• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.335-339
• /
• 2005

본 논문에서는 퍼지 RBF 네트워크의 학습 성능을 개선하기 위하여 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하는 개선된 퍼지 RBF 네트워크를 제안한다. 제안된 학습 알고리즘은 일반화된 델타 학습 방법에 퍼지 C-Means 알고리즘을 결합한 방법으로, 중간층의 노드를 자가 생성하고 중간층과 출력충의 학습에는 일반화된 델타 학습 방법에 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하여 학습 성능을 개선한다. 제안된 RBF 네트워크의 학습 성능을 평가하기 위하여 컨테이너 영상에서 추출한 40개의 식별자를 학습 데이터로 적용한 결과, 기존의 ART2 기반 RBF 네트워크와 기존의 퍼지 RBF 네트워크 보다 학습 시간이 적게 소요되고, 학습의 수렴성이 개선된 것을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.695-698
• /
• 2014

As most the scanning systems developed until now provide radiation scan plane images of the inspected objects, there has been a limitation in judging exactly the shape of the objects inside a logistics container exactly with only 2-D radiation image information. Two 2-dimensional radiation images which have different disparity values are acquired from a newly designed stereo image acquisition system which has one additional line sensor to the conventional system. Using a matching algorithm the 3D reconstruction process which find the correspondence between the images is progressed. In this paper, we proposed a new volume based 3D reconstruction algorithm and experimental results show the proposed new volume based reconstruction technique can provide more efficient visualization for cargo inspection. The proposed technique can be used for the development of the high speed and more efficient non-destructive auto inspection system.

• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.35-43
• /
• 2004

In this paper, we proposed a vehicle recognition and electronic toll collection system with detection and classification of vehicle identification mark and emblem as well as recognition of vehicle license plate to unman toll fee collection system or incoming/outcoming vehicles to an institution. In the proposed algorithm, we first process pre-processing step such as noise reduction and thinning from the rear side input image of vehicle and detect vehicle mark, emblem and license plate region using intensity variation informations, template masking and labeling operation. And then, we classify the detected vehicle features regions into vehicle mark and emblem as well as recognize characters and numbers of vehicle license plate using hybrid and seven segment pattern vector. To show the efficiency of the proposed algorithm, we tested it on real vehicle images of implemented vehicle recognition system in highway toll gate and found that the proposed method shows good feature detection/classification performance regardless of irregular environment conditions as well as noise, size, and location of vehicles. And also, the proposed algorithm may be utilized for catching criminal vehicles, unmanned toll collection system, and unmanned checking incoming/outcoming vehicles to an institution.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.19-25
• /
• 2021

In this paper proposes a method of finding missing persons based on face-recognition technology and deep learning. In this paper, a real-time face-recognition technology was developed, which performs face verification and improves the accuracy of face identification through data fortification for face recognition and convolutional neural network(CNN)-based image learning after the pre-processing of images transmitted from a mobile device. In identifying a missing person's image using the system implemented in this paper, the model that learned both original and blur-processed data performed the best. Further, a model using the pre-learned Noisy Student outperformed the one not using the same, but it has had a limitation of producing high levels of deflection and dispersion.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.160-170
• /
• 2010

This paper proposes a Haar Wavelet Feature Detector (HWFD) based on the Haar wavelet transform and average box filter. By decomposing the original image using the Haar wavelet transform, the proposed detector obtains the variance information of the image, making it possible to extract more distinctive features from the original image. For detection of interest points that represent the regions whose variance is the highest among their neighbor regions, we apply the average box filter to evaluate the local variance information and use the integral image technique for fast computation. Due to utilization of the Haar wavelet transform and the average box filter, the proposed detector is robust to illumination change, scale change, and rotation of the image. Experimental results show that even though the proposed method detects fewer interest points, it achieves higher repeatability, higher efficiency and higher matching accuracy compared with the DoG detector and Harris corner detector.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.5
• /
• pp.28-34
• /
• 2007

