• 한국빅데이터학회지
• /
• 제7권1호
• /
• pp.63-73
• /
• 2022

2020년부터 현재까지 COVID-19가 지속되고 있으며, 사회적으로도 많은 변화가 생겼다. 마스크를 착용하는 것은 필수가 되었고, 마스크 미착용 시, 공공시설이나 식당 등을 이용할 수 없게 되었다. 이로 인해 대부분의 공공시설 출입구에서는 마스크 인식 시스템을 구비하여 마스크 착용 여부를 확인하고 있다. 그러나 목도리로 입을 가린 사람이나 마스크를 제대로 착용하지 않은 사람 등에 대한 판별 여부가 불분명하다. 본 연구에서는 YOLOv5를 이용한 임베디드 마스크 인식 시스템을 제안하였다. 기존 마스크 인식 시스템과는 달리 마스크 착용 여부뿐만 아니라 목도리를 입으로 가린 사람, 손으로 입을 가린 사람 등 다양한 예외 상황에서도 마스크 착용 여부를 구별해낼 수 있었으며, Nvida Jetson Nano Board에 탑재하였을 때 우수한 성능을 보였다.

• 문화기술의 융합
• /
• 제4권4호
• /
• pp.361-366
• /
• 2018

학습 데이터를 구성하는 각각의 문자들에 대해 서로 다른 글자체들을 픽셀 단위로 더해서 MASK를 만들고, 해당 MASK에 속하는 픽셀값들을 세 영역으로 나눈다. 실험 데이터를 골격 형태로 수정하고, 지역 경계 연산을 사용하여 수정된 실험 데이터의 배경 중에서 문자의 골격에 인접한 배경 영역을 구분하는 경계를 만든다. 수정된 실험 데이터와 MASK들 간의 불일치 정도를 계산해서 최소값을 가지는 MASK를 찾는다. 이 MASK가 해당 실험 데이터에 대해 최종적으로 인식된 학습 데이터 문자로 선택된다. 문자의 골격과 지역 경계 연산을 사용하는 인식법은 주어진 학습 데이터에 새로운 글자체를 추가해서 학습 데이터를 쉽게 확장할 수 있으며, 구현하기가 간단하면서도 높은 문자 인식률을 얻을 수 있다.

• 한국안전학회지
• /
• 제33권6호
• /
• pp.28-36
• /
• 2018

There was a difference in recognition of respirators according to the educational performance environment. they were showed higher recognition of respirators of group by internal and external mix trainer, less than 6 months, over 1hour, more than 5 times, variety of education. To identify the relationship between types of job classification(typical and atypical)and the levels of recognition of respirators, a total of 153 workers in a business workplace. mainly, typical workers showed higher recognition of respirators than atypical workers. Training of correct wearing showed high demands both typical and atypical workers. Descriptive statistics(SAS ver 9.2)was performed. the results of recognition of respirators were analyzed the mean and standard deviation by t-test, and anova, fit factor is used geometric means(geometric standard deviation), paired t-test, Wilcoxon analysis(P=0.05). Particulate filtering facepiece respirators (PFFR) is one of the most widely used items of personal protective equipments, and a tight fit of the respirators on the wearers is critical for the protection effectiveness. In order to effectively protect the workers through the respirators, it is important to find and evaluate the ways that can be readily applicable at the workplace to improve the fit of the respirators. This study was designed to evaluate effects of mask style (cup or foldable type) and donning training on fit factors (FF) of the respirators, since these are available at various workplace, especially at small business workplace. A total of 40 study subjects, comprised of employment type workers in metalworking industries, were enrolled in this study. The FF were quantitatively measured before and after training related to the proper donning and use of cup or foldable-type respirators. The pass/fail criterion of FF was set at 100. After the donning training for the cup-type mask, fit test were increased by 769%. but foldable-type mask was also increased after the donning training, the GM of FF for the foldable-type mask and it's increase rate were smaller as compared to the cup-type mask. Furthermore, the differences of the increase rates of the GM of FF in employment type of the subjects were not significantly for the foldable-type mask. These results imply that the raining on the donning and use of PFFR can enhance the protection effectiveness of cup or foldable-type mask, and that the training effects for the foldable-type mask is less significant than that for the cup-type mask. Therefore, it is recommended that the donning training and fit tests should be conducted before the use of the PFFR, and listening to workers opinion regularly.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.411-427
• /
• 2022

Digging historical and cultural information from seals in ancient books is of great significance. However, ancient Chinese seal samples are scarce and carving methods are diverse, and traditional digital image processing methods based on greyscale have difficulty achieving superior segmentation and recognition performance. Recently, some deep learning algorithms have been proposed to address this problem; however, current neural networks are difficult to train owing to the lack of datasets. To solve the afore-mentioned problems, we proposed an SEL-RefineMask which combines selector of feature pyramid network (SEL-FPN) with RefineMask to segment and recognize seals. We designed an SEL-FPN to intelligently select a specific layer which represents different scales in the FPN and reduces the number of anchor frames. We performed experiments on some instance segmentation networks as the baseline method, and the top-1 segmentation result of 64.93% is 5.73% higher than that of humans. The top-1 result of the SEL-RefineMask network reached 67.96% which surpassed the baseline results. After segmentation, a vision transformer was used to recognize the segmentation output, and the accuracy reached 91%. Furthermore, a dataset of seals in ancient Chinese books (SACB) for segmentation and small seal font (SSF) for recognition were established which are publicly available on the website.

