• Title/Summary/Keyword: 강인화

Search Result 720, Processing Time 0.026 seconds

Implementation of a Multi-DSP Board for High-definition Video Signal Processing and a Real-time Tracking System for Objects in the Video Sequence (고해상도 영상처리에 적합한 다중 DSP 보드의 구현 및 비디오 영상 내 물체의 실시간 추적 시스템)

  • Jeong, Cheol-Jun;Kim, Jin-Yul;Lee, Cheol-Woo;Yang, Yoon-Gi
    • Proceedings of the KIEE Conference
    • /
    • 2008.04a
    • /
    • pp.113-114
    • /
    • 2008
  • 본 논문에서는 HD 비디오 영상 처리를 효과적으로 수행할 수 있는 다중 DSP 아키텍쳐를 제안하고 프로토타입 보드를 설계 제작하였다. 또한, 구현된 보드를 이용하여 비디오 영상 내 물체(얼굴)의 실시간 추석시스템을 구현하였다. 물체 추적 기법인 PF(Particle Filtering) 기법은 배경 클러터가 존재하는 환경에서도 강인하게 물체를 추적할 수 있지만 많은 수의 샘플을 사용하는 경우 필요한 계산량이 많아져 실시간 구현이 매우 어렵다는 문제점을 가지고 있다. 본 논문에서는 이러한 경우에도 실시간 추적이 가능하도록 병렬화된 PF 추적 방법을 제안하고 제작된 보드 상에 구현하였다. 구현된 병렬 처리 추적에서는 150개의 PF 샘플들을 5개의 슬레이브 DSP로 분산하여 컬러 유사도 기탄의 관측 확률을 계산하고 그 결과를 마스터 DSP에서 종합하여 추적의 정확도를 높이고자 하였다. 실험에는 $720{\times}480$ 픽셀 영상이 사용되었으며, 실험 결과 배경 클러터가 존재하는 경우에도 충분한 PF 샘플 수의 사용에 따라 대상 물체를 강인하게 추적하는 우수한 성능을 확인할 수 있었다.

  • PDF

A Study on Face Recognition using Support Vector Machine (SVM을 이용한 얼굴 인식에 관한 연구)

  • Kim, Seung-Jae;Lee, Jung-Jae
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.16 no.6
    • /
    • pp.183-190
    • /
    • 2016
  • This study proposed a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. The algorithm proposed detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). Also, by applying the feature vector obtained for SVM, face areas can be tested. After the testing, using the feature vector is final face recognition performed. The algorithm proposed in this study could increase the stability and accuracy of recognition rates and as a large amount of calculation was not necessary due to the use of two dimensions, real-time recognition was possible.

Rotation invariant face recognition in a polar coordinate system using LDAr (극좌표계에서 회전에 강인한 LDAr을 이용한 얼굴 인식)

  • Oh, Jae-Hyun;Kwak, No-Jun
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 2010.07a
    • /
    • pp.195-197
    • /
    • 2010
  • 본 논문은 기존 평행좌표를 이용하는 얼굴 영상 대신 극좌표계 변환을 이용한 얼굴 영상을 이용하여 회전에 강인한 얼굴인식 방법을 제안한다. 극좌표계 변환 방법은 얼굴의 중심부분의 한 점을 극으로 삼아 이 점을 기준으로 360도 각 방향으로 일정 길이만큼 얼굴 영상을 샘플링 하여 새로운 얼굴 영상을 제작하는 방법이다. 이 극좌표계 변환 방법을 이용해 재구성된 영상에 대해 회귀( regression )문제 해결을 위해 변형된 LDA인 LDAr(LDA for regression)을 이용하여 얼굴의 중심부분의한 점인 극을 중심으로 임의의 각도로 회전된 영상의 회전 정도를 추정하여 이를 정규화 시키는 방법을 통해 얼굴 인식의 인식률을 향상시키고자 한다. LDAr은 LDA의 기본개념인 각 클래스 간 떨어진 정도를 최대화하는 것이 목적으로 클래스간 분산과 클래스내 분산의 비율을 최대화 하는 방법을 응용하여 이를 회귀문제에 적용할 수 있게 변형을 한 것이다. 즉, LDAr은 목표값(target)의 차이가 큰 샘플들과 목표값의 차이가 작은 샘플들 간의 거리의 비율을 최대화 하는 것을 목적으로 하게 된다. 제안된 방법을 Yale데이터에 적용하여 임의의 각도로 회전시킨 영상에 대해 회전 각도를 정확히 찾아내는 것을 확인할 수 있었다.

