• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권3호
• /
• pp.322-326
• /
• 2004

This paper describes a new iris recognition method based on a shift-invariant wavelet sub-images. For the feature representation, we first preprocess an iris image for the compensation of the variation of the iris and for the easy implementation of the wavelet transform. Then, we decompose the preprocessed iris image into multiple subband images using a shift-invariant wavelet transform. For feature representation, we select a set of subband images, which have rich information for the classification of various iris patterns and robust to noises. In order to reduce the size of the feature vector, we quantize. each pixel of subband images using the Lloyd-Max quantization method Each feature element is represented by one of quantization levels, and a set of these feature element is the feature vector. When the quantization is very coarse, the quantized level does not have much information about the image pixel value. Therefore, we define a new similarity measure based on mutual information between two features. With this similarity measure, the size of the feature vector can be reduced without much degradation of performance. Experimentally, we show that the proposed method produced superb performance in iris recognition.

• 한국안전학회지
• /
• 제26권5호
• /
• pp.17-22
• /
• 2011

This study proposes feature extraction method of pattern recognition by evaluation of weld defects in weld zone of titanium. For this purpose, analysis objectives in this study are features of attractor quadrant and fractal dimension. Trajectory changes in the attractor indicated a substantial difference in fractal characteristics resulting from distance shifts such as porosity of weld zone. These differences in characteristics of weld defects enables the evaluation of unique characteristics of defects in the weld zone. In quantitative fractal feature extraction, feature values of 0.87 and 1.00 in the case of part of 0.5 skip distance and 0.72 and 0.93 in the case of part of 1.0 skip distance were proposed on the basis of fractal dimensions. Attractor quadrant point, feature values of 1.322 and 1.172 in the case of ${\phi}1{\times}3mm$ porosity and 2.264 and 307 in the case of ${\phi}3{\times}3mm$ porosity were proposed on the basis of distribution value. The Proposed feature extraction of pattern recognition in this study can be used for safety evaluation of weld zone in titanium.

• Journal of Multimedia Information System
• /
• 제6권2호
• /
• pp.91-98
• /
• 2019

Many researchers have attempted to recognize three-dimensional faces using feature points extracted from two-dimensional facial photographs. However, due to the limit of flat photographs, it is very difficult to recognize faces rotated more than 15 degrees from original feature points extracted from the photographs. As such, it is difficult to create an algorithm to recognize faces in multiple angles. In this paper, it is proposed a new algorithm to recognize three-dimensional face recognition based on feature points extracted from a flat photograph. This method divides into six feature point vector zones on the face. Then, the vector value is compressed and expanded according to the rotation angle of the face to recognize the feature points of the face in a three-dimensional form. For this purpose, the average of the compressibility and the expansion rate of the face data of 100 persons by angle and face zone were obtained, and the face angle was estimated by calculating the distance between the middle of the forehead and the tail of the eye. As a result, very improved recognition performance was obtained at 30 degrees of rotated face angle.

• 전자공학회논문지CI
• /
• 제38권5호
• /
• pp.58-64
• /
• 2001

현재 많은 정보들이 비디오 데이터로 전송 또는 저장되고 있으며 고성능 PC의 보급과 internet과 같은 통신망의 대중화로 이런 비디오 데이터는 급속도로 증가하고 있다. 본 논문에서는 이런 비디오 데이터의 검색을 위하여 비디오 스트립을 분석하여 shot을 찾아내고 이들 중 key frame을 찾는 방법에 대하여 연구하고 이로서 사용자의 질의에 부합하는 비디오를 검색한다. 본 논문에서는 shot 경계 검출을 위해 객체의 움직임에 강인하면서 shot 내에서의 칼라의 변화에 둔감한 새로운 feature를 제안하고, shot frame에서 구한 각 feature들의 통계적 특성을 이용하여 스트립의 특징에 따라 weight를 부가하여 구해진 characterizing value의 시간 변화량을 구한다. 구해진 변화량의 local maxima와 local minima는 비디오 스트림에서 각각 가장 특정적인 frame과 평균적인 frame을 나타낸다. 이 순간의 short frame을 구함으로서 효과적이고 빠른 시간 내에 key frame을 추출한다. 추출되어진 key frame에 대하여 원 영상을 복원한 후, 색인을 위하여 다수의 parameter를 구하고, 사용자가 질의한 영상에 대해서 이들 parameter를 구하여 key frame들과 가장 유사한 대표영상들을 검색한다. 실험결과 일반적인 방법보다 더 나은 결과를 보였고, 높은 검색율을 보였다.

