• 전자공학회논문지B
• /
• 제30B권12호
• /
• pp.21-30
• /
• 1993

In this paper, we propose a connected Korean digit recohnition system employing neural networks and lexical constraints of the Korean digits. In the proposed recognition system, firstly, each frame of digit string is labelled by phoneme classification neural networks.which are trained with the reference phoneme segments extracted form an isolated digit based on the position information. And, the frame labels are combined with each other for constructing the phoneme segments. Then, these segments are combined to form a digit candidate using the digit combination rules. The digit candidate is decided based on the condition for digit decision. If the condition is not satisfied, the digit candidate is further recognized using the digit decision neural network in the next step. In our approach, the neural networks are trained with 10 isolated digits uttered by 5 male speakers. To investigate the performance of the proposed recognition system, an intensive computer simulation on the 30 connected digit strings uttered by 5 male speakers is performed. The simulation result indicates that 95.6% digit recognition rate and 82% digit string recognition rate are provided by the proposed Korean digit recognition system.

• 한국컴퓨터정보학회논문지
• /
• 제9권1호
• /
• pp.25-30
• /
• 2004

본 논문은 지휘자의 지휘 동작으로부터 일련의 영상들을 추출하여 지휘자가 지휘하는 박자를 인식하는 방법을 제안하고 있다 색상판별에 의해서 손의 위치를 감지하였으며 양자화를 통해서 그 위치를 기호화함으로써 지휘 동작을 일련의 기호로 표현하였다. 변형을 포함하는 기호열의 인식에 좋은 결과를 보이는 HMM(Hidden Markov Model)을 사용함으로써 표현된 기호열을 지휘박자로 인식하도록 하는 시스템을 구성하였다.

• 산업경영시스템학회지
• /
• 제22권50호
• /
• pp.11-21
• /
• 1999

In this paper, an algorithm to generate the mounting position and orientation of SMD is proposed. For the proposed algorithm, we used the image captured from PCB and utilized image processing technique. Pre-processing technique, threshold level determination method, divided recognition of the SMD pattern on a PCB, calculating mounting position and orientation are related topics of this research. All of the related topics were reviewed and the results of this research were obtained from applying the algorithm to the real Surface Mounting Machine(model:MCUl/CPM) made by Samsung Electronics Co.

• 전자공학회논문지B
• /
• 제33B권2호
• /
• pp.10-19
• /
• 1996

This paper presents a finger-shaped multisensor system which can measure the tyep and position of a target surface by contactl. The multi-sensor system consists of a sphere-shpaed optical tactile sensor located at the finger tip and a force/torque sensor located at the joint of a finger. The optial tactile sensor determines the type and position of the target surface using the shape and position of the CCD image of the touching area generated by a contact between the sensor and the taget surface. The force/torque sensor also determines the position and surface normal vector by applying the distributionof forces and torques t the contact point to the equations of finger shape. The measurements on the position and surface normal vector at a contact point obtined by two individual sensors are fused using a statistical method. The integrated sensor system has 0.8mm error in position measurement and 1.31$^{\circ}$ error in normal vector measurement. The developed sensor system has many applications, such as autonomous compliance control, automatic grasping and recognition, etc.

• 사상체질의학회지
• /
• 제19권1호
• /
• pp.50-59
• /
• 2007

1. Objectives The Face is an important standard for the classification of Sasang Contitutions. Now We are developing 3D Automatic Face Recognition Apparatus to analyse the facial characteristics. This apparatus show us 3D image of man's face and measure facial figure. We should examine accuracy of position recognition in 3D Automatic Face Recognition Apparatus(3D-AFRA). 2. Methods We took a photograph of Face status with Land Mark by using 3D-AFRA. And We scanned Face status by using laser scanner(vivid 700). We analysed error average of distance between Facial Definition Points. We compare the average between using 3D-AFRA and using laser scanner. So We examined the accuracy of position recognition in 3D-AFRA at indirectly. 3. Results and Conclusions The error average of distance between Right Pupil and The Other Facial Definition Points is 0.5140mm and the error average of distance between Left Pupil and The Other Facial Definition Points is 0.5949mm in frontal image of face. The error average of distance between Left Pupil and The Other Facial Definition Points is 0.5308mm and the error average of distance between Left Tragion and The Other Facial Definition Points is 0.6529mm in laterall image of face. In conclusion, We assessed that accuracy of position recognition in 3D-AFRA is considerably good.

