Behavior of Certain Wavelets in Classification of Orthopaedic Images of Different Modalities

M. V. Latte,Kumar Swamy.V,B.S.Anami 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.12

Orthopedicians often identify imaging modality visually out of their experience. To be effective, the process needs to be automated. This paper presents a behavior of wavelets in classification of orthopedic imaging modalities using Artificial Neural Network (ANN). In this work, we have considered orthopedic imaging modalities, namely, X-ray, CT and MRI and Bone scan images. Four wavelets, namely Haar, Daubechies, Symlets and Coiflets are used for sub band decomposition and their approximation co-efficients are recorded. Features, namely, mean standard deviation, median, variance and entropy is drawn from the decomposed images. Results are drawn from the performance of these wavelets at five levels of decomposition. Feature reduction is based on the classification accuracies which are analysed using wavelets. The experimental results show that the proposed method achieves satisfactory results with an average accuracy of 98% for four wavelets and for all the modalities considered. The study can be extended to include other modalities in medical field. The work is useful for orthopaedics practitioners.

분할된 웨이블릿들에 GLCM을 적용한 수피분류

이재만(Jae-Man Lee),김동필(Dong-Pil Kim),김선종(Seon-Jong Kim) 한국정보기술학회 2012 Proceedings of KIIT Conference Vol.2012 No.5

본 논문에서는 질감의 특징을 효과적으로 이용하여 수피를 분류하는 시스템을 제안하였다. 특징은 웨이블릿 변환으로 분할된 각 영상에 GLCM질감을 이용하였다. 먼저 그레이 영상에 3-level 웨이블릿 변환 후 분할된 10개의 영역을 각각 GLCM 적용시킨다. GLCM은 질감의 특징을 추출함에 있어서 여러 특징 중 엔트로피(entropy), 에너지(energy), 대조(contrast), 동질성(homogeneity) 4가지 특징을 이용하며 각각의 성능을 실험한 결과 대조를 사용하였을 때의 성능이 가장 효과적임을 확인하였다. 각 분할된 영역마다 한 개의 특징을 사용하므로 모두 10개의 특징이 사용되며 각 패턴은 유클리드 거리에 따라 유사도를 측정하였다. 실험 결과 일반적인 그레이 영상에 적용된 GLCM 보다는 평균 41% 향상 되었고 웨이블릿방법 보다는 20%, 그레이와 바이너리 웨이블릿보다는 4%의 성능이 향상되었다. In this paper, we give an efficient bark classification system by using texture. The features are extracted by GLCM of partial wavelets. We applied 3-level wavelets from the gray bark image. They consists of 10 wavelets to an image. In GLCM, it is used entropy, energy, contrast, homogeneity. We used the Euclidean distance as a measure of the similarity. The experiment results showed the best performance when applying the contrast in the bark classification if only applying a feature of GLCM. And we obtained that the proposed can be improved 41% more than the conventional method, and 20% more than gray-scale wavelets only, and 4% more than applying both the gray and binary wavelets.

Constrained Local Model과 Gabor Wavelets을 이용한 얼굴 인증 방법

박노진(Nojin Park),박충호(Chungho Park),노성혁(Sunghyeok No),곽노윤(Noyoon Kwak) 한국정보기술학회 2018 Proceedings of KIIT Conference Vol.2018 No.6

본 논문은 Constrained Local Model과 Gabor Wavelets을 이용한 얼굴 인증 방법에 관한 것이다. 제안된 방법은 CLM(Constrained Local Models) 기반의 얼굴 특징점 추출을 통해 얼굴의 주요 성분을 추출하는 과정과 이렇게 추출된 특징점을 대상으로 Gabor 웨이블릿 변환을 통해 Gabor 특징 벡터를 생성한 후, Gabor 특징 벡터들 간의 상호 상관도를 이용해 개인을 이증하는 과정으로 구성된다. Probe 얼굴 영상의 조명 상태가 정상 조도에서 저조도로 가변되는 상황에서도 평균 98.72%의 양호한 얼굴 인증률을 제공함을 확인할 수 있었다. 제안된 방법을 온라인 강의 모니터링 시스템, 온라인 심사, 의무 보수 교육 등과 같은 응용 분야에서 적용할 경우 양호한 성능을 제공할 것으로 기대된다. This paper relates to face verification method using constrained local model and Gabor wavelets. The proposed method extracts facial feature points based on Constrained Local Models (CLM), and extracts Gabor feature vectors using Gabor wavelets transform, and then verifies individuals using cross-correlation between Gabor feature vectors. The proposed method provides a good face recognition rate of 98.72% on the average even when the illumination condition of the probe face image changes from normal illumination to low illumination. The proposed method is expected to provide good performance when applied to applications such as online lecture monitoring system, online examination, and mandatory maintenance training.

