• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.597-600
• /
• 1999

In this paper, we propose a fast object-tracking algorithm in a moving picture. The proposed object-tracking algorithm is based on a projection scheme. More specifically, to alleviate the computational complexities of the previous motion estimation methods, we propose to use the projected row and column 1-D image data to extract the motion information. Experimental results show that the proposed method can detect the motion of an object fairly well with reduced computational time.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.171-174
• /
• 2000

This paper proposes a pipelined adaptive filter based on affine projection algorithm with order 2. This filter gives a better convergence performance than that of LMS or NLMS pipeline algorithm and has same latency with the pipeline algorithm based on equivalent transformation. Compared to the critical path of the pipeline NLMS implementation, only 2 additions are increased in that of the proposed implementation.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.443-451
• /
• 2015

In this paper we suggest a new two-wheelers detection algorithm using uniform local binary pattern weighting value for projection vectors. The first, we calculate feature vectors using projection method which has robustness for rotation invariant and reducing dimensionality for each cell from origin image. The second, we applied new weighting values which are calculated by the modified local binary pattern showing the fast compute and simple to implement. This paper applied the Adaboost algorithm to make a strong classification from weak classification. In this experiment, we can get the result that the detection rate of the proposed method is higher than that of the traditional method.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.502-509
• /
• 2016

Feature detection and description are key ingredients of common image processing and computer vision applications. Most existing algorithms focus on robust feature matching under challenging conditions, such as inplane rotations and scale changes. Consequently, they usually fail when the scene is blurred by camera shake or an object's motion. To solve this problem, we propose a new feature description algorithm that is robust to image blur and significantly improves the feature matching performance. The proposed algorithm builds a feature descriptor by considering the integral projection along four angular directions ($0^{\circ}$, $45^{\circ}$, $90^{\circ}$, and $135^{\circ}$) and by combining four projection vectors into a single highdimensional vector. Intensive experiment shows that the proposed descriptor outperforms existing descriptors for different types of blur caused by linear motion, nonlinear motion, and defocus. Furthermore, the proposed descriptor is robust to intensity changes and image rotation.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.18 no.3
• /
• pp.101-111
• /
• 1993

The purpose of this paper is to show the graphic representation of a linear programming problem by a projection method. First, we develop a projection method which conserves the optimality in the projected space, and next we introduce an algorithm to visualize the feasible solution set and the solution process by the projection method. Finally, we give an example to represent a 4-dimensional linear programming problem graphically.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.91-94
• /
• 1998

본 논문에서는 블록간, 블록 내수, 수평. 수직 방향성, 그리고 시간 영역의 정보를 이용하는 압축 동영상의 블록화 및 링 현상을 제거하는 방식을 제안한다. 위의 정보를 이용하여 새로운 부가 함수가 정의되며, 최적 해를 구하기 위해 gradient와 projection을 결합시킨 hybrid 형태의 기법을 이용한다. 또한, 정규화 계수들 및 projection을 위한 영역의 설정을 부호화단에서는 이용 가능한 정보로부터 추출하게 되므로 계산량을 감소시킬 수 있다. 실험 결과로부터 제안된 방식의 효율성을 확인할 수 있다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.11a
• /
• pp.119-120
• /
• 2010

• ETRI Journal
• /
• v.37 no.2
• /
• pp.317-327
• /
• 2015

A reliable analysis of consumer preference from a large amount of purchase data acquired in real time and an accurate customer characterization technique are essential for successful direct marketing campaigns. In this study, an optimal segmentation of post office customers in Korea is performed using a subspace projection-based clustering method to generate an accurate customer characterization from a high-dimensional census dataset. Moreover, a traditional temporal mining method is extended to an algorithm using the MapReduce framework for a consumer preference analysis. The experimental results show that it is possible to use parallel mining through a MapReduce-based algorithm and that the execution time of the algorithm is faster than that of a traditional method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2349-2351
• /
• 2010

Photo Acoustic Tomography (PAT) is a hybrid imaging modality which combines high contrast of optical imaging and spatial resolution of ultrasound imaging, thus it is suitable to image biological tissue noninvasively. Laser-induced photoacoustic signals were measured from a sample by means of an unfocused ultrasound transducer, then PAT image was reconstructed based on a universal back-projection algorithm. To evaluate the feasibility of our system, phantom test was performed, consequently, the PAT images obtained using our system showed highly analogous shape and volume with those of the phantom. This result demonstrated that our system can provide a powerful tool for imaging the substructure of biological tissue in non-invasive manner.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.895-896
• /
• 2008

We propose a adaptive combination of affine projection algorithm (APA) filters with different update interval. Two APA filters with different update interval are adapted independently in order to keep the advantages of both component filters. This novel scheme provides improvement of performance in term of the convergence rate and the steady-state error. Experimental results show good properties of the proposed algorithm.