• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.308-318
• /
• 2004

A subject to recognize the damaged facial image is becoming an important issue in commercialization of automatic face recognition. The method to recognize a face on a damaged image is divided into two types. The one is to recognize remainders after removing the damaged information and the other is to recognize a total face after recovering the damaged information. On this paper, we present the reconstruction method by analyzing the main materials after extracting the damaged region through Kohonen network. The suggested algorithm in this paper estimates feature vectors of the damaged region using eigen-faces in PCA and then reconstructs the damaged image. This allows also the reconstruction under the untrained images. Through testing the artificial images where the eye and the mouth which have many effects to face recognition are damaged, the recognition rate of the proposed results showed similar results with the method which used Kohonen network, and improved about 11.8% more than symmetrical property method. Also, in case of the untrained image, our results improved about 14% more than that of the Kohonen method and about 7% more than that of the symmetrical property method.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.34-43
• /
• 2008

This paper presents a system for recognizing sunglasses and a mask of an ATM (Automatic Teller Machine) user. The proposed system extracts firstly facial contour, then from this extraction results it estimates the regions of eyes and mouth. Finally, it recognizes sunglasses and a mouth using Histogram Indexing based on those regions. We adopt a face shape model to be able to extract facial contour and to estimate the regions of eyes and mouth when those regions are occluded by sunglasses and a mask. To improve the fitting accuracy of the shame model, we adopt 2-step face detection method and conduct fitting several times by varying the initial position of the model instance. To achieve a good performance of the face detection method based on a background model, we enable the system to automatically update the background model. In experiment, we present some experiments on setting parameters of the system with images taken from in our laboratory, and demonstrate the results of recognizing sunglasses and a mask.

• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.213-223
• /
• 2004

In this paper, we propose a new face detection method for real-time applications. It is based on the template-matching and appearance-based method. At first, we apply Min-max normalization with histogram equalization to the input image according to the variation of intensity. By applying the PCA transform to both the input image and template, PC components are obtained and they are applied to the LDA transform. Then, we estimate the distances between the input image and template, and we select one region which has the smallest distance. SVM is used for final decision whether the candidate face region is a real face or not. Since we detect a face region not the full region but within the $\pm$12 search window, our method shows a good speed and detection rate. Through the experiments with 6 category input videos, our algorithm shows the better performance than the existing methods that use only the PCA transform. and the PCA and LDA transform.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.19-27
• /
• 2021

In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.155-167
• /
• 2007

There are four types of human beings according to the Sasang Typology, Oriental medical doctors frequently prescribe healthcare information and treatment depending on one's type, The feature ratios (Table 1) on the human face are the most important criterions to decide which type a patient is. In this paper, we proposed a system to extract these feature ratios from the people's side face, There are two challenges in acquiring the feature ratio: one that selecting representative features; the other, that detecting region of interest from human profile facial image effectively and calculating the feature ratio accurately. In our system, an adaptive color model is used to separate human side face from background, and the method based on geometrical model is designed for region of interest detection. Then we present the error analysis caused by image variation in terms of image size and head pose, To verify the efficiency of the system proposed in this paper, several experiments are conducted using about 173 korean's left side facial photographs. Experiment results shows that the accuracy of our system is increased 17,99% after we combine the front face features with the side face features, instead of using the front face features only.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.557-560
• /
• 2006

최근 들어 정보통신 분야의 기술이 급격히 발전함에 따라 컴퓨터 사용의 증가와 임베디드 시스템 및 사회 각 분야에서 보안에 대한 의식이 점점 높아져 가고 있다. 각 분야에서 신체 정보를 이용한 연구들이 활발히 이루어지고 있는데 본 논문에서는 USB 캠을 이용한 실시간 얼굴 인식 방법에 대해서 제안한다. 카메라를 이용하여 얼굴을 인식하는 방법은 현재까지 여러 가지 방법들이 제시되어 왔지만 일반 pc에서 쓰는 USB 캠을 사용하여 제약 조건 없고 안정적인 인식 방법은 아직까지 나와 있지 않다. 얼굴영역을 주성분 변수로 변환하여 영상의 명암, 얼굴위치, 얼굴의 영역을 추출할 수 있는 기존의 시스템들이 많이 연구되어 왔는데 본 논문에서 제안된 방법에서는 일상생활에서 흔히 쓰는 USB 캠을 사용하여 기존의 CCTV와 같은 고가의 하드웨어를 대체하며 보다 효율적인 성능을 위하여 얼굴을 식별하기 위해 LVQ, FCMA, RBF 알고리즘을 적용한 시스템을 설계한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.156-161
• /
• 2007