• 한국음향학회지
• /
• 제19권3호
• /
• pp.20-25
• /
• 2000

본 논문에서는 3차원 물체 인식을 위한 표면 분류 및 임계치 선정 방법에 대해 제안 하고자 한다. 3차원 영상 처리는 크게 거리 영상의 획득과 특징 추출 그리고 정합 과정으로 이루어진다. 본 논문에서는 전체 3차원 영상 처리 시스템중 거리 영상을 입력으로 했을 시 형상 특징을 추출하는 방법에 대해 제안하고자 한다. 이를 위해 첫째, 거리 영상의 깊이 변화 부호 값의 분포 특성에 따라 표면을 분류하는 방법을 제안하고자 한다. 또한 평균 곡률과 가우스 곡률을 이용하여 표면을 분류했던 기존 방법을 토대로 그의 문제점이었던 실제 거리 영상에서의 임계치 선정 방법에 대하여 제안하고자 한다. 끝으로 제안한 방법의 유용성을 실험에 의해 입증하고자 한다.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(4)
• /
• pp.81-84
• /
• 2000

In this paper, a new technology for extracting the feature of the speech signal of an isolated word by the analysis on the frequency domain is proposed. This technology can be applied efficiently for the limited speech domain. In order to extract the feature of speech signal, the number of peaks is calculated and the value of the frequency for a peak is used. Then the difference between the maximum peak and the second peak is also considered to identify the meanings among the words in the limited domain. By implementing this process hierarchically, the feature of speech signal can be extracted more quickly.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.162-164
• /
• 2004

This paper proposes a new classification system combining the adaptive feature weighting algorithm using the genetic algorithm and the modified KNN rule. GA is employed to choose the middle value of weights and weights of features for high performance of the system. The modified KNN rule is proposed to estimate the class of test pattern using adaptive feature space. Experiments with the unconstrained handwritten digit database of Concordia University in Canada are conducted to show the performance of the proposed method.

• Journal of Mechanical Science and Technology
• /
• 제16권6호
• /
• pp.762-769
• /
• 2002

This paper presents how effective it is to use many features for improving the speed and accuracy of visual servo systems. Some rank conditions which relate the image Jacobian to the control performance are derived. The focus is to describe that the accuracy of the camera position control in the world coordinate system is increased by utilizing redundant features in this paper. It is also proven that the accuracy is improved by increasing the number of features involved. Effectiveness of the redundant features is evaluated by the smallest singular value of the image Jacobian which is closely related to the accuracy with respect to the world coordinate system. Usefulness of the redundant features is verified by the real time experiments on a Dual-Arm robot manipulator made by Samsung Electronic Co. Ltd..

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권23호
• /
• pp.10539-10542
• /
• 2015

A method to predict the risk of lung cancer is proposed, based on two feature selection algorithms: Fisher and ReliefF, and BP Neural Networks. An appropriate quantity of risk factors was chosen for lung cancer risk prediction. The process featured two steps, firstly choosing the risk factors by combining two feature selection algorithms, then providing the predictive value by neural network. Based on the method framework, an algorithm LCRP (lung cancer risk prediction) is presented, to reduce the amount of risk factors collected in practical applications. The proposed method is suitable for health monitoring and self-testing. Experiments showed it can actually provide satisfactory accuracy under low dimensions of risk factors.