Blind Image Detection Based on Fusion Feature

Kueh Lee Hui,Sonia Carole Kouayep 한국정보기술학회 2016 한국정보기술학회논문지 Vol.14 No.4

Here, we proposed the fused feature based on the theoretical analysis and experimental verification of Local Binary Pattern (LBP) operator and Level Co-occurrence Matrix (GLCM) features to provide robust and complementary features than a single descriptor set for improving the detection performance of the blind image. This framework was focused on whether the image is blind or not by applying the fusion of two texture descriptor algorithms. The LBP algorithm is firstly employed to the image to create LBP image (LBP features). Then, the GLCM algorithm is applied to the LBP image to extract local co-occurrence features. The fused features both gain spatial distribution from the LBP image and the co-occurrence features. Finally, Support Vector Machine (SVM) is computed for forgery detecting on the image. The experiment results show that the proposed framework can achieve the accuracy of 98.5% on color image dataset of CASIA database.

Assessment of Carbon Stock in Chronosequence Rehabilitated Tropical Forest Stands in Malaysia

Kueh, Roland Jui Heng,Majid, Nik Muhamad,Ahmed, Osumanu Haruna,Gandaseca, Seca Institute of Forest Science 2016 Journal of Forest Science Vol.32 No.3

The loss and degradation in tropical forest region are some of the current global concern. Hence, these issues elevated the role of rehabilitated forests in providing ecological products and services. The information on the carbon stock is important in relation to global carbon and biomass use, but lacking from the tropical region. This paper reports the assessment of tree and soil carbon stock in a chronosequence rehabilitated tropical forest stands in Malaysia. The study site was at the UPM-Mitsubishi Forest Rehabilitation Project, UPMKB. $20{\times}20m$ plot was established each and assessed in 2009 at 1-, 10- and 19-year-old sites while an adjacent ${\pm}23-year-old$ natural regenerating secondary forest plot was established for comparison. The overall total carbon stock was in the order of 19-year-old>${\pm}23-year-old$>10-year-old>1-year-old. When forest carbon stock is low, the soil component plays an important role in the carbon storage. The forest carbon recovery is crucial to increase soil carbon stock. The variations in the carbon stock showed the different stages of the forest recovery. Species survived after 19-years of planting are potential species for carbon sequestration activities in rehabilitated forest. Human intervention in rehabilitating degraded forest areas through tree planting initiatives is crucial towards recovering the forest ecological role especially in forest carbon stock capacity.

Detection of Copy-Move Image Forgery Based on SIFT-LBP

Kueh Lee Hui,Sonia Carole Kouayep 한국정보기술학회 2015 한국정보기술학회논문지 Vol.13 No.7

Here, we proposes a new view of an enhanced copy-move forgery detection using Local Binary Pattern (LBP) based on Scale Invariant Features Transform (SIFT). This framework computes rotating invariant subuniform local binary patterns from the image keypoints. The SIFT algorithm is first applied to the converted grayscale image from the original image to extract scale invariant keypoints of the image. Then, the subuniform LBP is computed centered at the keypoints to extract the feature vector of each keypoint. Finally, Chi-square histogram-based distance is computed for matching purpose to determine similarity. Besides that, Random Sample Consensus (RSC) algorithm is adopted in to this framework to remove mismatches. Our experiment results show that the proposed method can produce accurate detection results and exhibit high robustness to scale and rotation forged regions.

R-LDA Face Recognition

Lee Hui Kueh,John-Tark Lee,Kwon-Soon Lee 한국지능정보시스템학회 2009 한국지능정보시스템학회 학술대회논문집 Vol.2009 No.11

A face recognition based on Regularized LDA is presented. The recognition performance is demonstrated in Matlab using face database of Intelligent Control Laboratory (ICONL). The algorithm attempts to address the SSS problem using a regularized Fisher's separability criterion. The simulations are conducted which identified the test samples as belonging to the same subject of those of trained subject of the ICONL face database. In addition, the recognition performance is compared to the recognition performance of the original PCA which are demonstrated in the paper. The main idea of the paper is to demonstrate the proposed method is particularly robust against the SSS problem compared to the traditional LDA and the simulations results show that the proposed algorithm improves the robustness of the recognition performance compared to PCA.

Revised R-LDA based ANN for Small Sample Size (SSS) Problem of Face Recognition

Lee Hui Kueh,Sang-Hyun Byun,John-Tark Lee 보안공학연구지원센터 2012 International Journal of Hybrid Information Techno Vol.5 No.2

Face Recognition Using Newly Regularized LDA

Lee Hui Kueh,John Tark Lee,Kwon Soon Lee 한국정보기술학회 2010 한국정보기술학회논문지 Vol.8 No.6

A newly proposed FR (Face Recognition) approach with a weighted regularization parameter based on the conventional R-LDA (Regularized Linear Discriminant Analysis) method was presented in this paper. In the case of SSS (Small Sample Size), since the face feature space has typically a large number of pixels and the total number of training samples is less than the dimension of face feature space, all the scatter matrices of LDA are singular and its recognition accuracy is directly deteriorated. Therefore, it is impossible to apply the origina1 LDA algorithm to the FR. In this paper, it was attempted to optimize the revised Fisher's criterion with a weighted regularization parameter as a solution of the SSS problem. ORL (Olivetti Research Lab) database by using MATLAB was analyzed and the performance of face recognition was evaluated. The simulations were given by identifying the test samples as the some of the training subjects. In addition, the recognition performance of the proposed approach was compared to the ones of the well-known conventional methods such as Eigenfaces and R-LDA, which were established in this paper. The main interest idea of this paper was to demonstrate the superiority in robustness against the SSS problem of the proposed approach to the conventional Eigenfaces and R-LDA methods. The recognition rate of the proposed approach were fairly higher than others. In the future, the applicability of this proposed algorithm to the FR of the large sample database shall be discussed.

