments, we acquired total 480 frames with various head-poses of sixteen persons with both eyes shown by taking pictures in inner space and also by capturing broadcasting images. As a result, it showed that more elaborate facial contour is extracted at average processing time of 0.28 seconds when using interpolated initial curves according to facial rotation degree and using combined image energy of edge intensity and brightness.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.128-139
• /
• 2005

Moving object boundary is very important for moving object segmentation. But the moving object boundary shows broken boundary We invent a novel space-oriented boundary linking algorithm to link the broken boundary The boundary linking algorithm forms a quadrant around the terminating pixel in the broken boundary and searches forward other terminating pixel to link within a radius. The boundary linking algorithm guarantees shortest distance linking. We also register the background from image sequence. We construct two object masks, one from the result of boundary linking and the other from the registered background, and use these two complementary object masks together for moving object segmentation. We also suppress the moving cast shadow using Roberts gradient operator. The major advantages of the proposed algorithms are more accurate moving object segmentation and the segmentation of the object which has holes in its region using these two object masks. We experiment the algorithms using the standard MPEG-4 test sequences and real video sequence. The proposed algorithms are very efficient and can process QCIF image more than 48 fps and CIF image more than 19 fps using a 2.0GHz Pentium-4 computer.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.493-496
• /
• 2010

This paper proposes an effective hardware scheme for thinning stage processing of a fingerprint identification algorithm based on minutiae with 40% cycle occupation of 32-bit RISC microprocessor. The thinning step is needed to be processed by hardware block, because it is performed repeatedly by processing the same operation using an image window masking method. It can reduce the burden of the system and improve speed. The hardware is implemented by HDL and simulated. The result is compared with a conventional one.

• The KIPS Transactions:PartB
• /
• v.8B no.2
• /
• pp.189-194
• /
• 2001

본 논문에서는 개인 식별을 위하여 복수 해상도 구조를 제시하였고 이 방법으로 구순문 인식을 구현하였다. 구순문 인식은 지문, 음성 패턴, 홍채 패턴과 얼굴 인식과 같은 신체적 특징에 비하여 상대적으로 연구가 많이 이루어지지 않은 신체적 특징이다. 구순문은 CCD 카메라를 이용할 경우 홍채나 얼굴 패턴 같은 다른 특징 요소와 연결하여 인식 시스템을 구축할 수 있는 장점을 가지고 있다. 구순문 인식을 위해 pattern kernels를 이용한 새로운 방법을 제시하였다. Pattern kernels는 여러 개의 local lip print mask들로 구성된 함수이며, lip print의 정보를 디지털 데이터로 전환시켜 준다. 복수 해상도를 가지는 인식 시스템은 단일 해상도의 시스템보다 더욱 신뢰적이며 인식률도 높다.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.21 no.1
• /
• pp.51-60
• /
• 2013

In this paper, to control the existing headlamp control system using steering wheel angle more efficiently and more actively, image processing algorithm which improved the detection rate of lane at night based on camera was suggested. And to recognize road lane more clearly in the conditions of low illumination, new algorithms were developed in the aspects of improving brightness, extracting clear lane edge and using the characteristics of lane. Through this research, it turned out that lane detection ability by using the normalized stretching, angular mask and expected-area scan have good performance in the night compare to existing algorithms.

• Annual Conference of KIPS
• /
• 2003.05a
• /
• pp.587-590
• /
• 2003

본 논문에서는 웨이블릿 변환(wavelet transform)을 이용하여 저 비트율로 압축한 영상을 복원하였을 때 나타나는 화질열화를 개선하는 방법을 제안하였다. 웨이블릿 변환을 이용하여 정지영상을 압축하는 방법에서는 에지부근에 링잉현상(ringing artifacts)이 나타나게 되었다. 이는 강한 에지성분이 있는 곳이므로 캐니 마스크(Canny mask)를 적용하여 강한 에지부근을 찾아낸 후 그 주변을 탐색하여 평탄한 영역(flat region)과 텍스쳐 영역(texture region)을 구분하여 각각에 맞는 필터를 적용하게 된다. 실험결과, 링잉현상이 나타나는 저비트율 압축 영상에서 제안된 방법의 PSNR 값은 0.05db정도 낮아졌지만 인간 시각의 주관적 관점에서 볼 때 평탄한 영역에서의 링잉현상이 보다 개선된 화질을 보였다.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.521-523
• /
• 2018

본 논문은 보이스피싱 발생 후의 대처 방안이 아닌, 범죄 행위 자체의 예방을 목적으로 하는 신원 허가 후의 자동인출기 시스템을 제안한다. 범죄예방 현금인출기(ATM)의 작동과정은 크게 두 가지이다. 첫째, YOLO Detection System을 이용하여 학습된 데이터에 기반하여, 사용자의 얼굴에서 선글라스와 마스크를 검출한다. 둘째, 미리 학습된 범죄자 모델 데이터에 앞서 사용자의 신원을 조회하고 ATM의 사용허가를 내준다. 혹은 주요지명 피의자일 경우, 경찰에 실시간 안내를 주어 범죄 수사를 용이하게 한다.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.224-229
• /
• 2003

In this paper, an effective skeleton method is proposed in order to obtain an enhanced digital image of skeleton line. The edge-detection method is applied in the preprocessing stage and after that, the modified Parallel method is applied to obtain the improved image of skeleton line. The existing parallel methods are Zhang, Lu and Wang, and Paul methods. Firstly, a parallel process method Is applied, and the proposed method is applied that the original is compared with the four neighbor pixels and four corner pixels of mask. In conclusion, the proposed method shows an improved connectivity and quality of skeleton line.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.305-307
• /
• 2009

본 논문에서는 기존의 퍼지 논리를 이용한 필터링 알고리즘의 문제점을 개선하는 동시에 컬러 영상에 적용할 수 있는 퍼지 필터 알고리즘을 제안한다. 제시된 퍼지 필터 알고리즘은 영상의 RGB 컬러 정보를 각각의 R, G, B 채널 영상으로 분리하고, 각 채널 영상에서 마스크가 위치한 기준 픽셀의 잡음 가능성 정도를 퍼지 논리에 적용하여 판단한다. 잡음 정도에 따라서 출력 영상의 화소값을 평균값 또는 중간값으로 결정한다. 제안된 방법을 잡음이 존재하는 칼라 영상에 적용한 결과, 단색 정보를 기준으로 처리하는 기존의 퍼지 필터 방법에 비해서 효과적인 것을 확인하였다.