• 음성과학
• /
• 제15권2호
• /
• pp.79-88
• /
• 2008

Recently demands for the speech technology-based products targeted for the mobile terminals such as cellular phones and PDA are rapidly increasing. And voting-based speaker identification algorithm is known to have a good performance in the mobile environment, since it works well with small amount of speaker training data. In this paper, we proposed a method to improve the performance of this voting based speaker identification system by using the observation confidence value which is derived from the function of SNR each frame. The proposed method is evaluated with ETRI cellular phone DB which is made for the speaker recognition task. The experimental results show that the proposed method has better performance of 2-3% identification rate than the conventional GMM method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권1호
• /
• pp.8-16
• /
• 2014

We consider the visual barcode recognition problem in a noisy video data setup. Unlike most existing single-frame recognizers that require considerable user effort to acquire clean, motionless and blur-free barcode signals, we eliminate such extra human efforts by proposing a robust video-based barcode recognition algorithm. We deal with a sequence of noisy blurred barcode image frames by posing it as an online filtering problem. In the proposed dynamic recognition model, at each frame we infer the blur level of the frame as well as the digit class label. In contrast to a frame-by-frame based approach with heuristic majority voting scheme, the class labels and frame-wise noise levels are propagated along the frame sequences in our model, and hence we exploit all cues from noisy frames that are potentially useful for predicting the barcode label in a probabilistically reasonable sense. We also suggest a visual barcode tracking approach that efficiently localizes barcode areas in video frames. The effectiveness of the proposed approaches is demonstrated empirically on both synthetic and real data setup.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2011년도 추계학술대회
• /
• pp.288-291
• /
• 2011

Video stabilization is an important image enhancement widely used in surveillance system in order to improve recognition performance. Most previous methods calculate inter-frame homography to estimate global motion. These methods are relatively slow and suffer from significant depth variations or multiple moving object. In this paper, we propose a fast and practical approach for video stabilization that selects the most reliable key frame as a reference frame to a current frame. We use optical flow to estimate global motion within an adaptively selected region of interest in static camera environment. Optimal global motion is found by probabilistic voting in the space of optical flow. Experiments show that our method can perform real-time video stabilization validated by stabilized images and remarkable reduction of mean color difference between stabilized frames.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권2호
• /
• pp.88-94
• /
• 2012

Many hand gesture recognition systems using advanced computer vision techniques to eliminate the need for a TV remote controller have been proposed. Nevertheless, some issues still remain, such as high computational complexity and insufficient information on the target object and background. Moreover, none of the proposed techniques consider how to enter the control mode of the system. This means that they may need a TV remote controller to enter the control mode. This paper proposes a hand mouse system using a pre-defined gesture with high background adaptability. By doing so, a remote controller to enter the control mode of the IPTV system can be eliminated.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제17권1호
• /
• pp.79-85
• /
• 2017

In this paper, several optimizations are proposed to enhance the quality of lane detection algorithms in automotive applications. Considering the diagonal directions of lanes, the proposed limited Hough transform newly introduces image-splitting and angle-limiting schemes that relax the number of possible angles at the line voting process. In addition, unnecessary edges along the horizontal and vertical directions are pre-defined and removed during the edge detection procedures, increasing the detecting accuracy remarkably. Simulation results shows that the proposed lane recognition algorithm achieves an accuracy of more than 90% and a computing speed of 92 frame/sec, which are superior to the results from the previous algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권3호
• /
• pp.193-197
• /
• 2012

This paper focuses on identifying which appliance is currently operating by analyzing electrical load signature for home energy monitoring system. The identification framework is comprised of three steps. Firstly, specific appliance features, or signatures, were chosen, which are DC (Duty Cycle), SO (Slope of On-state), VO (Variance of On-state), and ZC (Zero Crossing) by reviewing observations of appliances from 13 houses for 3 days. Five appliances of electrical rice cooker, kimchi-refrigerator, PC, refrigerator, and TV were chosen for the identification with high penetration rate and total operation-time in Korea. Secondly, K-NN and Naive Bayesian classifiers, which are commonly used in many applications, are employed to estimate from which appliance the signatures are obtained. Lastly, one of candidates is selected as final identification result by majority voting. The proposed identification frame showed identification success rate of 94.23%.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.67-90
• /
• 2019

