• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.101-106
• /
• 2023

With the recent surge in YouTube usage, there has been a proliferation of user-generated videos where individuals evaluate cosmetics. Consequently, many companies are increasingly utilizing evaluation videos for their product marketing and market research. However, a notable drawback is the manual classification of these product review videos incurring significant costs and time. Therefore, this paper proposes a deep learning-based cosmetics search algorithm to automate this task. The algorithm consists of two networks: One for detecting candidates in images using shape features such as circles, rectangles, etc and Another for filtering and categorizing these candidates. The reason for choosing a Two-Stage architecture over One-Stage is that, in videos containing background scenes, it is more robust to first detect cosmetic candidates before classifying them as specific objects. Although Two-Stage structures are generally known to outperform One-Stage structures in terms of model architecture, this study opts for Two-Stage to address issues related to the acquisition of training and validation data that arise when using One-Stage. Acquiring data for the algorithm that detects cosmetic candidates based on shape and the algorithm that classifies candidates into specific objects is cost-effective, ensuring the overall robustness of the algorithm.

• Proceedings of the KIEE Conference
• /
• 2005.11b
• /
• pp.283-285
• /
• 2005

This paper presents a new two-terminal numerical algorithm for fault location estimation and for faults recognition using the synchronized phasor in time-domain. The proposed algorithm is also based on the synchronized voltage and current phasor measured from the PMUs(Phasor Measurement Units) installed at both ends of the transmission lines. Also the arc voltage wave shape is modeled numerically on the basis of a great number of arc voltage records obtained by transient recorder. From the calculated arc voltage amplitude it can make a decision whether the fault is permanent or transient. In this paper the algorithm is given and estimated using DFT(Discrete Fourier Transform) and the LES(Least Error Squares Method). The algorithm uses a very short data window and enables fast fault detection and classification for real-time transmission line protection. To test the validity of the proposed algorithm, the Electro-Magnetic Transient Program(EMTP/ATP) and MATLAB is used.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.797-803
• /
• 2014

In this paper, 3D face recognition system is designed by using polynomial based on RBFNNs. In case of 2D face recognition, the recognition performance reduced by the external environmental factors such as illumination and facial pose. In order to compensate for these shortcomings of 2D face recognition, 3D face recognition. In the preprocessing part, according to the change of each position angle the obtained 3D face image shapes are changed into front image shapes through pose compensation. the depth data of face image shape by using Multiple Point Signature is extracted. Overall face depth information is obtained by using two or more reference points. The direct use of the extracted data an high-dimensional data leads to the deterioration of learning speed as well as recognition performance. We exploit principle component analysis(PCA) algorithm to conduct the dimension reduction of high-dimensional data. Parameter optimization is carried out with the aid of PSO for effective training and recognition. The proposed pattern classifier is experimented with and evaluated by using dataset obtained in IC & CI Lab.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1044-1049
• /
• 2006

얼굴 추적은 Vision base HCI의 핵심인 얼굴인식, 표정인식 그리고 Gesture recognition등의 다른 여러 기술을 지원하는 중요한 기술이다. 이런 얼굴 추적기술에는 영상(Image)의 Color또는 Contour등의 불변하는 특징들을 사용 하거나 템플릿(template)또는 형태(appearance)를 사용하는 방법 등이 있는데 이런 방법들은 조명환경이나 주위 배경등의 외부 환경에 민감하게 반응함으로 해서 다양한 환경에 사용할 수 없을 뿐더러 얼굴영상만을 정확하게 추출하기도 쉽지 않은 실정이다. 이에 본 논문에서는 deformable한 model을 사용하여 model과 유사한 shape과 appearance를 찾아 내는 AAM(Active Appearance Model)을 사용하는 얼굴 추적 시스템을 제안하고자 한다. 제안된 시스템에는 기존의 Combined AAM이 아닌 Independent AAM을 사용하였고 또한 Fitting Algorithm에 Inverse Compositional Image Alignment를 사용하여 Fitting 속도를 향상 시켰다. AAM Model을 만들기 위한 Train set은 150장의 4가지 형태에 얼굴을 담고 있는 Gray-scale 영상을 사용 하였다. Shape Model은 각 영상마다 직접 표기한 47개의 Vertex를 Trianglize함으로서 생성되는 71개의 Triangles을 하나의 Mesh로 구성하여 생성 하였고, Appearance Model은 Shape 안쪽의 모든 픽셀을 사용해서 생성하였다. 시스템의 성능 평가는 Fitting후 Shape 좌표의 정확도를 측정 함으로서 평가 하였다.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1187-1199
• /
• 2017