• 대한전자공학회논문지SP
• /
• 제44권3호
• /
• pp.48-60
• /
• 2007

기존의 연구에서는 홍채 특징 추출을 위해 검출된 원형 홍채 영역을 직교 사각형 홍채 영상으로 스트레칭 및 보간 하는 작업을 수행하였다. 이러한 경우 실제 홍채 특징이 왜곡되는 현상이 발생한다. 본 논문에서는 홍채 영상의 왜곡 없이 정확하게 홍채 특징을 추출할 수 있는 방법을 제안한다. 본 연구는 다음과 같은 세 가지 장점을 가지고 있다. 첫 번째, 극좌표 원형 영상 방식을 이용하여 기존의 직교 사각형 영상 방식보다 인식 성능 면에서 우수하다는 점을 해밍거리, 코사인거리, 유클리디안 거리의 3가지 metric을 이용하여 실제로 비교해본 점이며, 두 번째, 최근 홍채인식 연구의 주된 흐름인 품질이 좋지 못한 Non-Ideal 홍채 영상 중 하나의 형태인 홍채 카메라의 중심을 쳐다보지 않은 상태에서 취득된 홍채 영상의 동공과 홍채 중심 위치가 많이 차이나는 경우에 동공과 홍채 경계를 각각 원형 경계 검출로 경계를 찾은 후, 영상에 대한 보간(interpolation)없이 극좌표 원형 홍채 영상에서 직접 특징을 추출함으로써 홍채인식의 성능을 향상한 점이다. 마지막 세 번째는 극좌표 원형방식을 사용할 경우 발생하는 중복 포인트 문제를 해결한 것이다. 이러한 중복 포인트들은 같은 위치에서 여러 홍채 특징을 추출하는 현상을 야기함으로서 저주파 홍채 특징을 생성하는 결과를 낳게 된다. 즉, 홍채 특징의 신호 변화가 실제로 존재함에도 불구하고 같은 위치에서의 여러 홍채 특징들을 추출함으로써 파형변화가 적은 비슷한 홍채 신호를 만들게 된다. 중복 포인트가 주기적으로 많이 발생하는 동공부근의 첫 번째 트랙에 가버필더 적용 시 필터의 주파수를 작게 하여 중복 포인트에 의해 발생된 저주파 홍채 신호를 정확하게 추출하게 함으로써 홍채 인식 성능을 향상 시킨 점이다. 실험 결과, 기존의 직교 사각형 영상 기반 방식이 EER 0.29% 와 d'값 5.8 이였으며, 제안하는 극좌표 원형 방식이 EER 0.16% 와 d'값 6.4로 인식 성공률이 보다 높음을 알 수 있었다.

• 디지털산업정보학회논문지
• /
• 제15권4호
• /
• pp.149-157
• /
• 2019

In case of reading passport using a smart phone in contrast with a dedicated passport reading system, MRZ(Machine Readable Zone) character recognition can be hard when the character strokes were broken, touched or blurred according to the lighting condition, and the position and size of MRZ character lines were varied due to the camera distance and angle. In this paper, the effective recognition algorithm of the passport MRZ information using a combined neural network recognizer of CNN(Convolutional Neural Network) and ANN( Artificial Neural Network), is proposed under the various sized and skewed passport images. The MRZ line detection using connected component analysis algorithm and the skew correction using perspective transform algorithm are also designed in order to achieve effective character segmentation results. Each of the MRZ field recognition results is verified by using five check digits for deciding whether retrying the recognition process of passport MRZ information or not. After we implement the proposed recognition algorithm of passport MRZ information, the excellent recognition performance of the passport MRZ information was obtained in the experimental results for PC off-line mode and smart phone on-line mode.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.797-803
• /
• 2014

In this paper, 3D face recognition system is designed by using polynomial based on RBFNNs. In case of 2D face recognition, the recognition performance reduced by the external environmental factors such as illumination and facial pose. In order to compensate for these shortcomings of 2D face recognition, 3D face recognition. In the preprocessing part, according to the change of each position angle the obtained 3D face image shapes are changed into front image shapes through pose compensation. the depth data of face image shape by using Multiple Point Signature is extracted. Overall face depth information is obtained by using two or more reference points. The direct use of the extracted data an high-dimensional data leads to the deterioration of learning speed as well as recognition performance. We exploit principle component analysis(PCA) algorithm to conduct the dimension reduction of high-dimensional data. Parameter optimization is carried out with the aid of PSO for effective training and recognition. The proposed pattern classifier is experimented with and evaluated by using dataset obtained in IC & CI Lab.

• 한국멀티미디어학회논문지
• /
• 제11권12호
• /
• pp.1676-1687
• /
• 2008

In this paper, we proposed a new multi-view human recognition method based on face and gait features detection algorithm. For getting the position of moving object, we used the different of two consecutive frames. And then, base on the extracted object, the first important characteristic, walking direction, will be determined by using the contour of head and shoulder region. If this individual appears in camera with frontal direction, we will use the face features for recognition. The face detection technique is based on the combination of skin color and Haar-like feature whereas eigen-images and PCA are used in the recognition stage. In the other case, if the walking direction is frontal view, gait features will be used. To evaluate the effect of this proposed and compare with another method, we also present some simulation results which are performed in indoor and outdoor environment. Experimental result shows that the proposed algorithm has better recognition efficiency than the conventional sing]e view recognition method.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.557-564
• /
• 2015

There are many prior studies for more natural Human-Computer Interaction. Until now, the efforts is continued in order to recognize motions in various directions. In this paper, we suggest a user-specific recognition by hit detection method using Kinect camera and human proportion. This algorithm extracts the user-specific valid recognition rage after recognizing the user's body initially. And it corrects the difference in horizontal position between the user and Kinect, so that we can estimate a action of user by matching cursor to target using only one frame. Ensure that efficient hand recognition in the game to take advantage of this method of suggestion.