• 한국컴퓨터정보학회논문지
• /
• 제27권4호
• /
• pp.19-26
• /
• 2022

최근 지능형 교통 체계의 발전에 따라 자동차 번호판 인식 시스템이 다양한 분야에서 활용되고 있다. 주행 중인 자동차의 번호판을 인식하기 위해서는 실시간성이 보장되어야 하며, 영상이 왜곡되어 뚜렷하지 않거나 번호판의 크기가 작은 저해상도 영상에서도 높은 인식률이 유지되어야 한다. 본 논문에서는 자유 앵커 방식 기반의 객체 탐지 알고리즘과 합성곱 신경망(CNN) 기반의 문자 인식 알고리즘을 이용하여 처리 속도를 향상한 실시간 자동차 번호판 인식 시스템을 제안한다. 더불어 공간 변형 네트워크를 이용하여 저해상도 및 왜곡된 영상에서의 인식률을 높였다. 제안하는 시스템의 인식률은 93.769%, 이미지 당 처리 속도는 약 0.006초로 기존 자동차 번호판 인식 시스템보다 빠른 속도로 자동차 번호판을 인식하며, 다양한 환경 및 품질의 영상에 대해 높은 인식률을 유지하는 것을 확인할 수 있다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1431-1434
• /
• 2005

In the steel production line, the molten metal of a furnace is transformed into billet and then moves to the heating furnace of the hot rolling mill. This paper describes about the development of recognition system for the characters, which was marked at the billet material by use template-marking plate and hand written method, in the steel plant. For the recognition of template-marked characters, we propose PSVM algorithm. And for the recognition of hand written character, we propose combination methods of CCD algorithm and PSVM algorithm. The PSVM algorithm need some more time than the conventional KLT or SVM algorithm. The CCD algorithm makes shorter classification time than the PSVM algorithm and good for the classification of closed curve characters from Arabic numerals. For the confirmation of algorithm, we have compared our algorithm with conventional methods such as KLT classifier and one-to-one SVM. The recognition rate of experimented billet characters shows that the proposing PSVM algorithm is 97 % for the template-marked characters and combinational algorithm of CCD & PSVM is 95.5 % for the hand written characters. The experimental results show that our proposing method has higher recognition rate than that of the conventional methods for the template-marked characters and hand written characters. By using our algorithm, we have installed real time character recognition system at the billet processing line of the steel-iron plant.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(3)
• /
• pp.121-124
• /
• 2000

In this paper, we propose a pen gesture recognition system for user interface in multimedia terminal which requires fast processing time and high recognition rate. It is realtime and interaction system between graphic and text module. Text editing in recognition system is performed by pen gesture in graphic module or direct editing in text module, and has all 14 editing functions. The pen gesture recognition is performed by searching classification features that extracted from input strokes at pen gesture model. The pen gesture model has been constructed by classification features, ie, cross number, direction change, direction code number, position relation, distance ratio information about defined 15 types. The proposed recognition system has obtained 98% correct recognition rate and 30msec average processing time in a recognition experiment.

• 한국생산제조학회지
• /
• 제20권2호
• /
• pp.207-213
• /
• 2011

In this paper, we present a study on the real-time implementation of mobile robot to which the interactive voice recognition technique is applied. The speech command utters the sentential connected word and asserted through the wireless remote control system. We implement an automatic distance speech command recognition system for voice-enabled services interactively. We construct a baseline automatic speech command recognition system, where acoustic models are trained from speech utterances spoken by a microphone. In order to improve the performance of the baseline automatic speech recognition system, the acoustic models are adapted to adjust the spectral characteristics of speech according to different microphones and the environmental mismatches between cross talking and distance speech. We illustrate the performance of the developed speech recognition system by experiments. As a result, it is illustrated that the average rates of proposed speech recognition system shows about 95% above.

• 제어로봇시스템학회논문지
• /
• 제13권9호
• /
• pp.915-919
• /
• 2007

This paper proposed a transponder detection method to reduce recognition time in RFID system. It's also shown that conventional procedure of communication in the system could cause a waste of time when a reader recognizes a transponder. The reduction of recognition time can be obtained by developing a circuit to detect a transponder actively. Detecting a transponder is achieved by using the voltage variation of reader antenna voltage that happens when a transponder approaches to the vicinity of magnetic field formed by the reader. By adding a comparator to the antenna receiver of a reader, the reader can perceive approach or existence of a transponder. A reader for experiment is made using the MFRC500 by Phillips that supports ISO/IEC 14443 protocol. Comparing the proposed method with the conventional methods by experiment, there are 47.5ms reduction of recognition time maximally and 12ms in average.

• 전자공학회논문지B
• /
• 제31B권2호
• /
• pp.28-34
• /
• 1994

In this paper, a new time-domain parameter extraction method for speech recognition is proposed. The suggested emthod is based on the fact that the local peak-to-peak interval, i.e., the interval between maxima and minima of speech waveform is closely related to the frequency component of the speech signal. The parameterization is achieved by a sort of filter bank technique in the time domain. To test the proposed parameter extraction emthod, an isolated word recognizer based on Vector Quantization and Hidden Markov Model was constructed. As a test material, 22 words spoken by ten males were used and the recognition rate of 92.9% was obtained. This result leads to the conclusion that the new parameter extraction method can be used for speech recognition system. Since the proposed method is processed in the time domain, the real-time parameter extraction can be implemented in the class of personal computer equipped onlu with an A/D converter without any DSP board.