Impact resistance efficiency of bio-inspired sandwich beam with different arched core materials

Ahmad B.H. Kueh,Chun-Yean Tan,MOHD YAZID YAHYA,Mat Uzir Wahit 국제구조공학회 2022 Steel and Composite Structures, An International J Vol.44 No.1

Impact resistance efficiency of the newly designed sandwich beam with a laterally arched core as bio-inspired by the woodpecker is numerically investigated. The principal components of the beam comprise a dual-core system sandwiched by the top and bottom laminated CFRP skins. Different materials, including hot melt adhesive, high-density polyethylene (HDPE), acrylonitrile butadiene styrene (ABS), epoxy resin (EPON862), aluminum (Al6061), and mild carbon steel (AISI1018), are considered for the side-arched core layer of the beam for impact efficiency assessment. The aluminum honeycomb takes the role of the second core. Contact force, stress, damage formation, and impact energy for beams equipped with different materials are examined. A diversity in performance superiority is noticed in each of these indicators for different core materials. Therefore, for overall performance appraisal, the impact resistance efficiency index, which covers several chief impact performance parameters, of each sandwich beam is computed and compared. The impact resistance efficiency index of the structure equipped with the AISI1018 core is found to be the highest, about 3-10 times greater than other specimens, thus demonstrating its efficacy as the optimal material for the bio-inspired dual-core sandwich beam system.

Assessment of Carbon Stock in Chronosequence Rehabilitated Tropical Forest Stands in Malaysia

Roland Jui Heng Kueh,Nik Muhamad Majid,Osumanu Haruna Ahmed,Seca Gandaseca 강원대학교 산림과학연구소 2016 Journal of Forest Science Vol.32 No.3

The loss and degradation in tropical forest region are some of the current global concern. Hence, these issues elevated the role of rehabilitated forests in providing ecological products and services. The information on the carbon stock is important in relation to global carbon and biomass use, but lacking from the tropical region. This paper reports the assessment of tree and soil carbon stock in a chronosequence rehabilitated tropical forest stands in Malaysia. The study site was at the UPM-Mitsubishi Forest Rehabilitation Project, UPMKB. 20×20 m plot was established each and assessed in 2009 at 1-, 10- and 19-year-old sites while an adjacent ±23- year-old natural regenerating secondary forest plot was established for comparison. The overall total carbon stock was in the order of 19-year-old>±23-year-old> 10-year-old>1-year-old. When forest carbon stock is low, the soil component plays an important role in the carbon storage. The forest carbon recovery is crucial to increase soil carbon stock. The variations in the carbon stock showed the different stages of the forest recovery. Species survived after 19-years of planting are potential species for carbon sequestration activities in rehabilitated forest. Human intervention in rehabilitating degraded forest areas through tree planting initiatives is crucial towards recovering the forest ecological role especially in forest carbon stock capacity.

Newly Regularized LDA for SSS Problem with application to Face Recognition

곽려혜(Lee Hui Kueh),김권우(Kwon-Woo Kim),한동열(Dong-Yeol Han),이승호(Seung-Ho Lee),이준탁(John-Tark Lee),이권순(Kwon-Soon Lee) 대한전기학회 2010 대한전기학회 학술대회 논문집 Vol.2010 No.7

A newly proposed FR (Face Recognition) approach with a weighted regularization parameter based on the conventional R-LDA (Regularized Linear D iscriminant A nalysis) method was presented in this paper. SSS (Sm all Sample Size) problem refers to the total number of training samples is less than the dimension of face feature space and all the scatter matrices of LDA are singular. Therefore, it is impossible to apply the LDA algorithm to the FR. In this paper, it was attempted to optimize the revised Fisher's criterion with a weighted regularization parameter as a solution of the SSS problem. Simulations using ORL (Olivetti Research Lab) database in MATLAB were simulated in order to evaluate the recognition performance of the proposed FR. In addition, the recognition performance of the proposed approach was compared to the ones of the well-known conventional methods such as Eigenfaces and R-LDA, which were established in this paper.

Repeated impact response of bio-inspired sandwich beam with arched and honeycomb bilayer core

Ahmad B.H. Kueh,Juin-Hwee Tan,Shukur Abu Hassan,Mat Uzir Wahit 국제구조공학회 2023 Structural Engineering and Mechanics, An Int'l Jou Vol.85 No.6

The article examines the impact response of the sandwich beam furnished by a novel bilayer core as inspired by the woodpecker’s head architecture under different repeatedly exerted low-velocity impact loadings by employing the finite element package, ABAQUS. The sandwich beam forms four essential parts comprising bottom and top carbon fiber reinforced polymer laminates encasing bilayer core made of laterally arched solid hot melt adhesive material and aluminum honeycomb. Impact loadings are implemented repeatedly with a steel hemisphere impactor for various impact energies, 7.28 J, 9.74 J, and 12.63 J. Essentially, the commonly concentrated stresses at the impact region are regulated away by the arched core in all considered cases thus reducing the threat of failure. The sandwich beam can resist up to 5 continual impacts at 7.28 J and 9.74 J but only up to 3 times repeated loads at 12.63 J before visible failure is noticed. In the examination of several key impact performance indicators under numerous loading cases, the proposed beam demonstrates favorably up to 1.3-11.2 higher impact resistance efficacies compared to existing designs, therefore displaying an improvement in repeated impact resistance of the new design.