• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.262-263
• /
• 2012

다중 센서의 영상, 예를 들어 가시광 영상과 적외선 영상은 서로 다른 특징을 가지고 있기 때문에 본 논문에서는 IR 영상의 특징을 보존한 새로운 혼합기법을 제안하다. 이러한 혼합기법은 의료 영상, 보안 영상 등에서 매우 중요하고 다양하게 다루어진다. 일반적인 혼합기법을 사용하게 되면 영상간의 특색 때문에 혼합 시 조화롭지 못하는 문제점을 가진다. 이러한 문제점을 해결하기 위해서 본 논문에서는 중요도 맵을 추출하고 그 영역에 대하여 포아송 블랜딩을 통해 두 개의 다른 특징을 가시광 영상을 혼합한다. 제안한 알고리즘은 기존의 연구와 다르게 혼합할 영역을 수동으로 지정하는 것이 아니라 자동적으로 추출하고, 가시광 영상에 IR 영상에서만 검출되는 영역을 결합한 새로운 결과를 얻을 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.143-145
• /
• 2022

MPEG-VCM(Video Coding for Machine)은 입력된 비디오 특징(feature)를 압축하는 Track1 과 입력 영상을 직접 압축하는 Track2 로 나뉘어 표준화가 진행중이다. 본 논문은 VCM Track 1 에 해당하는 Detectron2 FPN(Feature Pyramid Network)에서 추출한 다중 스케일 특징맵을 VVC 로 압축하는 MSFC(Multi-Scale Feature Compression)을 구조를 제안한다. 본 논문의 MSFC 에서는 다중 스케일 특징을 결합하여 부호화/복호화하는 기존의 구조에서 특징맵의 해상도를 줄여 압축하는 개선된 MSFC 를 제시한다. 제안 방법은 VCM 의 Track2 의 영상 앵커(image anchor) 보다 우수한 BPP-mAP 성능을 보이고 최대 -84.98%의 BD-rate 성능향상을 보인다.

• Korean Journal of Cognitive Science
• /
• v.7 no.1
• /
• pp.37-56
• /
• 1996

In this paper,we design a verifier for unconstrained handwritten numerals using structural feature analysis,and use it as a comnination algorithm for multiple recognizers.The existing combination algorithms mainly use learnings,statistical methods,or probabilistic methods without considering structural features of numerals.That is why they cannot recognize some numerals which human can identify clearly.To overcome the shortcomings,we design one-to-one verifiers which compare and analyze the relative structural features between frequently confused numeral pairs,and apply them to combine multiple recongnizers.Structural features for verification consist of contour,direction al chain code,polygonal approximation,and zero crossing number of horizontal/vertical projections. We gained a 97.95% reliability with CENPARMI numeral data,and showed that some misconceived factors generated from typical combination algorithms can be removed.

• Nuclear Medicine and Molecular Imaging
• /
• v.42 no.2
• /
• pp.153-163
• /
• 2008

Medical imaging modalities to image either anatomical structure or functional processes have developed along somewhat independent paths. Functional images with single photon emission computed tomography (SPECT) and positron emission tomography (PET) are playing an increasingly important role in the diagnosis and staging of malignant disease, image-guided therapy planning, and treatment monitoring. SPECT and PET complement the more conventional anatomic imaging modalities of computed tomography (CT) and magnetic resonance (MR) imaging. When the functional imaging modality was combined with the anatomic imaging modality, the multimodality can help both identify and localize functional abnormalities. Combining PET with a high-resolution anatomical imaging modality such as CT can resolve the localization issue as long as the images from the two modalities are accurately coregistered. Software-based registration techniques have difficulty accounting for differences in patient positioning and involuntary movement of internal organs, often necessitating labor-intensive nonlinear mapping that may not converge to a satisfactory result. These challenges have recently been addressed by the introduction of the combined PET/CT scanner and SPECT/CT scanner, a hardware-oriented approach to image fusion. Combined PET/CT and SPECT/CT devices are playing an increasingly important role in the diagnosis and staging of human disease. The paper will review the development of multi modality instrumentations for clinical use from conception to present-day technology and the application software.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.6
• /
• pp.679-686
• /
• 2020

