• The KIPS Transactions:PartB
• /
• 제9B권6호
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• Journal of Food Hygiene and Safety
• /
• 제34권5호
• /
• pp.421-430
• /
• 2019

In this study, 195 pesticide residues in fruit samples (n=150) at local markets in Chungcheongnam-do Chungnam, Korea were monitored using a multi-residue method combined with GC-MS/MS and LCMS/MS. Among 150 fruit samples, 40 types of pesticides were detected in 63 samples and the detection rate was 42.0%. However, the amounts were below the maximum residue limit (MRL). Detection rates for pesticides in each thpe of fruit were as follows ; citrus fruits (55.2%), pome fruits (41.3%), berries (38.7%) and stone fruits (36.0%). Although the sample size was small (n=2), pesticide residues were not detected in tropical fruits. Occurrences of detection of pesticide residues in apple showed the highest level, and mainly, insecticides were detected most frequently. The most commonly detected pesticides residues were bifenthrin (21), pyraclostrobin (17), novaluron (13), boscalid (10), chlorfenapyr (9), trifloxystrobin (9), furathiocarb (9), acetamiprid (8) and chlorpyrifos (8). Five types of residual pesticides (bifenthrin, chlorfenapyr, deltamethrin, fenpropathrin and fenvalerate) were detected in quince, and out of these five, fenpropathrin exceeded the MRL based on the Positive List System (PLS). These results suggested that pesticide residues in fruit samples should be continuously monitored, although residue levels in 63 other fruit samples were evaluated as being within a safe level.

• Journal of Korea Multimedia Society
• /
• 제15권5호
• /
• pp.577-586
• /
• 2012

The smartphone emerged due to the rapid development of the Internet has brought greater convenience to life in a positive manner. Recently, however, because of unconstrained exposure to harmful video, reckless use of smart phones has become a domestic issue in our society. In this paper, a service which detects harmful videos by using the acoustic information is designed and implemented on the Android OS. In order to implement the service of Android OS-based detection of the harmful movie, the speed of existing sound-based detection method for harmful videos is improved. The GMM(Gaussian Mixture Model) was used for classifier and the number of Gaussian Mixture was 18. The implemented service shows a detection rate of 97.02% for a total of 1,210 data files (approximately 687 hours) which comprises 669 general videos files (about 424 hours) and 541 harmful video files (about 263 hours). It's speed is 5.6 times faster than the traditional methods whitout reducing the detection rate.

• Journal of IKEEE
• /
• 제24권1호
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• Journal of Software Assessment and Valuation
• /
• 제16권2호
• /
• pp.153-162
• /
• 2020

Digital image forgery detection is one of very important fields in the field of digital forensics. As the forged images change naturally through the advancement of technology, it has made it difficult to detect forged images. In this paper, we use passive forgery detection for copy paste forgery in digital images. In addition, it detects copy-paste forgery using the L₀ Norm-based LE operator, and compares the detection accuracy with the forgery detection using the existing L₂, L₁ Norm-based LE operator. In comparison of detection rates, the proposed lower triangular(Ayalneh and Choi) window was more robust to BAG mismatch detection than the conventional window filter. In addition, in the case of using the lower triangular window, the performance of image forgery detection was measured increasingly higher as the L₂, L₁ and L₀ Norm LE operator was performed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.301-304
• /
• 2000

본 논문에서는 디지털 영상에서 얼굴 영상 검출을 위해 픽셀의 퍼지 소속도를 이용하여 신경망으로 학습하는 퍼지 신경망을 이용한 얼굴영상 검출을 제안한다. 입력 영상의 피라미드 영상에서 추출된 20$\times$20 윈도우 템플릿 영상안의 각 픽셀의 소속도로 얼굴 영상 패턴을 학습하여 얼굴 영상을 검출하는 방법은 단순히 영상의 픽셀 값 하나씩만을 고려해서 각 픽셀의 소속도를 고려하여 수행하는 얼굴 영상 분할보다 얼굴 영상을 훨씬 더 정확하고 인식률이 높게 검출해 낼 수 있다.

