• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.275-276
• /
• 2007

In this paper, we propose an efficient illumination preprocessing algorithm for face recognition. One of the best known illumination preprocessing method, based on anisotropic smoothing, enhances the edge information, but instead deteriorates the contrast of the original image. Our proposed method reduces the deterioration of the contrast while enhancing the edge information, and thus the preprocessed image does not lose features like Gabor features of the original images much.. The effectiveness of the proposed illumination preprocessing method is verified through experiments of face recognition.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.1000-1012
• /
• 2000

There are many factors for face recognition. Two of those are orientation and brightness of illumination. In early studies of face recognition, with fixing these factors to good conditions th goal of research was focused on improving recognition rate itself. But they are very important factors to be solved for implementing face recognition system. In this paper, two methods wer proposed to minimize the influence of illumination. One is the local difference filter to reduce the influence fo variation of illumination. The other is weight function considering the horizontal difference of intensity. Applying tow proposed methods, the resultant recognition rate revealed 86.5% for 275 test images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.583-586
• /
• 2003

보안이 점점 큰 의미를 가지는 요즘, 생체정보를 개인 신분 확인수단으로 이용하려는 연구가 많이 이루어지고 있다 생체정보를 이용한 분야로는 얼굴 인식, 지문 인식, 정맥 인식, 홍채 인식 등이 있는데 그 중에서도 홍채는 패턴의 불변성과 개인의 정보로 이용될 수 있을 정도로 다양한 패턴 형태를 이루고 있다. 이러한 홍채를 이용하여 신분을 인식하기 위해서는 불필요한 영역은 배제하고 인식을 위한 특징만을 가지고 있는 영역을 정확히 찾는 것이 중요하다고 하겠다. 또한 인식 시간의 단축을 위해서 특징 데이터의 크기를 줄이기 위한 방법도 고려되어야 한다. 이 두 가지 문제를 해결하기 위하여 본 논문에서는 홍채의 특징이 가장 많이 분포되어 있는 영역을 찾기 위한 전처리 기법과 인식을 위한 신경망에서 인식시간을 단축하면서 인식률을 높일 수 있는 최적의 신경망 구조를 찾아내는 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1101-1104
• /
• 2019

키넥트는 RGBD 카메라로 인체의 뼈대와 관절을 3D 공간에서 스켈레톤 데이터수집을 가능하게 해주었다. 스켈레톤 데이터를 활용한 행동 분류는 RNN, CNN 등 다양한 인공 신경망으로 접근하고 있다. 본 연구는 키넥트를 이용해서 Skeleton Joints를 수집하고, DNN 기반 스켈레톤 모델링 학습으로 행동을 분류한다. Skeleton Joints Processing 과정은 키넥트의 Depth Map 기반의 Skeleton Tracker로 25가지 Skeleton Joints 좌표를 얻고, 학습을 위한 전처리 과정으로 각 좌표를 상대좌표로 변경하고 데이터 수를 제한하며, Joint가 트래킹 되지 않은 부분에 대한 예외 처리를 수행한다. 스켈레톤 모델링 학습 과정에선 3계층의 DNN 신경망을 구축하고, softmax_cross_entropy 함수로 Skeleton Joints를 집는 모션, 내려놓는 모션, 팔짱 낀 모션, 얼굴을 가까이 가져가는 모션 해서 4가지 행동으로 분류한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.581-587
• /
• 2005

This paper presents a hybrid face recognition method of both the first moment of image and the independent component analysis(ICA) of fixed point(FP) algorithm based on Newton method. First moment is a method for finding centroid of image, which is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. FP-ICA is also applied to find a set of independent basis images for the faces, which is a set of statistically independent facial features. The proposed method has been applied to the problem for recognizing the 48 face images(12 persons o 4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed method has a superior recognition performances(speed, rate) than conventional FP-ICA without preprocessing. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• Journal of Korea Multimedia Society
• /
• v.14 no.4
• /
• pp.494-503
• /
• 2011

In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

• Journal of Digital Contents Society
• /
• v.19 no.3
• /
• pp.435-443
• /
• 2018

Recently, with the explosive development of computing power, various methods such as RNN and CNN have been proposed under the name of Deep Learning, which solve many problems of Computer Vision have. The Generative Adversarial Network, released in 2014, showed that the problem of computer vision can be sufficiently solved in unsupervised learning, and the generation domain can also be studied using learned generators. GAN is being developed in various forms in combination with various models. Machine learning has difficulty in collecting data. If it is too large, it is difficult to refine the effective data set by removing the noise. If it is too small, the small difference becomes too big noise, and learning is not easy. In this paper, we apply a deep CNN model for extracting facial region in image frame to GAN model as a preprocessing filter, and propose a method to produce composite images of various facial expressions by stably learning with limited collection data of two persons.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.6
• /
• pp.604-608
• /
• 2008

The TFT-LCD image allows non-uniform illumination variation and that is one of main difficulties of finding defect region. The SQI (self quotient image) has the HPF (high pass filter) shape and is used to reduce low frequency-lightness component. In this paper, we proposed the TFT-LCD defect-enhancement algorithm using characteristics of the SQI, that is the SQI has low-frequency flattening effect and maintains local variation. The proposed method has superior flattening effect and defect-enhancement effect compared with previous the TFT-LCD image preprocessing.

• 전자공학회논문지 IE
• /
• v.45 no.4
• /
• pp.60-67
• /
• 2008

Skin color is a very important information for an automatic face recognition. In this paper, we proposed a skin region extraction method using color information and skin color model. We use the adaptive lighting compensation technique for improved performance of skin region extraction. Also, using an preprocessing filter, normally large areas of easily distinct non skin pixels, are eliminated from further processing. And we use the modified ST color space, where undesired effects are reduced and the skin color distribution fits better than others color space. Experimental results show that the proposed method has better performance than the conventional methods, and reduces processing time by $35{\sim}40%$ on average.