In this thesis, an enhanced method for the feature extraction of vocal source signals and score combination using an MCE-Based weight estimation of the score of multiple feature vectors are proposed for the performance improvement of speaker recognition systems. The proposed feature vector is composed of perceptual linear predictive cepstral coefficients, skewness, and kurtosis extracted with lowpass filtered glottal flow signals to eliminate the flat spectrum region, which is a meaningless information section. The proposed feature was used to improve the conventional speaker recognition system utilizing the mel-frequency cepstral coefficients and the perceptual linear predictive cepstral coefficients extracted with the speech signals and Gaussian mixture models. In addition, to increase the reliability of the estimated scores, instead of estimating the weight using the probability distribution of the convectional score, the scores evaluated by the conventional vocal tract, and the proposed feature are fused by the MCE-Based score combination method to find the optimal speaker. The experimental results showed that the proposed feature vectors contained valid information to recognize the speaker. In addition, when speaker recognition is performed by combining the MCE-based multiple feature parameter scores, the recognition system outperformed the conventional one, particularly in low Gaussian mixture cases.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.404-411
• /
• 2018

This paper proposes a dolphin whistle mimicking underwater communication method using FSK (Frequency Shift Keying) and method to improve BER (Bit Error Rate) performance by using multipath gain combining. The proposed method divides whistle sound into short time intervals and transmits FSK modulated signal that ensures orthogonality of the symbol. Multipath gain can be obtained by using characteristic of mimicked signal frequency that varies with time. To demonstrate the performance of the proposed method, computer simulations and lake experiments were conducted. Computer simulation results show that an additional multipath gain is obtained by multipath. From lake experiments, when symbol length is 20 msec and modulation band is 900 Hz, the proposed FSK method with multipath combining gain obtains BER of 0.002, which is better than CSS (Chirp Spread Spectrum) with BER of 0.185. he proposed based on FSK method has higher imitation degree than the CSS method by analyzing mean cross-correlation value in the time - frequency domain of the imitated signal and actual whistle signal.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.4
• /
• pp.259-265
• /
• 2016

In this paper, new method was proposed to classify lung tissues such as Broncho vascular, Emphysema, Ground Glass Reticular, Ground Glass, Honeycomb, Normal for early lung disease detection. 459 Statistical features was extraced from joint histogram matrix based on multi resolution analysis, volumetric LBP, and CT intensity, then dominant features was selected by using adaboost learning. Accuracy of proposed features and 3D AMFM was 90.1% and 85.3%, respectively. Proposed joint histogram based features shows better classification result than 3D AMFM in terms of accuracy, sensitivity, and specificity.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.60-62
• /
• 1999

다중 클래스 문서분류는 주어진 여러 개의 관심사별로 문서를 선별해 주는 문제이다. 문서 분류 문제의 특징은 문서가 매우 높은 차원으로 표현된다는 것이다. 다른 학습 알고리즘에 비해 SVM 알고리즘은 차원을 전혀 줄이지 않고 문제를 해결한다. 본 논문에서는 SVM 학습 알고리즘을 이용하여 대규모의 뉴스 그룹 문서 분류 문제를 다룬다. 다중 클래스 문서 분류를 위해서 각 클래스에 대한 SVM학습 결과를 효과적으로 결합하였으며 실험을 통하여 SVM과 다른 학습 알고리즘과의 성능을 비교하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.450-453
• /
• 2003

본 논문에서는 멀티모달 생체인식 시나리오 중에서, 단일 생체 특징에 적용되는 다중 획득 및 매칭이 시스템 성능에 기여하는 효과에 대하여 논의한다. 얼굴이라는 단일 생체 검중 시스템에 본 논문에서 제안한 간단한 다중 획득 및 매칭 결합 방법론들을 적용하였고, 실제적인 평가모델과 데이터베이스를 구축하여 이를 실험하고 결과를 분석하였다 실험결과, 단일 획득 및 매칭 시스템보다 25％ 가량 향상된 우수한 성능을 나타냈으며, 이는 얼굴 검증 시스템 구축에 있어 반드시 고려되어야 할 사항 중에 하나임을 보여준다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.5 s.305
• /
• pp.103-114
• /
• 2005

This paper presents a content-based image retrieval (CBIR) method using the combination of color and texture features. As a color feature, a color autocorrelogram is chosen which is extracted from the hue and saturation components of a color image. As a texture feature, BDIP(block difference of inverse probabilities) and BVLC(block variation of local correlation coefficients) are chosen which are extracted from the value component. When the features are extracted, the color autocorrelogram and the BVLC are simplified in consideration of their calculation complexity. After the feature extraction, vector components of these features are efficiently quantized in consideration of their storage space. Experiments for Corel and VisTex DBs show that the proposed retrieval method yields 9.5% maximum precision gain over the method using only the color autucorrelogram and 4.0% over the BDIP-BVLC. Also, the proposed method yields 12.6%, 14.6%, and 27.9% maximum precision gains over the methods using wavelet moments, CSD, and color histogram, respectively.