  • PDF

An Efficient PN Sequence Embedding and Detection Method for High Quality Digital Audio Watermarking (고음질 디지털 오디오 워터마킹을 위한 효율적인 PN 시퀸스 삽입 및 검출 방법)

  • 김현욱;오현오;김연정;윤대희
    • Journal of Broadcast Engineering
    • /
    • v.6 no.1
    • /
    • pp.21-31
    • /
    • 2001
  • In the PN-sequence based audio watermarking system, the PN sequence is shaped by a filter derived from the psychoacoustic model to increase robustness and inaudibility The psychoacoustic model calculated in each audio segment, however, requires heavy computational loads. In this paper, we propose an efficient watermarking system adopting a fixed-shape perceptual filter that substitutes psychoacoustic model derived filter. The proposed filter can shape the PN-sequence to be inaudible and enable to embed the robust watermark in a simple manner. Moreover, we propose an anchitecture for the PN-sequence compensation fitter In the watermark detecter to increase correlation between the watermark and the PN-sequence. With the proposed architecture, the blind watermark detection performance has been enhanced.

  • PDF

The Study on the Strength and Toughness of Austempered Ductile Cast Iron (오스템퍼 처리(處理)한 구상흑연주철(球狀黑鉛鑄鐵)의 강인화(强靭化)에 관(關)한 연구(硏究)(1))

  • Lee, Young-Kye;Kim, Sug-Won;Kim, Dong-Keon;Lee, Bang-Sik
    • Journal of Korea Foundry Society
    • /
    • v.10 no.2
    • /
    • pp.144-153
    • /
    • 1990
  • Ductile cast iron has good ductility and toughness, for the graphite morphology is spheroidal. It has been reported that the strengthening and toughening of the ductile cast iron was resulted from the modification of matrix structure by the heat treatment or the addition of alloying elements. In this study, effects of various special heat treatments (cyclic heat treatment and intermediate heat treatment) and Ni addition on the toughness and strength of the austempered ductile cast iron were studied. The results obtained from this study were as follows : 1. The amount of fine pearlite was increased with the Ni content and the number of cycle in cyclic heat treatment. 2. When the specimens treated and not by special heat treatment at 820 was austempered, in the former the austenite was formed on grain boundary entirely, but in the latter on grain boundary partially. 3. The impact energy was decreased with the Ni content, because the coarisen austenite pools formed with the Ni content was transformed into martensite during quenching. 4. The mechanical properties of austempered ductile cast iron containing 2%Ni treated cyclic heat treatment(5 cycles)was very excellent in handness 99(HRB), impact energy 12(kg-m) maximum fracture load 1500(kg-f).

  • PDF

Error Concealment Techniques for Visual Quality Improving (화질 향상을 위한 오류 은폐 기법)

  • Suh, Jae-Won
    • The Journal of the Korea Contents Association
    • /
    • v.6 no.2
    • /
    • pp.65-74
    • /
    • 2006
  • The MPEG-2 video compressed bitstream is very sensitive to transmission errors due to the complex coding structure of the MPEG-2 video coding standard. If one packet is lost or received with errors, not only the current frame will be corrupted, but also errors will propagate to succeeding frames within a group of pictures. Therefore, we employ various error resilient coding/decoding techniques to protect and reduce the transmission error effects. Error concealment technique is one of them. Error concealment technique exploits spatial and temporal redundancies of the correctly received video data to conceal the corrupted video data. Motion vector recovery and compensation with the estimated motion vector is good approach to conceal the corrupted data. In this paper, we propose various error concealment algorithms based on motion vector recovery, and compare their performance to those of conventional error concealment methods.

