• 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.

• 한국수산과학회지
• /
• 제42권4호
• /
• pp.316-321
• /
• 2009

This study was conducted to improve the fish odor of extracts obtained from salmon frame. Salmon frame extracts were prepared using four kinds of pretreated salmon frame (salmon frame soaked in soybean milk and fried salmon frame) or containing additives (cystine and xylose-added salmon frame, and methionine and xylose-added salmon frame). Among the extracts prepared in this study, extracts containing cystine and xylose had the highest volatile component intensity and odor sensory score. These suggested that the fish odor of salmon frame extracts can be reduced by adding cystine and xylose before extraction.

• 한국식품영양과학회지
• /
• 제36권12호
• /
• pp.1596-1603
• /
• 2007

연어 frame 추출물에 대하여 건강 기능성 개선을 위하여 4종의 상업적 효소(Alcalase, Flavourzyme, Neutrase 및 Protamex) 처리에 의한 건강 기능성 연어 frame 가수분해물의 개발을 시도하였다. 연어 frame 가수분해물의 ACE 저해능($IC_{50}$)은 Neutrase로 4시간 처리한 가수분해물이 0.67 mg/mL로 가장 우수하였으나, 항산화성은 기대 이하의 범위(15% 이하)이었다. Neutrase 처리 연어 frame 가수분해물은 무처리 추출물에 비하여 일반성분과 관능적 특성(비린내 및 맛)에 있어서 차이가 없었으나 추출물 질소 함량은 높았고, 투과도는 개선되었다. 효소처리 연어 frame 가수분해물은 축육과 뼈로 제조한 시판 곰탕에 비하여 단백질 함량, 추출물 질소, 구성아미노산과 칼슘 함량이 높았고, 투과도, 관능적 비린내 등에서는 차이가 없었으며, 추후 조미 등에 의하여 보강 가능한 관능적 맛은 기호도에 있어 약간 차이가 있었다. 이상의 결과로 미루어 보아 연어 frmae 추출물에 Neutrase로 4시간 처리함으로 인하여 투과도와 ACE 저해능과 같은 건강 기능성은 기대할 수 있으리라 판단된다.

• 말소리와 음성과학
• /
• 제11권4호
• /
• pp.89-96
• /
• 2019

본 논문에서는 방송 콘텐츠에서 음성 구간 검출을 효과적으로 할 수 있는 심층 학습 모델 구조를 제안한다. 또한 특징 벡터의 시간적 변화를 학습하기 위한 다중 스케일 시간 확장 합성곱 층을 제안한다. 본 논문에서 제안한 모델의 성능을 검증하기 위하여 여러 개의 비교 모델을 구현하고, 프레임 단위의 F-score, precision, recall을 계산하여 보여 준다. 제안 모델과 비교 모델은 모두 같은 학습 데이터로 학습되었으며, 모든 모델은 다양한 장르(드라마, 뉴스, 다큐멘터리 등)로 구성되어 있는 한국 방송데이터 32시간을 이용하여 모델을 학습되었다. 제안 모델은 한국 방송데이터에서 F-score 91.7%로 가장 좋은 성능을 보여주었다. 또한 영국과 스페인 방송 데이터에서도 F-score 87.9%와 92.6%로 가장 높은 성능을 보여주었다. 결과적으로 본 논문의 제안 모델은 특징 벡터의 시간적 변화를 학습하여 음성 구간 검출 성능 향상에 기여할 수 있었다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.26-30
• /
• 2019

This paper proposes a new voice activity detection (VAD) method which is based on SNR and non-intrusive speech intelligibility estimation. In the conventional SNR-based VAD methods, voice activity probability is obtained by estimating frame-wise SNR at each spectral component. However these methods lack performance in various noisy environments. We devise a hybrid VAD method that uses non-intrusive speech intelligibility estimation as well as SNR estimation, where the speech intelligibility score is estimated based on deep neural network. In order to train model parameters of deep neural network, we use MFCC vector and the intrusive speech intelligibility score, STOI (Short-Time Objective Intelligent Measure), as input and output, respectively. We developed speech presence measure to classify each noisy frame as voice or non-voice by calculating the weighted average of the estimated STOI value and the conventional SNR-based VAD value at each frame. Experimental results show that the proposed method has better performance than the conventional VAD method in various noisy environments, especially when the SNR is very low.