Accurate detection, tracking and analysis of human movement using robots and other visual surveillance systems is still a challenge. Efforts are on to make the system robust against constraints such as variation in shape, size, pose and occlusion. Traditional methods of detection used the sliding window approach which involved scanning of various sizes of windows across an image. This paper concentrates on employing a state-of-the-art, hierarchical graph based method for segmentation. It has two stages: part level segmentation for color-consistent segments and object level segmentation for category-consistent regions. The tracking phase is achieved by employing SIFT keypoint descriptor based technique in a combined matching and tracking scheme with validation phase. Localization of human region in each frame is performed by keypoints by casting votes for the center of the human detected region. As it is difficult to avoid incorrect keypoints, a consensus-based framework is used to detect voting behavior. The designed methodology is tested on the video sequences having 3 to 4 persons.

• 방송공학회논문지
• /
• 제15권4호
• /
• pp.498-512
• /
• 2010

인트라 프레임 부호화 기술은 임의 접근성과 에러 확산 방지에 용이하기 때문에 비디오 부호화 기술의 필수적인 기술로 자리 잡고 있다. 그러나 인터 부호화 기술에 비해 낮은 부호화 효율이 문제점으로 지적되고 있다. H.264/AVC 인트라 부호화 방식은 기존 표준 방법들보다 부호화 효율을 크게 향상시켰지만 부호화 과정이 복잡하여 저 비트율 기반의 양방향 서비스에는 부적합하다. 따라서 본 논문에서는 복호화기 측의 예측을 이용해 인트라 부호화 효율을 보다 향상시키며 부호화 시간을 단축시키는 V-IMBS (Voting-based Intra Mode Bit Skip)를 제안한다. 제안하는 방법은 복호화기가 부호화기에서와 동일하게 최적의 인트라 예측 모드를 결정할 수 있으면 인트라 예측 모드를 전송하지 않는다. 그러나 최적의 인트라 예측 모드를 결정할 수 없을 경우에는 기존의 H.264/AVC 표준과 동일한 방식으로 인트라 예측 모드를 부호화하여 복호화기로 전송한다. V-IMBS는 H.264/AVC보다 시험 시퀀스에 대해 PSNR 값이 평균 약 0.24 dB 정도 향상되었고, 비트율도 평균 약 4.44% 정도 감소되었다. 또한 전체 부호화 시간도 평균 약 42.8% 정도 감소되었다.

• 한국콘텐츠학회논문지
• /
• 제21권1호
• /
• pp.105-118
• /
• 2021

본 연구의 목적은 가짜뉴스가 크고 작은 사회적 문제를 야기한다는 점에 주목하여, 전자투표시스템 관련 가짜뉴스가 뉴스 이용자의 시스템 이용에 대한 태도, 시스템을 통한 선거 참여 의도, 뉴스서비스 신뢰도에 어떠한 영향력을 미치는지 실험을 통해 확인하는데 있다. 연구결과, 부정적인 내용으로 프레임된 가짜뉴스는 이용자의 태도와 선거 참여 의도 수준을 감소시키는 효과를 보였다. 특히 각 뉴스서비스에 따른 가짜뉴스 영향력 차이를 검증한 결과, 이용자가 일반 인터넷신문을 통해 가짜뉴스에 노출되고 해당 뉴스가 가짜임을 인지한 경우에는 태도와 선거 참여 의도 수준이 감소 후 다시 회복되는 모습을 보였다. 하지만 네이버와 페이스북 가짜뉴스에 노출된 이용자들은 가짜뉴스에 담긴 부정적인 내용을 더욱 강하게 형성하는 것으로 나타났다. 가짜뉴스가 이용자의 인지적 차원에 영향력을 행사하고, 최초 노출 정보와 일치하는 방향으로 인식을 강화하려는 경향이 있다는 사실을 실증적으로 확인하였다.