COMPACTLY SUPPORTED WAVELET AND THE NUMERICAL SOLUTION OF THE VLASOV EQUATION

Benhadid, Yacine 한국전산응용수학회 2007 Journal of applied mathematics & informatics Vol.24 No.1

A new scheme for solving the Vlasov equation using a compactly supported wavelets basis is proposed. We use a numerical method which minimizes the numerical diffusion and conserves a reasonable time computing cost. So we introduce a representation in a compactly supported wavelet of the derivative operator. This method makes easy and simple the computation of the coefficients of the matrix representing the operator. This allows us to solve the two equations which result from the splitting technique of the main Vlasov equation. Some numerical results are exposed using different numbers of wavelets.

Comparative Analysis of Wavelet-Based Scale-Invariant Feature Extraction Using Different Wavelet Bases

Joohyun Lim,Youngouk Kim,Joonki Paik 보안공학연구지원센터(IJSIP) 2009 International Journal of Signal Processing, Image Vol.2 No.4

르장드르 웨이블릿을 이용한 쌍일차 시스템 수치 해석

김범수(Beomsoo Kim) 제어로봇시스템학회 2013 제어·로봇·시스템학회 논문지 Vol.19 No.9

In this paper, an efficient computational method is presented for state space analysis of bilinear systems via Legendre wavelets. The differential matrix equation is converted to a generalized Sylvester matrix equation by using Legendre wavelets as a basis. First, an explicit expression for the inverse of the integral operational matrix of the Legendre wavelets is presented. Then using it, we propose a preorder traversal algorithm to solve the generalized Sylvester matrix equation, which greatly reduces the computation time. Finally the efficiency of the proposed method is discussed using numerical examples.

Vibration analysis of composite pipes using the finite element method with B-spline wavelets

Wasiu A. Oke,Yehia A. Khulief 대한기계학회 2016 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.30 No.2

A finite element formulation using the B-spline wavelets on the interval is developed for modeling the free vibrations of composite pipes. The composite FRP pipe element is treated as a beam element. The finite pipe element is constructed in the wavelet space and then transformed to the physical space. Detailed expressions of the mass and stiffness matrices are derived for the composite pipe using the Bspline scaling and wavelet functions. Both Euler-Bernoulli and Timoshenko beam theories are considered. The generalized eigenvalue problem is formulated and solved to obtain the modal characteristics of the composite pipe. The developed wavelet-based finite element discretization scheme utilizes significantly less elements compared to the conventional finite element method for modeling composite pipes. Numerical solutions are obtained to demonstrate the accuracy of the developed element, which is verified by comparisons with some available results in the literature.

NUMERICAL SIMULATION OF ELLIPTIC PARTIAL DIFFERENTIAL EQUATIONS USING 3-SCALE HAAR WAVELETS

K.P. SUMANA,L.N. ACHALA,VISHNU NARAYAN MISHRA 장전수학회 2021 Advanced Studies in Contemporary Mathematics Vol.31 No.3

Elliptic partial differential equations (PDEs) arise in the mathematical modelling of many physical phenomena in science and engineering. In this paper, we obtain the numerical solution of Laplace and Poisson equations using two-dimensional 3-scale Haar wavelets. The elliptic PDEs are converted into a system of algebraic equations that involve a finite number of variables. The numerical results are compared with the exact solution to prove the accuracy of the Haar wavelet method. The error analysis of the 3-scale Haar wavelet method proves that the solution improves with the increase in the levels of resolution of the wavelet.

A Wavelet-based Yarn Quality Assessment for Fabric Visual Qualities

Kim, Joo-Yong Korean Society for Emotion and Sensibility 2002 감성과학 Vol.5 No.3

Random and/or periodic defects occur in all spun yarns. These irregularities can often lead to defects in finished fabric. Yarn evenness tests are used to obtain statistical data about yarn properties, such as CV%, which is useful in comparing several sets of similar data that differ in mean value but may have some commonality in relative variation. Although this statistical data is helpful in determining relative yam quality, accurate predictions of how the yarn will appear in fabric form are still difficult to obtain. As an promising alterative, wavelet analysis has been employed to localize yarn defect so as to predict the visual qualities of the fabrics.

직물외관을 위한 웨이블릿 기반의 방적사 평가시스템

김주용 ( Joo Yong Kim ) 한국감성과학회 2002 춘계학술대회 Vol.2002 No.-

Random and/or periodic defects occur in all spun yarns. These irregularities can often lead to defects in finished fabric. Yarn evenness tests are used to obtain statistical data about yarn properties, such as CV%, which is useful in comparing several sets of similar data that differ in mean value but may have some commonality in relative variation. Although this statistical data is helpful in determining relative yarn Quality, accurate predictions of how the yarn will appear in fabric form are still difficult to obtain. As an promising alterative, wavelet analysis has been employed to localize yam defect so as to predict the visual qualifies of the fabrics.