• 한국멀티미디어학회논문지
• /
• 제5권5호
• /
• pp.512-522
• /
• 2002

본 논문에서는 GMM(Gaussian Mixture Model)에 기반한 실시간문맥독립화자식별시스템[1][2]의 성능향상을 위하여 프레임선택(Frame Selection)방법과 프레임가중치(Weighting Model Rank)방법을 혼합한 hybrid방법을 제안한다. 본 시스템에서는 GMM의 파라미터를 최적화하기 위하여 MLE(Maximum likelihood estimation)방법과 인식 알고리즘으로 ML(Maximum Likelihood)을 기본적으로 사용하였다. 제안한 hybrid 방법은 두 단계로 이루어진다. 첫째, 화자모델과 테스트 데이터를 이용하여 프레임단위로 유사도를 계산하고, 가장 큰 유사도 값과 두 번째로 큰 유사도 값의 차를 계산한 후, 차가 문턱치보다 큰 프레임만을 선택한다 두 번째로, 선택되어진 프레임에서 계산되어진 유사도 값 대신에 가중치 값을 사용하여 전체 스코어를 계산한다. 특징 파라미터로서는 켑스트럼과 회귀계수를 사용하였으며, 학습과 테스트를 위한 데이터베이스는 채집기간이 다른 여러 데이터베이스들로 구성되어 있으며, 실험을 위한 데이터는 임의의 단어를 선택하여 사용하였다. 화자인식실험은 기본 시스템에 프레임선택방법, 프레임가중치방법, 제안한 Hybrid방법을 각각 적용하여 실험하였다. 실험결과, 프레임선택방법에 비해 평균 4%, 프레임가중치방법에 비해 평균 1%의 인식률 향상을 보여, 본 논문에서 적용한 hybrid방법의 유효성을 확인하였다.

• 대한가정학회지
• /
• 제40권5호
• /
• pp.15-24
• /
• 2002

The following research conclusions were made, relative to the experiments of the textiles of fire fighters Protective Clothing. 1. When the body protection efficiency such as the thickness, the strength and heat resistance are considered, Nomex(N) is tuned out the best outer shelf, Gore-tex(KG) the best moisture barrier, and Wool-felt(WC) the best thermal barrier. 2. In the hygienic and sanitary efficiency also, N is turned out the best outer shelf, KG the best moisture barrier, and WC the best thermal barrier in its degree of water resistance, water vapour permeability, and air permeability. 3. In the washing and maintenance efficiency, too. N is turned out the best outer shell, KG the best moisture barrier, and WC the best thermal barrier, being considered the material's rate of contraction, the changing rate of frame resistance, water resistance, and water vapour permeability. 4. When considered the frame resistance against the reflection tape and reflection efficiency, O is the best material for it marks the highest score in the frame resistance and reflective effect.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권1호
• /
• pp.69-78
• /
• 2015