본 논문에서는 실사 영상을 사용하여 3차원 아바타의 얼굴 텍스쳐를 생성하는 기법을 제시한다. 먼저 UVW 맵을 기준으로 실사영상에서의 해당 영역을 수동으로 지정해 준다. 그 다음 지정된 영상 영역들을 사용하여 UVW 맵에 해당하는 텍스쳐 영상을 생성한다. 제안된 텍스쳐 생성 기법은 포토샵 등을 사용한 기존의 일반적인 방법에 비해서 수작업 시간을 단축할 수 있으며 실사 영상의 사실감을 높여 준다. 기존의 텍스쳐 생성 절차들은 3차원 모델의 메쉬 구조에 영향을 주었으나, 제안된 방법은 3차원 모델의 메쉬구조를 수정하지 않고도 원하는 형태의 텍스쳐를 생성할 수 있는 장점이 있다. 실제 사람의 모습을 여러각도에서 촬영하여 얻은 영상을 사용하여 주어진 UVW 맵에 적합한 얼굴 텍스쳐를 생성하였다. 생성된 텍스쳐를 사용하여 3차원 아바타를 렌더링한 결과 아바타 얼굴의 사실감이 증가되었음을 알 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1408-1411
• /
• 2013

객체의 인식과 추적은 컴퓨터 비전 및 영상처리 분야에서 연구가 활발히 진행되고 있다. 특히 얼굴을 인식하고 추적하는 기술은 많은 분야에서 응용될 수 있다. 기존에 연구되어 온 기준 프레임과 관찰 프레임 사이의 차를 이용하여 객체를 인식하고 추적하는 방식은 관찰 대상이 다수인 경우 동일성을 확보하기에는 어려움이 많다. 따라서 본 논문에서는 각각의 프레임에서 빠르게 얼굴 영역을 인식하고, 독립적으로 인지된 얼굴들의 동일성을 연결하는 방법을 제시한다. 제안된 방법의 유용성은 실험으로 검증하였으며, 어느 정도 의미 있는 결과를 관찰할 수 있었다.

• Journal of KIISE:Software and Applications
• /
• v.34 no.10
• /
• pp.945-952
• /
• 2007

The face detection is a necessary first-step in the face recognition systems, with the purpose of localizing and extracting face regions from input images. But it is not a simple problem, because faces have many variations such as scale, rotation and lighting condition. In this paper, we propose a novel method to detect not only frontal faces but also partial rotated faces in still images. Firstly, we produce the eye candidates in the sub-regions of an input image to detect rotated faces. Secondly, the eye candidates are used to measure the angles of rotated faces. Thirdly, we are able to derotate the rotated face then put it to Bayesian classifier. We make an experiment with rotated multiracial face and show the good results in this paper.

• Korean Journal of Cognitive Science
• /
• v.29 no.1
• /
• pp.39-59
• /
• 2018

To elucidate the effect of working memory (WM) load on negative facial emotion processing, we examined ERP components (P1 and N170) elicited by fearful and neutral expressions each of which was presented during 0-back (low-WM load) or 2-back (high-WM load) tasks. During N-back tasks, visual objects were presented one by one as targets and each of facial expressions was presented as a passively observed stimulus during intervals between targets. Behavioral results showed more accurate and fast responses at low-WM load condition compared to high-WM load condition. Analysis of mean amplitudes of P1 on the occipital region showed significant WM load effect (high-WM load > low-WM load) but showed nonsignificant facial emotion effect. Analysis of mean amplitudes of N170 on the posterior occipito-temporal region showed significant overall facial emotion effect (fearful > neutral), but, in detail, significant facial emotion effect was observed only at low-WM load condition on the left hemisphere, but was observed at high-WM load condition as well as low-WM load condition on the right hemisphere. To summarize, facial emotion effect observed by N170 amplitudes was modulated by WM load only on the left hemisphere. These results show that early emotional processing of negative facial expression could be eliminated or reduced by high load of WM on the left hemisphere, but could not be eliminated by high load on the right hemisphere, and suggest right hemispheric lateralization of negative facial emotion processing.