A histogram-based road border line extractor is proposed for an efficient road extraction from the high-resolution satellite imagery. The road border lines are extracted from an edge strength map based on the directional histogram difference between the road and the non-road region. The straight and the curved roads are extracted hierarchically from the edge strength map of the original image and the segmented road cluster images, and the road network is constructed based on the connectivity. Unlike the conventional approaches based on the spectral similarity, the proposed road extraction method is more robust to noise because it extracts roads based on the histogram, and is able to extract both the location and the width of roads. In addition, the proposed method can extract roads with various spectral characteristics by identifying the road clusters automatically. Experimental results on IKONOS multi-spectral satellite imagery with high spatial resolution show that the proposed method can extract the straight and the curved roads as well as the accurate road border lines.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.586-589
• /
• 2015

A computer presentation system by using hand-motion identification rules is proposed. To identify hand motions of a presenter, a face region is extracted first using haar classifier. A motion status(patterns) and position of hands is discriminated using the center of gravities of user's face and hand after segmenting the hand area on the YCbCr color model. User's hand is applied to the motion detection rules and then presentation control command is then executed. The proposed system utilizes the motion identification rules without the use of additional equipment and it is then capable of controlling the presentation and does not depend on the complexity of the background. The proposed algorithm confirmed the stable control operation via the presentation of the experiment in the dark illumination range of indoor atmosphere (lx) 15-20-30.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.4
• /
• pp.117-125
• /
• 2003

The proposed mechanism has an group management server, which manages the information about both the receivers and the senders. Any receiver can dynamically join/leave the multicast VC. The signaling overload due to group membership changes is not concentrated on the sender, but it is distributed to many receivers for the scalability improvement. The associated signaling messages propagates from the receivers to the ATM switch dedicated to the multicast VC, and hence no signaling overload exists in the shared links there is no latency for the receiver to wait. Our proposed scheme is superior in the view of scalability, the efficiency and the latency to other schemes.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.137-138
• /
• 2018

본 논문에서는 해경, 경찰 소방의 임무 상황 등에서 신속하고 능동적으로 대처할 수 있는 드론(Drone) 영상 종합정보처리 및 분석용 시스템을 제안한다. 제안하는 시스템은 드론에서 획득한 영상을 RTP/RTSP 프로토콜을 통해 수신하여 서버에 저장하고, 다양한 시나리오에 따른 영상 처리 및 분석을 수행한다. 실험을 통해 교통량 측정, 용의자 및 차량 추적, 조난자 식별 및 해상 초계 임무에 적용할 수 있음을 확인한다. 드론 운용자가 임무에 따른 필요 기능을 선택하고 신속하게 대처할 수 있는 시스템을 구현하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.70-70
• /
• 2017

영상처리 기법을 이용한 유속 측정 방법인 표면영상유속계는 비접촉식으로 간편하게 유속을 측정할 수 있다는 장점이 있지만 영상 내 추적자의 움직임을 식별하기 어려운 야간의 경우와 새벽의 안개가 발생하는 경우에 대한 유속 측정의 어려움이 있었다. 표면영상유속계를 이용한 야간 유속 측정은 조명과 적외선 카메라를 이용하여 수표면을 가시화하는 방법을 통해 현장 적용성을 검증하였으나, 안개 발생 상황에서는 적용하기 어렵다는 한계가 있었다. 야간과 안개 등의 한계를 동시에 극복하기 위한 방법으로 원적외선 카메라를 이용한 연구들이 이루어지고 있지만 아직 시작단계이고, 원적외선의 경우 주변 환경 변화에 따라 물체의 표면온도가 검출되는 파장이 달라져 영상의 품질에 차이가 발생하기 때문에 이에 대한 다양한 실험적 연구가 필요하다. 이에 본 연구에서는 야외 개수로에서 드라이아이스를 이용하여 안개 조건을 재현하고, 다양한 흐름 조건에서 원적외선 영상을 이용한 표면유속 측정 적용성을 검토하였다. 안개가 발생하는 경우 원적외선 표면영상 유속계를 적용한 결과 안개가 없을 때의 유속 측정 결과와 거의 일치하는 것을 확인하였다. 따라서 원적외선 카메라를 이용한 표면유속 측정 방법은 야간과 안개가 발생하는 상황에 모두 사용하기에 적합한 것을 나타났다. 향후 하천 유량조사에 원적외선 카메라를 활용한다면 기존의 표면영상유속계의 비가시 환경에 대한 한계들을 많은 부분 극복할 수 있을 것으로 기대한다.