• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. 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 pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. 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 face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.1
• /
• pp.139-148
• /
• 2015

In this paper, a new algorithm is proposed for detecting the product number of each thick plate and extracting each character of the product number from a image which contains several thick plates. In general, a image of thick plates contains several steal plates. To obtain the product number from the image, we first need to separate each plate. To do so, we use the line edges of thick plates and a clustering algorithm. After separating each plate, background parts are eliminated from the image of each plate. Background parts of an individual thick plate image consist of the dark part of steel and the white part of paint which is used for printing the product number. We propose a two-tiered method where dark background parts are first eliminated and then white parts are eliminated. Finally, each character is extracted from the product number image using the characteristics of product number. The results of the experiments on the various steal plates images emphasize that the proposed algorithm detects each thick plate and extracts the product number from a image effectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3534-3549
• /
• 2020

The traditional method of smoke image recognition has low accuracy. For this reason, we proposed an algorithm based on the good group of IMFOA which is GMFOA to optimize the parameters of SVM. Firstly, we divide the motion region by combining the three-frame difference algorithm and the ViBe algorithm. Then, we divide it into several parts and extract the histogram of oriented gradient and volume local binary patterns of each part. Finally, we use the GMFOA to optimize the parameters of SVM and multiple kernel learning algorithms to Classify smoke images. The experimental results show that the classification ability of our method is better than other methods, and it can better adapt to the complex environmental conditions.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.466-469
• /
• 2002

Burr is a projected part of finished workpiece. It is unavoidable and undesirable by-product of most metal cutting or shearing process. Also, it must be removed to improve the fit of machined parts, safety of workers, and the effectiveness of finishing operation. But deburring process is one of manufacturing processes that have net been successfully automated, so deburring automation is strongly needed. This paper focused on developing a basic algorithm to find edge of workpiece and match two different image data for deburring automation which includes automatic recognition of parts, generation of deburring tool paths and edge/corner finding ability by analyzing the DXF drawing file which contains information of part geometry. As an algorithm for corner finding, SUSAN method was chosen. It makes good performance in finding edge and corner in suitable time. And this paper suggested a simple algorithm to find matching point between CCD image and drawing file.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1836-1839
• /
• 1997

This paper presents machine vision technique with a camera modeling that accounts for major sources of camera distortion, namely, radial, decentering, and thin prism distortion. Radial distortion causes an inward or outward displacement of a given image point from its ideal location. Actual optical systems are subject to various degrees of decentering, that is, the optical centers of lens elements are not strictly collinear. It is our purpose to develop the vision system for the pattern recognition and the automatic test of parts and to apply the line of manufacturing.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.115-118
• /
• 2003

This paper describes a system of detecting multi-views faces and estimating their face poses in an omni-directional camera environment for non-intrusive iris recognition. The paper is divided into two parts; First, moving region is identified by using difference-image information. Then this region is analyzed with face-color information to find the face candidate region. Second part is applying PCA (Principal Component Analysis) to detect multi-view faces, to estimate face pose.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 2006.06a
• /
• pp.251-257
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization)and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architecture II, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortion

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.583-586
• /
• 1999

In this paper, the wavelet transform is performed in the input 256$\times$256 color image and decomposes a image into low-pass and high-pass components. Since the high-pass band contains the components of three directions, edges are detected by combining three parts. After finding the position of face using the histogram of the edge component, a face region in low-pass band is cut off. Since RGB color image is sensitively affected by luminances, the image of low pass component is normalized, and a facial region is detected using face color informations. As the wavelet transform decomposes the detected face region into three layer, the dimension of input image is reduced. In this paper, we use the 3000 images of 10 persons, and KL transform is applied in order to classify face vectors effectively. FCM(Fuzzy C-Means) algorithm classifies face vectors with similar features into the same cluster. In this case, the number of cluster is equal to that of person, and the mean vector of each cluster is used as a codebook. We verify the system performance of the proposed algorithm by the experiments. The recognition rates of learning images and testing image is computed using correlation coefficient and Euclidean distance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• Journal of Fashion Business
• /
• v.8 no.2
• /
• pp.69-90
• /
• 2004

The purpose of this study is to find the recognition of Korean image fashion design by U.K fashion specialists. U.K is one of the important countries in design field including fashion design since 1960. For this purpose, literature research and focus individual interview research were carried. First, through the researches precedent, it was found that a national image is related with it's design industry and what is Korean image fashion design, were studied. Second, for individual interviews to 13 U.K fashion specialists, who are teaching and researching in University that has postgraduate course over M.A and had industrial experiences from 7years to 22years, were progressed using open questions and visual image stimulus. The open questions were consisted with four parts : personal educational and industrial background, recognitions about oriental fashion, recognitions about Korean image and Korean fashion design before seeing the visual stimulus, recognition about Korean image fashion design and the characteristics of Korean after seeing the visual stimulus. The results are as follows; First, the 12 U.K specialists have recognized 'oriental fashion' is one of important fashion trends now a days. Japan and Japanese designers are recognized as a represented nation and designer in oriental fashion by them. Two of the specialists referred to need changing the term 'oriental' because the term has been used in the sights of western from colonial age and Japanese is not included the oriental any more. Secondly, 11 interviews have recognized nothing about the Korean national image some of them has negative image due to political situation in Korean Peninsula. However 2 interviews who had been Korea before has positive image. In the questions about Korean fashion and Korean fashion designers, 10 of 13 interviews have nothing and negative recognitions. So it was founded that Korean fashion design was recognized as a lower level by U. K. fashion specialists. Thirdly, in the questions about Korean fashion image and the design characteristics of Korean fashion after seeing the visual stimulus, the response was represented two directions. One is about over decorative image through ethnic design and the other is about simple image differ from Japanese. The 13 interviews felt the Korean Image fashion design such like traditional, decorative, opulent, flat cutting, fresh proportion, loose, layering, natural, simplicity, complicate, adventure, easy, stylish, soft, feminine, young image, adult sexy image. The images were analyzed five image groups : adult sexy image, adult ethnic image, natural image, young avant-garde image, young simple casual image. No one preferred the adult sexy image, adult ethnic image and natural image. However 10 interviews preferred young avant-garde group and 13 interviews preferred the young simple casual image. So this group can be understanded and useful informed as one of competitive power in global fashion industry.