  • PDF

Multi-Watermarking Method for Image Ownership Protection and Tamper Proofing (영상의 소유권 보호와 변질검증을 위한 다중 워터마킹 방식)

  • 김창훈;박경준;고형화
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.28 no.8C
    • /
    • pp.811-820
    • /
    • 2003
  • In this paper, multi-watermarking algorithm is proposed to satisfy two purpose of ownership protection and tamper proofing simultaneously. At first, for robust watermarking, the location of the embedding wavelet coefficient is selected by using existing QSWT algorithm. And then, we propose the method inserting discrete cosine transformed watermark. The watermarked image is watermarked again for the tamper proofing. The tamper proofing algorithm is also proposed. According to the experimental results, the proposed multi-watermarking algorithm is robust to the attack, such as blurring, sharpening, JPEG compression. And also, the tampered area are detected in blocks, making it simple to judge which pixels are changed.

Mechanical Properties and Microstructures of Self-toughened Silicon Nitride Cermic Prepared by Microstructural Control (미세구조 제어에 의해 제조한 자체 강인화 질화규소 세라믹의 기계적 성질과 미세조직)

  • 김완중;이영규;조원승;최상욱
    • Journal of the Korean Ceramic Society
    • /
    • v.36 no.4
    • /
    • pp.432-443
    • /
    • 1999
  • The self-toughened Si3N4 ceramics where needle-like coarse ${\beta}$-Si3N4 grains were dispersed within fine-grain-ed matrix were prepared via hot-prssing at 1730$^{\circ}C$ for 2 h using 5 vol% ${\beta}$-Si3N4 whiskers as a seed. In this study the microstructures and mechanical properties of self-toughened Si3N4 ceramics were investigated. The flexural strength of self-toughened Si3N4 ceramics was increased from 600-800 MPa of the Si3N4 monolith to 830-1025 MPa. The KIC was also increased from 4.0-5.0MPa$.$m1/2 of the Si3N4 monolith to 5.8-6.5MPa$.$m1/2$.$The needle-like coarse Si3N4 grains in self-toughened ceramics were considered to induce various toughening mechanisms including the crack deflection pull-out and bridging and to contribute to KIC improvement. In ad-dition to toughening mechanisms the KIC improvement was considered to be partially indebted also to the orien-tation of large ${\beta}$-Si3N4 grains and to the promoting effect of ${\beta}$-Si3N4 whiskers on the ${\alpha}$ to ${\beta}$ transtion.

  • PDF

Microstructure and Mechanical Properties of Self-Reinforced Si3N4 Ceramic Prepared by Pressureless-Sintering (상압소결에 의해 제조한 자체 강인화 질화규소 세리믹의 미세조직과 기계적 성질)

  • 김완중;이영규;조원승;최상욱
    • Journal of the Korean Ceramic Society
    • /
    • v.36 no.5
    • /
    • pp.547-554
    • /
    • 1999
  • The self-reinforced Si3N4 ceramics were prepared by pressureless-sintering using ${\beta}$-Si3N4 whiskers as a seed. Effects of ${\beta}$-Si3N4 whiskers on microstructure and mechanical properties and the ${\alpha}$ to ${\beta}$ phase transition of Si3N4 were investigated. The self-reinforced Si3N4 ceramics were densified(relative density$\geq$98%) by pressureless-sintering (1800$^{\circ}C$ 2h) using 8mol% Y2O3 and 6mol% Al2O3 as sintering aids and 5 vol% ${\beta}$-Si3N4 whiskers within self-reinforced Si3N4 ceramic seemed to hinder the densification owing to their acicular shapes but accelerated the ${\alpha}$ to ${\beta}$ phase transition because they acted as pre-existing nuclei. It was found that the more ${\beta}$-Si3N4 nucei the faster ${\alpha}$ to ${\beta}$ phase transition.

  • PDF

Audio fingerprint matching based on a power weight (파워 가중치를 이용한 오디오 핑거프린트 정합)

  • Seo, Jin Soo;Kim, Junghyun;Kim, Hyemi
    • The Journal of the Acoustical Society of Korea
    • /
    • v.38 no.6
    • /
    • pp.716-723
    • /
    • 2019
  • Fingerprint matching accuracy is essential in deploying a music search service. This paper deals with a method to improve fingerprint matching accuracy by utilizing an auxiliary information which is called power weight. Power weight is an expected robustness of each hash bit. While the previous power mask binarizes the expected robustness into strong and weak bits, the proposed method utilizes a real-valued function of the expected robustness as weights for fingerprint matching. As a countermeasure to the increased storage cost, we propose a compression method for the power weight which has strong temporal correlation. Experiments on the publicly-available music datasets confirmed that the proposed power weight is effective in improving fingerprint matching performance.