• Title/Summary/Keyword: 추정 마스크

Search Result 66, Processing Time 0.024 seconds

Robust Head Pose Estimation for Masked Face Image via Data Augmentation (데이터 증강을 통한 마스크 착용 얼굴 이미지에 강인한 얼굴 자세추정)

  • Kyeongtak, Han;Sungeun, Hong
    • Journal of Broadcast Engineering
    • /
    • v.27 no.6
    • /
    • pp.944-947
    • /
    • 2022
  • Due to the coronavirus pandemic, the wearing of a mask has been increasing worldwide; thus, the importance of image analysis on masked face images has become essential. Although head pose estimation can be applied to various face-related applications including driver attention, face frontalization, and gaze detection, few studies have been conducted to address the performance degradation caused by masked faces. This study proposes a new data augmentation that synthesizes the masked face, depending on the face image size and poses, which shows robust performance on BIWI benchmark dataset regardless of mask-wearing. Since the proposed scheme is not limited to the specific model, it can be utilized in various head pose estimation models.

Bayesian Estimation of System & Component Reliability Using Masked Data (마스크 데이터를 이용한 베이지안 추정)

  • 김종걸;박창규
    • Proceedings of the Korean Reliability Society Conference
    • /
    • 2000.11a
    • /
    • pp.353-362
    • /
    • 2000
  • 다양한 컴포넌트들로 구성된 시스템의 수명 데이터는 시스템 컴포넌트들의 신뢰성을 추정하는데 많이 사용된다. 하지만 비용이나 고장진단의 기술적 문제 때문에 시스템 고장의 정확한 원인을 밝혀내기는 어렵다. 시스템이나 컴포넌트의 수명 데이터 중 정확한 고장원인을 알 수 없는 데이터를 마스크 데이터라 한다. 본 연구는 마스크데이터와 베이지안 추정의 연구방향을 살펴보고, 그리고 고장률의 비정보 사전분포를 이용하여, 컴포넌트가 직렬로 구성된 시스템의 수명 데이터가 마스크 데이터를 갖는 지수분포의 시스템 컴포넌트 고장률을 추정한다.

  • PDF

The future Research based on Reliability Analysis Using Masked Data (마스크 데이타를 이용한 신뢰성 분석의 연구방향)

  • 김종걸;박창규
    • Proceedings of the Safety Management and Science Conference
    • /
    • 2000.11a
    • /
    • pp.53-62
    • /
    • 2000
  • 다양한 컴포넌트들로 구성된 시스템의 수명 데이터는 시스템 컴포넌트들의 신뢰성을 추정하는데 많이 사용된다. 하지만 비용이나 고장진단의 기술적 문제 때문에 시스템 고장의 정확한 원인을 밝혀내기는 어렵다. 시스템이나 컴포넌트의 수명 데이터 중 정확한 고장원인을 알 수 없는 데이터를 마스크 데이터라 한다. 본 연구는 마스크데이터와 베이지안 추정의 연구방향을 살펴보고, 그리고 고장률의 비정보 사전분포를 이용하여, 컴포넌트가 직렬로 구성된 시스템의 수명 데이터가 마스크 데이터를 갖는 지수분포의 시스템 컴포넌트 고장률을 추정 한다.

  • PDF

Binary Mask Estimation using Training-based SNR Estimation for Improving Speech Intelligibility (음성 명료도 향상을 위한 학습 기반의 신호 대 잡음 비 추정을 이용한 이산 마스크 추정 방법)

  • Kim, Gibak
    • Journal of Broadcast Engineering
    • /
    • v.17 no.6
    • /
    • pp.1061-1068
    • /
    • 2012
  • This paper deals with a noise reduction algorithm which uses the binary masking approach in the time-frequency domain to improve speech intelligibility. In the binary masking approach, the noise-corrupted speech is decomposed into time-frequency units. Noise-dominant time-frequency units are removed by setting the corresponding binary masks as "0"s and target-dominant units are retained untouched by assigning mask "1"s. We propose a binary mask estimation by comparing the local signal-to-noise ratio (SNR) to a threshold. The local SNR is estimated by a training-based approach. An optimal threshold is proposed, which is obtained from observing the distribution of the training database. The proposed method is evaluated by normal-hearing subjects and the intelligibility scores are computed by counting the number of words correctly recognized.

A Study on Edge Detection Algorithm using Estimated Mask in Impulse Noise Environments (임펄스 잡음 환경에서 추정 마스크를 이용한 에지 검출 알고리즘에 관한 연구)

  • Lee, Chang-Young;Kim, Nam-Ho
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.18 no.9
    • /
    • pp.2259-2264
    • /
    • 2014
  • For edge detection methods, there are Sobel, Prewitt, Roberts and Canny edge detector, and these methods have insufficient detection characteristics in the image corrupted by the impulse noise. Therefore in this paper, in order to improve these disadvantages of the previous methods and to effectively detect the edge in the impulse noise environment, using the $5{\times}5$ mask, the noise factors within the $3{\times}3$ mask based on the central pixel is determined, and depending on its status, for noise-free it is processed as is, and if noise is found, by obtaining the estimated mask using the adjacent pixels of each factor, an algorithm that detects the edge is proposed.