• 한국산학기술학회논문지
• /
• 제22권2호
• /
• pp.20-25
• /
• 2021

본 논문은 Deep-learning 기반의 검출모델을 이용하여 연속적으로 입력되는 비디오 이미지 내의 해당 대상체를 의미별로 분류해야하는 문제에 대한 구현방법에 관한 논문이다. 기존의 대상체 검출모델은 Deep-learning 기반의 검출모델로서 유사한 대상체 분류를 위해서는 방대한 DATA의 수집과 기계학습과정을 통해서 가능했다. 대상체 검출모델의 구조개선을 통한 유사물체의 인식 및 분류를 위하여 기존의 검출모델을 이용한 분류 문제를 분석하고 처리구조를 변경하여 개선된 비전처리 모듈개발을 통해 이를 기존 인식모델에 접목함으로써 대상체에 대한 인식모델을 구현하였으며, 대상체의 분류를 위하여 검출모델의 구조변경을 통해 고유성과 유사성을 정의하고 이를 검출모델에 적용하였다. 실제 축구경기 영상을 이용하여 대상체의 특징점을 분류의 기준으로 설정하여 실시간으로 분류문제를 해결하여 인식모델의 활용성 검증을 통해 산업에서의 활용도를 확인하였다. 기존의 검출모델과 새롭게 구성한 인식모델을 활용하여 실시간 이미지를 색상과 강도의 구분이 용이한 HSV의 칼라공간으로 변환하는 비전기술을 이용하여 기존모델과 비교 검증하였고, 조도 및 노이즈 환경에서도 높은 검출률을 확보할 수 있는 실시간 환경의 인식모델 최적화를 위한 선행연구를 수행하였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제8권4호
• /
• pp.39-47
• /
• 2016

This study is a smart tourism research based on face recognition applied system that manages individual information of foreign tourists to smartphone. It is a way to authenticate by using face recognition, which is biometric information, as a technology applied to identification inquiry, immigration control, etc. and it is designed so that tourism companies can provide customized service to customers by applying algorism to smartphone. The smart tourism system based on face recognition is a system that prepares the reception service by sending the information to smartphone of tourist service company guide in real time after taking faces of foreign tourists who enter Korea for the first time with glasses attached to the camera. The smart tourism based on face recognition is personal information recognition technology, speech recognition technology, sensing technology, artificial intelligence personal information recognition technology, etc. Especially, artificial intelligence personal information recognition technology is a system that enables the tourism service company to implement the self-promotion function to commemorate the visit of foreign tourists and that enables tourists to participate in events and experience them directly. Since the application of smart tourism based on face recognition can utilize unique facial data and image features, it can be beneficially utilized for service companies that require accurate user authentication and service companies that prioritize security. However, in terms of sharing information by government organizations and private companies, preemptive measures such as the introduction of security systems should be taken.

• 한국지능시스템학회논문지
• /
• 제16권1호
• /
• pp.49-54
• /
• 2006

현재의 지문 인식 시스템은 지문 패턴의 복제와 지문 특징점의 해킹이라는 불안한 요소가 잠재되어 있어, 시스템 오동작의 주요 원인이 되기도 한다. 이에 본 논문에서는 신체의 일부인 지문을 주 핵심 인식기로 사용하고, 여기에 최근 널리 이용 되고 있는 화자 인증을 이용하여 직렬 형태의 다중 생체인식 시스템을 구현하였다. 구현된 시스템은 다중생체인식시스템으로 먼저 음성에 대한 인증과정이 성공하면 지문에 대한 인식과정을 수행하는 구조로 되어있다. 또한 효율적인 실시간 인증 처리를 위해 기존의 음성 인식 알고리즘 중에서 화자 종속형인 DTW(Dynamic Time Waning) 알고리즘을 사용하였으며, 지문 인식 알고리즘으로는 계산량을 고려하여 인공지능 기법인 KSOM(Kohonen Self-Organizing feature Map) 알고리즘을 적용하였다. 본 논문에서 구현한 다중생체 인식시스템을 실험한 결과 지문과 음성을 각각 이용한 단일인식시스템보다 본인거부율은 $2\~7\%$정도 떨어졌지만, 인식시스템에서 가장 중요한 요소인 타인수락율은 전혀 발생하지 않음을 확인하였다. 아울러 인식테스트 시간 또한 기존의 단일 생체 인식 시스템과 차이가 거의 없었으며, 인식에 걸린 시간은 평균 1.5초 정도였다. 이에 구현된 다중 생체 인의 시스템은 여러 가지 실험 결과 단일 인식 시스템보다 더 효율적인 보안 시스템임을 증명하였다.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1421-1429
• /
• 2017

Human activity recognition has been studied using various sensors and algorithms. Human activity recognition can be divided into sensor based and vision based on the method. In this paper, we proposed an activity recognition system using acceleration sensor and gyroscope sensor in smartphone among sensor based methods. We used Deep Belief Network (DBN), which is one of the most popular deep learning methods, to improve an accuracy of human activity recognition. DBN uses the entire input set as a common input. However, because of the characteristics of different time window depending on the type of human activity, the RBMs, which is a component of DBN, are configured hierarchically by combining them from different time windows. As a result of applying to real data, The proposed human activity recognition system showed stable precision.