A non-traditional forage-based protocol was employed to evaluate replacement heifer growth, fertility, and economics between small frame (SF, 3.50; n = 50) and large frame (LF, 5.56; n = 50) heifers using three increasing gain growth phases. Preceding an 85 d growing-breeding period (Phase 3; P3) the heifers were managed as a common group for Phases 1 and 2 (P1 and P2). During P1, heifers grazed common fields of unharvested corn and corn residue (total digestible nutrients [TDN] 56%) with supplemental hay. For P2, heifers grazed early spring crested wheatgrass pasture (CWG; TDN 62%) that was followed by the final P3 drylot growing and breeding period (TDN 68%). Small frame heifers were lighter at the end of P1 in May and at the start of P3 breeding in August (p = 0.0002). Percent of mature body weight (BW) at the end of P1 (209 d) was 48.7% and 46.8%, respectively, for the SF and LF heifers and the percent pubertal was lower for SF than for LF heifers (18.0% vs 40.0%; p = 0.02). At breeding initiation (P3), the percentage of mature BW was 57.8 and 57.2 and the percentage pubertal was 90.0 and 96.0 (p = 0.07) for the SF and LF heifers, respectively; a 5-fold increase for SF heifers. Breeding cycle pregnancy on days 21, 42, and 63, and total percent pregnant did not differ (p>0.10). In drylot, SF heifer dry matter intake (DMI) was 20.1% less (p = 0.001) and feed cost/d was 20.3% lower (p = 0.001), but feed cost/kg of gain did not differ between SF and LF heifers (p = 0.41). Economically important live animal measurements for muscling were measured in May and at the end of the study in October. SF heifers had greater L. dorsi muscle area per unit of BW than LF heifers (p = 0.03). Small frame heifer value was lower at weaning (p = 0.005) and the non-pregnant ending heifer value was lower for SF heifers than for the LF heifers (p = 0.005). However, the total development cost was lower for SF heifers (p = 0.001) and the net cost per pregnant heifer, after accounting for the sale of non-pregnant heifers, was lower for SF heifers (p = 0.004). These data suggest that high breeding efficiency can be attained among March-April born SF and LF virgin heifers when transitioned to a more favorable May-June calving period through the strategic use of grazed and harvested forages resulting in a lower net cost per pregnant SF heifer.

• 한국음향학회지
• /
• 제21권8호
• /
• pp.735-743
• /
• 2002

본 논문에서는 세 가지 문맥독립 화자식별방법을 제안한다. 먼저, 화자 식별시 성도의 특성을 충분히 표현하지 못한 프레임이 포함되지 않도록 하는 프레임선택 (Frame Selection; FS)방법을 제안한다. 이 방법은 각 프레임에서 가장 큰 유사도와 두 번째로 큰 유사도의 차이를 평가하여 중요 프레임을 선택한 후, 선택된 프레임만을 이용하여 유사도를 계산하는 방법이다. 두 번째로 제안하는 복합 (Hyrid)방법은 FS와 가중모델순위 (Weighting Model Rank: WMR)방법을 결합시킨 것으로, FS방법을 이용하여 중요 프레임을 선택한 후, 지수함수 가중치를 이용하여 식별화자를 결정하는 것이다. 마지막으로 제안하는 수정된 가중모델순위 (Modified WMR; MWMR)방법은 식별화자를 결정할 때 유사도의 상대적 위치만을 고려하였던 기존의 U방법과는 달리 유사도와 유사도의 상대적 위치를 함께 고려하는 방법이다. 화자식별 실험결과 제안한 방법들이 기존의 ML 방법보다 향상된 식별률을 보였으며, 복합 방법 및 MWMR방법의 경우에는 WMR방법보다 각각 약 2%와 3%의 향상된 식별률을 나타내어 제안한 방법들의 유효성을 확인할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.2053-2067
• /
• 2023

This paper proposes two video quality assessment methods based on deep neural network. (i)The first method uses the IQF-CNN (convolution neural network based on image quality features) to build image quality assessment method. The LIVE image database is used to test this method, the experiment show that it is effective. Therefore, this method is extended to the video quality assessment. At first every image frame of video is predicted, next the relationship between different image frames are analyzed by the hysteresis function and different window function to improve the accuracy of video quality assessment. (ii)The second method proposes a video quality assessment method based on convolution neural network (CNN) and gated circular unit network (GRU). First, the spatial features of video frames are extracted using CNN network, next the temporal features of the video frame using GRU network. Finally the extracted temporal and spatial features are analyzed by full connection layer of CNN network to obtain the video quality assessment score. All the above proposed methods are verified on the video databases, and compared with other methods.