• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• 전자공학회논문지
• /
• 제54권2호
• /
• pp.115-122
• /
• 2017

본 논문은 딥러닝 알고리즘을 기반으로 하여 시각장애인을 위한 표지판을 검출하고 인식하는 시스템을 제안한다. 제안된 시스템은 크게 표지판 검출 단계와 표지판 인식 단계로 나눠지는데 표지판 검출 단계에서는 영상에서 응집 채널 특징을 추출한 뒤 아다부스트 분류기를 적용하여 표지판 관심영역을 검출하였고, 표지판 인식 단계에서는 검출한 표지판 관심영역들에 합성곱 신경망을 적용하여 어떤 표지판인지 인식하였다. 본 논문에서는 미검출된 표지판의 개수가 최대한 감소하도록 아다부스트 분류기를 설계하였고, 딥러닝 알고리즘을 사용하여 인식 정확도를 높임으로써 검출 단계에서 발생한 양성 오류들을 제거시켰다. 실험 결과, 제안된 방법의 양성 오류 개수가 다른 방법들의 양성 오류 개수보다 효과적으로 감소했음을 확인하였다.

• 한국IT서비스학회지
• /
• 제20권6호
• /
• pp.97-105
• /
• 2021

Recently, with the development of IT technology, unmanned systems are being introduced in many industrial fields, and one of the most important factors for introducing unmanned systems in the automobile field is vehicle licence plate recognition(VLPR). The existing VLPR algorithms are configured to use image processing for a specific type of license plate to divide individual areas of a character within the plate to recognize each character. However, as the number of Korean vehicle license plates increases, the law is amended, there are old-fashioned license plates, new license plates, and different types of plates are used for each type of vehicle. Therefore, it is necessary to update the VLPR system every time, which incurs costs. In this paper, we use an object detection algorithm to detect character regardless of the format of the vehicle license plate, and apply a handwritten Hangul recognition(HHR) algorithm to enhance the recognition accuracy of a single Hangul character, which is called a Hangul unit. Since Hangul unit is recognized by combining initial consonant, medial vowel and final consonant, so it is possible to use other Hangul units in addition to the 40 Hangul units used for the Korean vehicle license plate.

• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.795-808
• /
• 2020

Due to the poor evaluation indexes such as detection accuracy and recall rate when Yolov3 network detects aircraft in remote sensing images, in this paper, we propose a remote sensing image aircraft detection method based on machine vision. In order to improve the target detection effect, the Inception module was introduced into the Yolov3 network structure, and then the data set was cluster analyzed using the k-means algorithm. In order to obtain the best aircraft detection model, on the basis of our proposed method, we adjusted the network parameters in the pre-training model and improved the resolution of the input image. Finally, our method adopted multi-scale training model. In this paper, we used remote sensing aircraft dataset of RSOD-Dataset to do experiments, and finally proved that our method improved some evaluation indicators. The experiment of this paper proves that our method also has good detection and recognition ability in other ground objects.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제32권12호
• /
• pp.1247-1259
• /
• 2005

본 연구는 웹카메라와 같은 저해상도의 동영상으로부터 실시간 다중 얼굴 인식 시스템을 제안한다. 동영상을 이용한 얼굴 인식 시스템은 크게 얼굴 검출 단계와 얼굴 분류 단계로 나눌 수 있다. 첫째, 얼굴 검출 단계에서는 빠르고 강인한 객체 검출 성능을 가진 AdaBoost를 이용하여 얼굴 후보 영역을 검출하였고, 검출된 얼굴 후보 영역에 대한 주성분을 수행하여 데이타의 크기기 현저히 줄어든 특징 벡터를 구한 다음에 특징 벡터에 대해 SVM 기반 이진 분류를 수행하여 얼굴 후보 영역을 검증하였다. 둘째, 얼굴 분류 단계에는 주성분 분석과 멀티 SVM을 이용하여 각 얼굴들을 분류하였다. 실험 결과 본 논문에서 제안한 방법은 저해상도에서도 높은 얼굴 검출율과 동영상에서 실시간 처리가 가능한 빠른 다중 얼굴 검출과 인식 성능을 보였다. 또한 팬-틸트 기능을 가진 웹카메라를 이용한 자동 추적형 얼굴 인식 시스템을 적용하여 얼굴 검출 성능을 향상시켰고, 얼굴 인식 시스템의 응용으로 무선 On/off 얼굴인식 도어락 시스템을 구현하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.417-417
• /
• 2000

This paper proposes a face detection and recognition method that combines the template matching method and the eigenface method with the neural network. In the face extraction step, the skin color information is used. Therefore, the search region is reduced. The global property of the face is achieved by the eigenface method. Face recognition is performed by a neural network that can learn the face property.

• 디지털융복합연구
• /
• 제14권8호
• /
• pp.233-243
• /
• 2016

소음환경에서의 음성인식 문제점으로 인해 1990년대 중반부터 음성정보와 영양정보를 결합한 AVSR(Audio Visual Speech Recognition) 시스템이 제안되었고, Lip Reading은 AVSR 시스템에서 시각적 특징으로 사용되었다. 본 연구는 효율적인 AVSR 시스템을 구축하기 위해 입 모양만을 이용한 발화 단어 인식률을 극대화하는데 목적이 있다. 본 연구에서는 입 모양 인식을 위해 실험단어를 발화한 입력 영상으로부터 영상의 전처리 과정을 수행하고 입술 영역을 검출한다. 이후 DNN(Deep Neural Network)의 일종인 CNN(Convolution Neural Network)을 이용하여 발화구간을 검출하고, 동일한 네트워크를 사용하여 입 모양 특징 벡터를 추출하여 HMM(Hidden Markov Mode)으로 인식 실험을 진행하였다. 그 결과 발화구간 검출 결과는 91%의 인식률을 보임으로써 Threshold를 이용한 방법에 비해 높은 성능을 나타냈다. 또한 입모양 인식 실험에서 화자종속 실험은 88.5%, 화자 독립 실험은 80.2%로 이전 연구들에 비해 높은 결과를 보였다.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.280-286
• /
• 2022

Facial recognition system is a biometric manipulation. Its applicability is simpler, and its work range is broader than fingerprints, iris scans, signatures, etc. The system utilizes two technologies, such as face detection and recognition. This study aims to develop a facial recognition system to recognize person's faces. Facial recognition system can map facial characteristics from photos or videos and compare the information with a given facial database to find a match, which helps identify a face. The proposed system can assist in face recognition. The developed system records several images, processes recorded images, checks for any match in the database, and returns the result. The developed technology can recognize multiple faces in live recordings.

• 디지털산업정보학회논문지
• /
• 제5권2호
• /
• pp.77-85
• /
• 2009

In this paper, we propose data format for smell, taste, touch with speech and vision which can be transmitted and implement a floral scent detection and recognition system. We provide representation method of data of smell, taste, and touch. Also, proposed floral scent recognition system consists of three module such as floral scent acquisition module using Metal Oxide Semiconductor (MOS) sensor array, entropy-based floral scent detection module, and floral scent recognition module using correlation coefficients. The proposed system calculates correlation coefficients of the individual sensor between feature vector(16 sensors) from floral scent input point until the stable region and 12 types of reference models. Then, this system selects the floral scent with the maximum similarity to the calculated average of individual correlation coefficients. To evaluate the floral scent recognition system using correlation coefficients, we implemented an individual floral scent recognition system using K-NN with PCA and LDA that are generally used in conventional electronic noses. In the experimental results, the proposed system performs approximately 95.7% average recognition rate.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.