• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.137-145
• /
• 2014

This paper suggests an LDA-based long distance face recognition algorithm for intelligent surveillance system. The existing face recognition algorithm using single distance face image as training images caused a problem that face recognition rate is decreased with increasing distance. The face recognition algorithm using face images by actual distance as training images showed good performance. However, this also causes user inconvenience as it requires the user to move one to five meters in person to acquire face images for initial user registration. In this paper, proposed method is used for training images by using single distance face image to automatically create face images by various distances. The test result showed that the proposed face recognition technique generated better performance by average 16.3% in short distance and 18.0% in long distance than the technique using the existing single distance face image as training. When it was compared with the technique that used face images by distance as training, the performance fell 4.3% on average at a close distance and remained the same at a long distance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2341-2349
• /
• 2015

The commonly used Goldschmidt's floating-point divider algorithm performs two multiplications in one iteration. In this paper, a tentative error corrected K'th Goldschmidt's floating-point number divider algorithm which performs K times multiplications in one iteration is proposed. Since the number of multiplications performed by the proposed algorithm is dependent on the input values, the average number of multiplications per an operation in single precision and double precision divider is derived from many reciprocal tables with varying sizes. In addition, an error correction algorithm, which consists of one multiplication and a decision, to get exact result in divider is proposed. Since the proposed algorithm only performs the multiplications until the error gets smaller than a given value, it can be used to improve the performance of a divider unit. Also, it can be used to construct optimized approximate reciprocal tables.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.425-427
• /
• 2012

H.264/AVC 는 움직임 예측/보상을 수행할 때, 하나 이상의 다중 참조영상을 허용하여 예측 정확성을 높임으로써 높은 압축효율을 얻을 수 있지만, 부호화기가 높은 복잡도를 갖는 단점이 있다. 본 논문에서는 H.264/AVC 부호화기의 높은 복잡도를 줄이기 위하여 이미 부호화된 주변 블록의 부호화 정보와 현재 부호화하는 매크로블록(MB)의 $16{\times}16$ 화면간 예측 결과를 적응적으로 이용하여 현재 부호화하는 매크로블록의 참조영상 후보의 수를 줄이는 고속 부호화 알고리즘을 제안한다. 모의실험을 통하여 제안한 알고리즘은 JM17.2 에 비해 평균 47% 정도의 부호화 시간을 감소시키며, 이때 평균 비트율은 1.4%로 부호화 효율의 감소가 미미함을 확인 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.276-277
• /
• 2014

일상생활 중 장시간 계측하는 심전도 모니터링의 경우 250Hz~500Hz 또는 그 이상의 높은 샘플링 속도가 요구된다. 그러나 일상생활 중 장시간 계측을 위해 소형화된 제한적인 기기로는 기하급수적으로 늘어나는 데이터를 감당하기가 어렵다. 따라서 본 연구에서는 한정된 자원을 효율적으로 이용하기 위한 템플릿 매칭 기반의 심전도 압축 알고리즘을 제안하였으며 모바일 어플리케이션에 구현하고자 하였다. 그 결과 CR평균은 5.56 PDR평균은 5.33으로 나타났으며, 모바일 어플리케이션에 적용하여 그 유용성을 확인하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.2
• /
• pp.111-123
• /
• 2009

We present an efficient algorithm for computing the Hausdorff distance between two 2D convex polygons. Two convex polygons are bounded by k-DOPs and the regions of interest are traced using the orientational and hierarchical properties of k-DOP. The algorithm runs in a logarithmic time in the average case, and the worst case time complexity is linear.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.921-924
• /
• 2006

본 논문에서는 이미지 인증을 위해 삽입한 워터마크로 인해 발생한 영상 정보의 손실을 워터마크 추출 후 제거하여 원영상으로 복원할 수 있는 리버서블 워터마킹 알고리즘을 제안하였다. 제안한 알고리즘은 Lee.S.K.[4]의 알고리즘이 지니는 플립 현상을 제거하기 위해 Location Map을 이용하여 워터마크를 삽입한다. 실험 결과 본 논문에서 제안한 알고리즘은 평균 52.06dB의 PSNR을 보여 우수한 비가시성을 나타냈으며, $6k{\sim}30k$ bits의 높은 정보 삽입량을 보여 이미지 인증 응용에 적합함을 확인할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.498-503
• /
• 2018

본 논문은 한국관광공사에서 제공하는 Tour API 3.0 Open API에서 제공하는 데이터를 바탕으로 한다. Google에서 제공해 주는 TensorFlow를 통해서 인공 신경망 딥러닝 알고리즘과 가중치 알고리즘을 통해서 사용자 기호에 맞춰 정보를 추천해 주는 어플리케이션 '눈치코칭_여행딥러닝'의 설계 및 구현에 대하여 서술한다. 현재 순위알고리즘은 평균적으로 40%, 딥러닝 모델은 60%정확도를 보여, 딥러닝이 보다 좋은 성능을 보였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.123-128
• /
• 2011

In this paper, we design the CA-CFAR processor using a root-square approximation approach and a fixed-point operation to improve hardware complexity and reduce computational effort. We also propose CA-CFAR processor with multi-window, which is capable of concurrent parallel processing. The proposed architecture is synthesized and implemented into the FPGA and the performance is compared with the conventional processor designed by root-square libarary licensed by FPGA corporation.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.621-626
• /
• 2016

Recursive query algorithm is used in many social network services, e.g., reachability queries in social networks. Recently, the size of social network data has increased as social network services evolve. As a result, it is almost impossible to use the recursive query algorithm on a single machine. In this paper, we implement recursive query on two popular in-memory distributed platforms, Spark and Twister, to solve this problem. We evaluate the performance of two implementations using 50 machines on Amazon EC2, and real-world data sets: LiveJournal and ClueWeb. The result shows that recursive query algorithm shows better performance on Spark for the Livejournal input data set with relatively high average degree, but smaller vertices. However, recursive query on Twister is superior to Spark for the ClueWeb input data set with relatively low average degree, but many vertices.

• Journal of Digital Convergence
• /
• v.13 no.10
• /
• pp.219-224
• /
• 2015

This research estimates the Mixture of Normals of households saving rate in Korea. Our sample is MDSS, micro-data in 2014 and Gibbs algorithm is used to estimate the Mixture of Normals. Evidences say some results. First, Gibbs algorithm works very well in estimating the Mixture of Normals. Second, Saving rate data has at least two components, one with mean zero and the other with mean 29.4%. It might be that households would be separated into high saving group and low saving group. Third, analysis of Mixture of Normals cannot answer that question and we find that income level and age cannot explain our results.