• Information and Communications Magazine
• /
• 제29권4호
• /
• pp.10-14
• /
• 2012

본고에서는 스마트폰 환경에서 음성 통신에 필요한 가변 전송률 음성 부호화기를 위한 음성 검출 기술을 알아본다. 소개할 음성 검출 기술은 통계적 모델(statistical model)을 기반으로 한 우도비 테스트(likelihood ratio test, LRT)를 이용하여 음성 존재 여부를 판단하는 결정법을 유도한다. 이후 통계적 모델을 기반으로 한 음성 검출 방법의 신뢰도를 높이기 위해 새로운 방법들이 연구되었으며 최근까지 연구가 진행 중인 통계적 모델 기반의 음성 검출 방법을 소개한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제11권1호
• /
• pp.39-44
• /
• 2001

본 논문에서는 디지털 영상에서 얼굴 영상 검출을 위해 픽셀의 퍼지 소속도를 이용하여 신경망으로 학습하는 퍼지 신경망을 이용한 얼굴영상 검출을 제안한다. 입력 영상의 피라미드 영상에서 추출된 20$\times$20 윈도우 영상 안의 각 픽셀의 소속도로 얼굴 영상 패턴을 학습하여 얼굴 영상을 검출하는 방법은 단순히 영상의 픽셀 값 하나씩만을 고려해서 각 픽셀의 소속도를 고려하여 수행하는 얼굴 영상 분할보다 얼굴 영상을 더 정확하고 인식률이 높게 검출해 낼 수 있다.

• Annual Conference of KIPS
• /
• 한국정보처리학회 2004년도 추계학술발표논문집(상)
• /
• pp.821-824
• /
• 2004

본 논문은 지문인식률에 있어서 중요한 요소인 중심점(core point) 검출에 대하여 기존의 Poincare 지수를 이용하는 방법과 Sine을 취하는 방법의 결점을 해결하기 위해 마스크 블록을 이용하여 중심점을 검출 하는 방법을 제안하였다. 이에 대한 실험결과는 기존의 방법보다 빠르면서 검출 일관성에서도 좀더 나은 결과를 나타내었고 Arch형 지문의 중심점 검출에 있어서도 기존 방법들의 오류를 줄일 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송공학회 2013년도 하계학술대회
• /
• pp.52-55
• /
• 2013

본 논문은 Boosted Random Ferns 기반의 회전 불변 얼굴 검출 방법을 제안한다. 기존 Random Ferns 의 경우 특징값을 추출할 때 임의로 선택한 두 픽셀의 밝기값 비교를 통하여 이진 특징값을 추출한다. 이 경우 해당 픽셀의 밝기값에 잡음이 포함되면 특징값이 부정확하게 추출되는 문제가 있다. 본 논문에서는 이러한 문제를 해결하기 위하여 임의로 두 블록을 선택하고 해당 블록내 밝기값의 평균을 비교하여 이진 특징값을 추출하였다. 또한 픽셀 위치를 임의로 선택하여 ferns 를 구성하였던 기존의 방법 대신 최고의 분류 성능을 가지는 fern 들을 이용하여 분류기를 구성하기 위해, AdaBoost 의 방법을 Random Ferns 에 맞게 변경하였다. Boosted Random Ferns 를 트리 구조의 cascade 노드에 방향과 각도에 따라 배치하여 연산 속도를 향상시키고 false-positive를 줄이는 효과를 보았다. CMU Rotated Face Database 를 사용하여 평가하였을 때, 기존 Random Ferns 는 false-positive 의 수가 57 개 일 때 66%의 검출률을 보인 반면, Boosted Random Ferns 는 false-positive 의 수가 45 개 일 때 88%의 검출률을 보였다.