• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.238-245
• /
• 2013

Gesture recognition has been widely one of the research areas for natural user interface. This paper presents a novel gesture recognition method using tree classification and multiclass SVM(Support Vector Machine). In the learning step, 3D trajectory of human gesture obtained by a Kinect sensor is classified into the tree nodes according to their distributions. The gestures are resampled and we obtain the histogram of the chain code from the normalized data. Then multiclass SVM is applied to the classified gestures in the node. The input gesture classified using the constructed tree is recognized with multiclass SVM.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1954-1955
• /
• 2011

본 연구에서는 교육용으로 제작된 NXT 장비에 설치된 Light 센서, Ultrasonic센서, Sound센서를 이용하여 각 거리(10~60cm)에서 5cm 간격으로 각 센서 데이터를 취득하였다. 데이터 취득은 NI(National Instrument)에서 제공하는 LabVIEW Software를 사용하여 각 거리마다 100개의 셈플 데이터를 취득하였다. 취득한 데이터는 제안한 모델의 입력 데이터로 사용하여 실제거리와 모델 출력과의 정확도를 평가 하였다. 본 연구에서 제안한 모델은 지능형 모델 중 퍼지추론 기반의 최적 다항식 RBF 뉴럴네트워크(Radial Basis Function Neural Network; RBFNN)를 설계한다. 제안된 RBFNN은 기존 RBF 뉴럴네트워크를 기반으로 한 구조로, 퍼지추론 메커니즘의 기능적 모듈 동작 특성을 갖도록 정규화 부분을 추가하고, 은닉층과 출력층 사이의 연결가중치를 기존 상수항에서 선형식(first order)으로 확장한 형태이다. 또한 최적의 알고리즘인 PSO(Paticle Swarm Optimization)와 DE(Differential Evolution)을 이용하여 제안된 모델의 파라미터들을 동정하여 성능을 비교, 분석 하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.114-114
• /
• 2022

딥러닝의 학습 및 예측성능을 개선하기 위해서는 딥러닝 기법 내 연산과정의 개선과 함께 학습 및 예측에 사용되는 데이터의 전처리 과정이 중요하다. 본 연구에서는 딥러닝의 성능을 개량하기 위해 제안된 메타휴리스틱 최적화 알고리즘-딥러닝 결합모형과 데이터 전처리 기법을 통해 댐의 수위를 예측하였다. 수위예측을 위해 Multi-Layer Perceptron(MLP), 메타휴리스틱 최적화 알고리즘인 Harmony Search(HS)와 딥러닝을 결합한 MLP using a HS(MLPHS) 및 Exponential Bandwidth Harmony Search with Centralized Global Search(EBHS-CGS)와 딥러닝을 결합한MLP using a EBHS-CGS(MLPEBHS)를 통해 댐의 수위를 예측하였다. 메타휴리스틱 최적화 알고리즘-딥러닝 결합모형의 학습 및 예측성능을 개선하기 위해 학습 및 예측을 위한 자료를 기반으로 데이터 전처리기법을 적용하였다. 적용된 데이터 전처리 기법은 정규화, 수위구간별 사상(Event)분리 및 수위 변동에 대한 자료의 구분이다. 수위예측을 위한 대상유역은 금강유역에 위치한 대청댐으로 선정하였다. 대청댐의 수위예측을 위해 대청댐 상류에 위치하는 수위관측소 3개소를 선정하여 수위자료를 취득하였다. 각 수위관측소에서 취득한 수위자료를 입력자료로 설정하였으며, 대청댐의 수위자료를 출력자료로 설정하여 메타휴리스틱 최적화 알고리즘-딥러닝 모형의 학습을 진행하였다. 각 수위관측소 및 대청댐에서 취득한 수위자료는 2010년부터 2020년까지 총 11년의 일 단위 수위자료이며, 2010년부터 2019년까지의 자료를 학습자료로 사용하였으며, 2020년의 자료를 예측 및 검증자료로 사용하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.165-170
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1312-1317
• /
• 2003