In recent years, research about Natural User Interface (NUI) has become focused because NUI system can give natural feelings for users in virtual reality. Most important thing in NUI system is how to communicate with the computer system. There are many things to interact with users such as speech, hand gestures, body actions. Among them, hand gesture is suitable for the purpose of NUI because people often use a relatively high frequency in daily life and hand gesture have meaning only by itself. This hand gestures called multi-cultural hand gesture and we proposed the method to recognize this kind of hand gestures. Proposed method is composed of Histogram of Oriented Gradients (HOG) used for hand shape recognition and Histogram of Oriented Displacements (HOD) used for hand center point trajectory recognition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.5
• /
• pp.147-159
• /
• 2002

This paper proposes a method to recognize the noisiness of road images connected with the extraction of lane-related information in order to prevent the usage of erroneous information. The proposed method uses a fuzzy neural network(FNN) with the back-Propagation loaming algorithm. The U decides road images good or bad with respect to visibility of lane marks on road images. Most input parameters to the FNN are extracted from an edge distribution function(EDF), a function of edge histogram constructed by edge phase and norm. The shape of the EDF is deeply correlated to the visibility of lane marks of road image. Experimental results obtained by simulations with real images taken by various lighting and weather conditions show that the proposed method was quite successful, providing decision-making of noisiness with about 99%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.8B
• /
• pp.1500-1505
• /
• 1999

In this paper, we presented the stereo algorithm for 3-D object recognition. In order to solve the problem for matching time in existed methods, we proposed the method which used the moving direction vector. On the other hand, after we extracted the moving vectors by moving direction of objects, rotated object was matched on axis of it. Using the Hough transform, we obtained the 2-D synthesed image as reference images corresponding to the rate of moving, and then compared with the unknown input images.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.05a
• /
• pp.345-346
• /
• 2023

As the shape and size of detectable objects diversifying recognition and segmentation algorithms have been developed to acquire accurate shape information. Although a high density of data captured by the repetition of scanning improves the accuracy of algorithms the high dense data decreases the efficiency due to its large size. This paper proposes standardization algorithms using the feature of structural members on indoor point cloud data to improve the process. First of all we determine the reduction rate of the density based on the features of the target objects then the data reduction algorithm compresses the data based on the reduction rate. Second the data arrangement algorithm rotates the data until the normal vector of data is aligned along the coordinate axis to allow the following algorithms to operate properly. Final the data arrangement algorithm separates the rotated data into their leaning axis. This allows reverse engineering of indoor point clouds to obtain the efficiency and accuracy of refinement processes.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.608-616
• /
• 2001

This paper proposes a face recognition technique that effectively combines fixed graph matching (FGM) and Fisherface algorithm. EGM as one of dynamic link architecture uses not only face-shape but also the gray information of image, and Fisherface algorithm as a class specific method is robust about variations such as lighting direction and facial expression. In the proposed face recognition adopting the above two methods, linear projection per node of an image graph reduces dimensionality of labeled graph vector and provides a feature space to be used effectively for the classification. In comparison with a conventional EGM, the proposed approach could obtain satisfactory results in the perspectives of recognition speeds. Especially, we could get higher average recognition rate of 90.1% than the conventional methods by hold-out method for the experiments with the Yale Face Databases and Olivetti Research Laboratory (ORL) Databases.