A Post-processing for Binary Mask Estimation Toward Improving Speech Intelligibility in Noise (잡음환경 음성명료도 향상을 위한 이진 마스크 추정 후처리 알고리즘)

  • Kim, Gibak
    • Journal of Broadcast Engineering
    • /
    • v.18 no.2
    • /
    • pp.311-318
    • /
    • 2013
  • This paper deals with a noise reduction algorithm which uses the binary masking in the time-frequency domain. To improve speech intelligibility in noise, noise-masked speech is decomposed into time-frequency units and mask "0" is assigned to masker-dominant region removing time-frequency units where noise is dominant compared to speech. In the previous research, Gaussian mixture models were used to classify the speech-dominant region and noise-dominant region which correspond to mask "1" and mask "0", respectively. In each frequency band, data were collected and trained to build the Gaussian mixture models and detection procedure is performed to the test data where each time-frequency unit belongs to speech-dominant region or noise-dominant region. In this paper, we consider the correlation of masks in the frequency domain and propose a post-processing method which exploits the Viterbi algorithm.

A study on combination of loss functions for effective mask-based speech enhancement in noisy environments (잡음 환경에 효과적인 마스크 기반 음성 향상을 위한 손실함수 조합에 관한 연구)

  • Jung, Jaehee;Kim, Wooil
    • The Journal of the Acoustical Society of Korea
    • /
    • v.40 no.3
    • /
    • pp.234-240
    • /
    • 2021
  • In this paper, the mask-based speech enhancement is improved for effective speech recognition in noise environments. In the mask-based speech enhancement, enhanced spectrum is obtained by multiplying the noisy speech spectrum by the mask. The VoiceFilter (VF) model is used as the mask estimation, and the Spectrogram Inpainting (SI) technique is used to remove residual noise of enhanced spectrum. In this paper, we propose a combined loss to further improve speech enhancement. In order to effectively remove the residual noise in the speech, the positive part of the Triplet loss is used with the component loss. For the experiment TIMIT database is re-constructed using NOISEX92 noise and background music samples with various Signal to Noise Ratio (SNR) conditions. Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI) are used as the metrics of performance evaluation. When the VF was trained with the mean squared error and the SI model was trained with the combined loss, SDR, PESQ, and STOI were improved by 0.5, 0.06, and 0.002 respectively compared to the system trained only with the mean squared error.

A Study on Median Filter using Estimated Mask on the Image Degraded by Salt and Pepper Noise (Salt and Pepper 잡음에 훼손된 영상에서 추정 마스크를 이용한 메디안 필터에 관한 연구)

  • Hong, Sang-Woo;Hwang, Yeong-Yeun;Kim, Nam-Ho
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2015.05a
    • /
    • pp.932-935
    • /
    • 2015
  • Recently, the image system is utilized in several fields due to the development of multimedia technology. However, the noise occurs according to various causes in the process of image data processing. The noises added to the image include several types according to the cause and shape, and the salt and pepper noise is one of the typical noise types. Thus, this paper proposed the median filter algorithm using the estimated mask in order to remove the salt and pepper noise effectively and also compared this algorithm with the current methods using PSNR(peak signal to noise ratio) as a criterion of judgment.

  • PDF

Measuring Willingness to Pay for PM10 Risk Reductions: Evidence from Averting Expenditures for Anti-PM10 Masks and Air Purifiers (미세먼지 건강위험 감소에 대한 지불의사 측정: 마스크 착용과 공기청정기 사용에 따른 회피비용을 중심으로)

  • Eom, Young Sook;Kim, Jin Ok;Ahn, So Eun
    • Environmental and Resource Economics Review
    • /
    • v.28 no.3
    • /
    • pp.355-383
    • /
    • 2019
  • This study is to investigate whether averting costs for wearing $anti-PM_{10}$ masks and using air purifiers at home to reduce exposure from $PM_{10}$ are influenced by subjective risk perceptions and/or objective $PM_{10}$ concentration levels, whose estimates will be used to measure the willingness to pay for $PM_{10}$ risk reduction. An empirical analysis was conducted on a sample of 1,224 respondents who participated in the web-based survey in the late October of 2017. As we reflect the potential endogeniety bias in the estimation of averting cost functions of using air purifiers, the coefficients of risk perception were differed by 6~7 times. Respondents. subjective risk perceptions were influenced by individuals' knowledge, attitudes and demographic variables, as well as the levels of $PM_{10}$ concentrations in their residential region. The marginal willingness to pay for risk reductions at the mean levels of their risk perceptions were measured at 1,000 won per month from wearing $anti-PM_{10}$ masks and 6,000 won for using air purifiers respectively.

Superresolution Restoration From Directional Rectangular Blurred Images (방향성 직사각형 열화 영상을 사용한 초해상도 영상복원)

  • Shin, Jeongho
    • Journal of Broadcast Engineering
    • /
    • v.19 no.1
    • /
    • pp.109-117
    • /
    • 2014
  • This paper presents a superresolution restoration technique that can restore high-resolution images from differently blurred low resolution images rather than using the motion information between low-resolution images. In order to restore the super-resolution image the rotatable aperture mask lens system is proposed. The proposed technique does not need to estimate point spread function at each frame. In addition, it does not require image registration because there is no global translational motion between low resolution images. By using a rotatable rectangular aperture, two consecutive captured images provide sufficiently exclusive information for superresolution. Therefore, the proposed method can reduce the registration error between the low-resolution image as well as the calculation amount for superresolution restoration. The existing lens system of the camera can be extended to obtain a superresolution image by only adding an rotatable rectangular aperture mask. Finally, in order to verify the performance of the proposed system, experimental results are performed. By comparing with the existing superresolution methods, the proposed method showed the significant improvements in the sense of spatial resolution.