This paper presents an integrated approach to unconstrained face recognition in arbitrary scenes. The front end of the system comprises of a scale and pose tolerant face detector. Scale normalization is achieved through novel combination of a skin color segmentation and log-polar mapping procedure. Principal component analysis is used with the multi-view approach proposed in[10] to handle the pose variations. For a given color input image, the detector encloses a face in a complex scene within a circular boundary and indicates the position of the nose. Next, for recognition, a radial grid mapping centered on the nose yields a feature vector within the circular boundary. As the width of the color segmented region provides an estimated size for the face, the extracted feature vector is scale normalized by the estimated size. The feature vector is input to a trained neural network classifier for face identification. The system was evaluated using a database of 20 person's faces with varying scale and pose obtained on different complex backgrounds. The performance of the face recognizer was also quite good except for sensitivity to small scale face images. The integrated system achieved average recognition rates of 87% to 92%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.4
• /
• pp.235-242
• /
• 2013

In this paper, the system which can translate sign language through motion recognition of Kinect camera system is developed for the communication between hearing-impaired person or language disability, and normal person. The proposed algorithm which can translate sign language is developed by using core function of Kinect, and two ways such as length normalization and elbow normalization are introduced to improve accuracy of translating sign langauge for various sign language users. After that the sign language data is compared by chart in order to know how effective these ways of normalization. The accuracy of this program is demonstrated by entering 10 databases and translating sign languages ranging from simple signs to complex signs. In addition, the reliability of translating sign language is improved by applying this program to people who have various body shapes and fixing measure errors in body shapes.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.2
• /
• pp.12-17
• /
• 2003

This paper proposes content-based image retrieval system with fuzzy ART neural network algorithm. Retrieving large database of image data, the clustering is essential for fast retrieval. However, it is difficult to cluster huge image data pertinently, Because current retrieval methods using similarities have several problems like low accuracy of retrieving and long retrieval time, a solution is necessary to complement these problems. This paper presents a content-based image retrieval system with neural network in order to reinforce abovementioned problems. The retrieval system using fuzzy ART algorithm normalizes color and texture as feature values of input data between 0 and 1, and then it runs after clustering the input data. The implemental result with 300 image data shows retrieval accuracy of approximately 87%.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.127-133
• /
• 2021

In this study, an augmented reality-based make-up tool was built to analyze the user's face shape based on face-type reference model data and to provide virtual makeup by providing face-type makeup. To analyze the face shape, first recognize the face from the image captured by the camera, then extract the features of the face contour area and use them as analysis properties. Next, the feature points of the extracted face contour area are normalized to compare with the contour area characteristics of each face reference model data. Face shape is predicted and analyzed using the distance difference between the feature points of the normalized contour area and the feature points of the each face-type reference model data. In augmented reality-based virtual makeup, in the image input from the camera, the face is recognized in real time to extract the features of each area of the face. Through the face-type analysis process, you can check the results of virtual makeup by providing makeup that matches the analyzed face shape. Through the proposed system, We expect cosmetics consumers to check the makeup design that suits them and have a convenient and impact on their decision to purchase cosmetics. It will also help you create an attractive self-image by applying facial makeup to your virtual self.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.135-138
• /
• 2001

본 논문에서는 3D 레이저 스캐너로 입력된 3차원 얼굴 영상에서 코의 특징 정보를 이용하여 얼굴을 인식하는 알고리즘을 제안하였다. 특히 3차원 영상은 주변의 조명 변화에 크게 영향을 받지 않는 장점이 있다. 이러한 정보를 이용하여, 제안된 알고리즘에서는 얼굴에서 가장 두드러지게 보이는 코의 3차원 정보를 이용하여 인식하는 알고리즘을 제안한다. 먼저 코를 추출한 다음, 회전된 3차원 영상에 대하여 정규화를 실시하고, 등고선을 이용한 영역기반의 방법과 특징기반의 방법을 이온하여 인식을 수행한다. 등고선을 이용한 영역기반은 3차원 얼굴 영상을 코끝의 좌표를 기준 점으로 등고선의 값이 10, 20, 30이 되는 영역을 추출 한 후 데이터 베이스 값들과 비교하여 각각의 차 영역에 대한 무게중심(X, Y), 픽셀 수, 분산을 구하여 순위가 가장 높은 것을 취한다. 특징 기반의 방법으로, 얼굴에 있어서의 실제의 코의 길이, 높이, 너비를 구하여 그 차가 가장 적은 것을 취한다. 위의 2가지 방법을 이용하여 인식을 수행 결과 100%의 인식률을 나타내었다.