• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2237-2253
• /
• 2017

For the existing security problem based on Fuzzy Vault algorithm, we propose a cancelable fingerprint template encryption scheme in this paper. The main idea is to firstly construct an irreversible transformation function, and then apply the function to transform the original template and template information is stored after conversion. Experimental results show it effectively prevents the attack from fingerprint template data and improves security of the system by using minutiae descriptor to encrypt abscissa of the vault. The experiment uses public FVC2004 fingerprint database to test, result shows that although the recognition rate of the proposed algorithm is slightly lower than the original program, but the improved algorithm security and complexity are better, and therefore the proposed algorithm is feasible in general.

• Journal of Information Processing Systems
• /
• 제12권3호
• /
• pp.392-409
• /
• 2016

The aim of this paper is to examine the effectiveness of combining three popular tools used in pattern recognition, which are the Active Appearance Model (AAM), the two-dimensional discrete cosine transform (2D-DCT), and Kernel Fisher Analysis (KFA), for face recognition across age variations. For this purpose, we first used AAM to generate an AAM-based face representation; then, we applied 2D-DCT to get the descriptor of the image; and finally, we used a multiclass KFA for dimension reduction. Classification was made through a K-nearest neighbor classifier, based on Euclidean distance. Our experimental results on face images, which were obtained from the publicly available FG-NET face database, showed that the proposed descriptor worked satisfactorily for both face identification and verification across age progression.

• 반도체디스플레이기술학회지
• /
• 제6권1호
• /
• pp.49-52
• /
• 2007

The recent advances in digital imaging and computing technology have resulted in a rapid accumulation of digital media in the personal computing and entertainment industry. In addition, large collections of such data already exist in many scientific application domains such as the geographic information systems (GIS), digital library, trademark imaging, satellite imaging and medical imaging. Thus, the need for content-based retrieval from visual media, such as image and video data, is ever increasing rapidly in many applications.

• Journal of Mechanical Science and Technology
• /
• 제16권1호
• /
• pp.75-82
• /
• 2002

A simultaneous optimal design problem of structural and control systems is discussed by taking a 3-D truss structure as an object. We use descriptor forms for a controlled object and a generalized plant because the structural parameters appear naturally in these forms. We consider a minimum weight design problem for structural system and disturbance suppression problem for the control system. The structural objective function is the structural weight and the control objective function is $H_{\infty}$ norm from the disturbance input to the controlled output in the closed-loop system. The design variables are cross sectional areas of the truss members. The conditions for the existence of controller are expressed in terms of linear matrix inequalities (LMI) By minimizing the linear sum of the normalized structural objective function and control objective function, it is possible to make optimal design by which the balance of the structural weight and the control performance is taken. We showed in this paper the validity of simultaneous optimal design of structural and control systems.

• 방송공학회논문지
• /
• 제5권2호
• /
• pp.176-187
• /
• 2000

본 논문에서는 MPEG-2 시스템 층의 하나인 방송 및 전송을 위한 트랜스포트 스트림(TS)상에 MPEG-4 데이터를 구조화하여 MPEG-4 Over MPEG-2 TS 비트 스트림을 만드는 방법과 이를 저장 매체 포맷중 하나인 MP4 파일로 변환하는 방법에 관한 연구이다. MPEG-4는 객체 단위의 부호화 비트 스트림으로 구성되기 때문에 이들 객체의 속성을 표현하는 객체 기술자, 객체들간의 시공간 관계를 표현하는 장면 기술자가 필요하며 또한 모든 객체들간의 복호화 정보와 객체간의 동기화를 위해 다양한 여러 가지 기술자들이 필요한데 이런 다양한 MPEG-4 비트 스트림을 어떻게 MPEG-2 TS 규격에 맞게 전송하는가에 초점을 두었다. 또한 설계한 MPEG-4 Over MPEG-2 TS 비트 스트림을 저장매체를 대상으로 하는 새로운 파일 규격인 MP4 파일로 변환하는 알고리듬을 제시하고 구현 방법을 소개한다.

• Transactions on Control, Automation and Systems Engineering
• /
• 제3권3호
• /
• pp.139-145
• /
• 2001

In this paper, we consider the H$_2$(or guaranteed cost control) and H$_{\infty}$ controller design methods for singular(or descriptor) systems with input time delay. Also, a mixed H$_2$and H$_{\infty}$ controller design algorithm is treated by combination of the proposed H$_2$and H$_{\infty}$ controller design method. The sufficient conditions for the existence of controllers and controller design methods are introduced at each Lemma and Theorem. Furthermore, we present optimization problems to get the upper bound of performance measures. The proposed methods are checked by examples.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권9호
• /
• pp.3762-3781
• /
• 2020

Infrared pedestrian target recognition is a vital problem of significant interest in computer vision. In this work, a novel infrared pedestrian target recognition method that uses heterogeneous features with multi-kernel transfer learning is proposed. Firstly, to exploit the characteristics of infrared pedestrian targets fully, a novel multi-scale monogenic filtering-based completed local binary pattern descriptor, referred to as MSMF-CLBP, is designed to extract the texture information, and then an improved histogram of oriented gradient-fisher vector descriptor, referred to as HOG-FV, is proposed to extract the shape information. Second, to enrich the semantic content of feature expression, these two heterogeneous features are integrated to get more complete representation for infrared pedestrian targets. Third, to overcome the defects, such as poor generalization, scarcity of tagged infrared samples, distributional and semantic deviations between the training and testing samples, of the state-of-the-art classifiers, an effective multi-kernel transfer learning classifier called MK-TrAdaBoost is designed. Experimental results show that the proposed method outperforms many state-of-the-art recognition approaches for infrared pedestrian targets.

• 한국정보과학회논문지:시스템및이론
• /
• 제37권5호
• /
• pp.314-318
• /
• 2010

본 논문에서는 사용자가 관심을 갖는 다중 영역기반(ROI)으로 이미지를 검색하는 방법을 제안한다. 제안한 방법은 이미지를 블록으로 구분한 후 사용자가 선택한 다중 ROI와 겹치는 부분을 선택하고 해당 블록의 MPEG-7 도미넌트 컬러와 블록의 상대적 위치를 고려하여 유사도를 측정한다. 실험결과 제안한 방법은 전역 이미지 검색이나 동일한 위치의 블록만 비교하는 경우보다 높은 성능향상을 나타냈고, 다중 ROI의 경우 상대적 위치를 고려하는 방법이 다른 방법에 비해 우수한 성능을 나타냈다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.288-301
• /
• 2017

In this paper, we propose an optimized algorithm for texture classification by computing a completed modeling of the local binary pattern (CLBP) instead of the traditional LBP of a scalable block size in an image. First, we show that the CLBP descriptor is a better representative than LBP by extracting more information from an image. Second, the CLBP features of scalable block size of an image has an adaptive capability in representing both gross and detailed features of an image and thus it is suitable for image texture classification. This paper successfully implements a machine learning scheme by applying the CLBP features of a scalable size to the Support Vector Machine (SVM) classifier. The proposed scheme has been evaluated on Outex and CUReT databases, and the evaluation result shows that the proposed approach achieves an improved recognition rate compared to the previous research results.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.