• International Journal of Advanced Culture Technology
• /
• 제6권2호
• /
• pp.123-128
• /
• 2018

Learning data is composed of 100 characters with 10 different fonts, and test data is composed of 10 characters with a new font that is not used for the learning data. In order to consider the variety of learning data with several different fonts, 10 learning masks are constructed by accumulating pixel values of same characters with 10 different fonts. This process eliminates minute difference of characters with different fonts. After finding maximum values of learning masks, test data is expanded by multiplying these maximum values to the test data. The algorithm calculates sum of differences of two corresponding pixel values of the expanded test data and the learning masks. The learning mask with the smallest value among these 10 calculated sums is selected as the result of the recognition process for the test data. The proposed algorithm can recognize various types of fonts, and the learning data can be modified easily by adding a new font. Also, the recognition process is easy to understand, and the algorithm makes satisfactory results for character recognition.

• 한국화재소방학회논문지
• /
• 제19권4호
• /
• pp.64-68
• /
• 2005

본 논문에서는 방범 및 보안설비로 설치된 CCD카메라로 화재가 발생한 지역의 영상을 획득하였을 때, 빠른시간 안에 화재 발생위치를 인식하고 경보를 발령할 수 있는 시스템을 연구하였다. 화재발생 지역 중 불꽃부위만을 효과적으로 추출할 수 있는 방법으로 RED Filtering법을 제안하였고, 불꽃부위 경계를 추출하기 위하여 2치 영상기법을 적용하였으며, Mask추출과 정합을 이용하여 화재가 발생한 위치 및 지역을 인식할 수 있도록 하였다. 실험결과, 불꽃과 복잡한 경계부분도 효과적으로 추출되었으며 원영상과의 정합을 통해 화재 발생위치를 효과적으로 인식하여 제안한 알고리즘의 타당성을 확인하였다

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권11호
• /
• pp.5605-5623
• /
• 2016

We propose a face recognition method that utilizes the LCP face descriptor. The proposed method applies a LoG mask to extract a face contour response, and employs the LCP algorithm to produce a binary pattern representation that ensures high recognition performance even under the changes in illumination, noise, and aging. The proposed LCP algorithm produces excellent noise reduction and efficiency in removing unnecessary information from the face by extracting a face contour response using the LoG mask, whose behavior is similar to the human eye. Majority of reported algorithms search for face contour response information. On the other hand, our proposed LCP algorithm produces results expressing major facial information by applying the threshold to the search area with only 8 bits. However, the LCP algorithm produces results that express major facial information with only 8-bits by applying a threshold value to the search area. Therefore, compared to previous approaches, the LCP algorithm maintains a consistent accuracy under varying circumstances, and produces a high face recognition rate with a relatively small feature vector. The test results indicate that the LCP algorithm produces a higher facial recognition rate than the rate of human visual's recognition capability, and outperforms the existing methods.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.255-263
• /
• 2022

3D object detection pipelines often incorporate RGB-based object detection methods such as YOLO, which detects the object classes and bounding boxes from the RGB image. However, in complex environments where objects are heavily cluttered, bounding box approaches may show degraded performance due to the overlapping bounding boxes. Mask based methods such as Mask R-CNN can handle such situation better thanks to their detailed object masks, but they require much longer time for data preparation compared to bounding box-based approaches. In this paper, we present a 3D object recognition pipeline which uses either the YOLO or Mask R-CNN real-time object detection algorithm, K-nearest clustering algorithm, mask reduction algorithm and finally Principal Component Analysis (PCA) alg orithm to efficiently detect 3D poses of objects in a complex environment. Furthermore, we also present an improved YOLO based 3D object detection algorithm that uses a prioritized heightmap clustering algorithm to handle overlapping bounding boxes. The suggested algorithms have successfully been used at the Artificial-Intelligence Robot Challenge (ARC) 2021 competition with excellent results.

• 융합정보논문지
• /
• 제9권6호
• /
• pp.233-241
• /
• 2019

본 연구는 수도권에 거주하는 20~30대 여성을 대상으로 마스크팩 인식 및 구매 행동에 대하여 설문지를 이용하여 조사하였다. 본 연구 결과, 연구 대상자들은 피부미용에 대한 관심이 높지만 마스크팩 타입에 따른 특징과 차별성 인식은 미흡한 것으로 조사되었다. 마스크팩을 사용한 후, 조사 대상자들의 51.1%가 효능 효과에 만족한 것으로 조사되었으나, 마스크팩 사용 시 대표적인 불편한 점으로는 시트형 마스크팩은 사용성, 크기, 밀착성 및 피부 자극으로 불만족스러웠으며, 하이드로 겔타입의 소재와 슬리밍 타입은 내용물, 흡수성에 대해 불만족스러운 것으로 확인되었다. 또한, 셀룰로오스 팩과 하이드로겔 타입의 팩은 동일하게 불쾌감을 가지는 것으로 확인되었다. 본 연구 결과를 통하여 마스크팩 시장의 기초 마케팅 자료로서 활용이 가능할 것으로 사료되어 진다.

• 한국인터넷방송통신학회논문지
• /
• 제10권5호
• /
• pp.179-185
• /
• 2010

본 논문에서는 특징 되먹임 알고리즘의 성능을 평가하기위해 특징되먹임 알고리즘의 성능에 가장 큰 영향을 주는 특징마스크를 검증한다. 특징 되먹임 기반 패턴 인식 방법은 PCALDA로 추출된 특징을 원 영역으로 역사상하여 인식에 중요한 부분을 추출하는 기법이다. 추출된 특징은 특징마스크의 형태로 원 영역으로 역사상 되므로, 특징마스크의 특징성능 검증에 대한 연구가 필수적이다. 본 논문에서는 Yale data 기반의 얼굴 인식에서 특징마스크를 검출하여 특징마스크에 따른 인식률 변화를 고찰하고 검출된 특징마스크의 성능을 검증한다.