• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.447-454
• /
• 2013

As the surveillance CCTVs are increasing every year, big data image processing for the CCTV image data has become a hot issue. In this paper, we propose a Hadoop-based big data image processing technique to recognize a vehicle number from a large amount of automatic number plate images taken from CCTVs. We also implement the vehicle route tracking system that displays the moving path of the searched vehicle on Google Maps with the related information together. In order to evaluate the performance we compare and analysis the vehicle number recognition time for a lot of CCTV image data in Hadoop and the single PC environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1700-1705
• /
• 2003

In this paper, the automatic steering system for unmanned vehicle was developed. The vision system is used for the lane detection system. This paper defines two modes for detecting lanes on a road. First is searching mode and the other is recognition mode. We use inverse perspective transform and a linear approximation filter for accurate lane detections. The PD control theory is used for the design of the controller to compare with $H_{\infty}$ control theory. The $H_{\infty}$ control theory is used for the design of the controller to reduce the disturbance. The performance of the PD controller and $H_{\infty}$ controller is compared in simulations and tests. The PD controller is easy to tune in the test site. The $H_{\infty}$ controller is robust for the disturbances in the test results.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.5
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.102-105
• /
• 2003

"e-Leaning" system is classified by lecture time into two types, that is, "synchronous type" spent the same lecture time between the lecturer and students, and "asynchronous type" spent the different lecture time. The size of image database is huge, and there are some problem on the management of the lecture image database in "asynchronous type" e-Learning system. The one of them is that the time tag for the database management must be added manually at present, and the cost of the addition of the time tag causes a serious problem. To resolve the problem, we will use the character recognition for the characters written by the lecturer on whiteboard, and will add the recognized character as a keyword to the tag of the image database. If the database would have the keyword, we could retrieve the database by the keyword efficiently, and the student could select the interested lecture scene only in the full lecture database.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.128-135
• /
• 2002

Burr is a projected part of finished workpiece. It is unavoidable and undesirable by-product of most metal cutting or shearing process. Also, it must be removed to improve the fit of machined parts, safety of workers, and the effectiveness of finishing operation. But deburring process Is one of manufacturing processes that have not been successfully automated, so deburring automation is strongly needed. This paper focused on developing a basic algorithm to find edge of workpiece and match two different image data for deburring automation which includes automatic recognition of parts, generation of deburring tool paths and edge/comer finding ability by analyzing the DXF drawing file which contains information of part geometry. As an algorithm fur corner finding, SUSAN method was chosen. It makes good performance in finding edge and corner in suitable time. And this paper suggested a simple algorithm to find matching point between CCD image and drawing file.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.1002-1013
• /
• 1996

The segmentation of characters is an important step in the automatic recognition of handwritten text. This paper proposes the segmenting method of off-line handwritten Hangul. The suggested approach is based on the structural characteristics of Hangul. The first step extracts the local features. connected component and strokes from the imput word. In the second step we identify the class of strokes. The third segmenting step specifies WRC(White Run Column) before consonant or horizontal vowel. If the segment is longer than threshold, the system estimates segmenting columns using the consonant-vowel information and column features, and then finds a cornered boundary along the strokes within the estimated segmenting columns.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.175-178
• /
• 2004

선박의 수중방사소음은 다양한 기계류나 추진기 혹은 선체와 유체간의 상호 작용으로 인하여 여러 형태의 특성신호로 나타나게 된다. 이는 선박의 운용조건, 장비 회전특성 및 내부구조에 따라 스펙트럼상에 상이한 주파수로 확인됨은 물론, 신호의 출현 형태에도 다양성을 보이고 있다. 일반적으로 선박소음은 속력 종속적인 추진 계통 성분과 비종속적인 보기류 신호로 구분되나 다수의 신호성분이 혼재되어 발생기원을 분류하는 것은 복잡한 과정을 거쳐야 한다. 본 연구에서는 이러한 점을 해결하기 위해 선박의 Tonal성 신호를 자동으로 탐지하고 분류하기 위해 규준화된 스펙트로그램 상에서 연속되는 신호에 가중치를 주어 지속성 신호여부를 판별한 후에 정해진 임계치를 초과하는 성분을 Tonal로 선정하였다. 선정된 Tonal에 대해 주파수선의 대역특성 및 시간 변동성에 대한 패턴인식 방법을 적용하여 Tonal의 발생기원이 속력 종속/비종속적인지를 자동으로 판별하는 알고리즘의 유용성에 대한 결과를 기술하였다.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.390-399
• /
• 1999

Extracting the character region(container identifier) in the image of a shipping container is one of the key factors in a system for identifying a shipping container automatically To improve the performance of the automatic recognition system for identifying a shipping container, thus a method partitioning the character region more correctly and efficiently is needed. In this paper, an efficient method is proposed to extract only the character region in the image of a shipping container. The proposed method removes noises that are not possibly related to the character using morphological operation, then the image is binarized using the threshold value that is determined from the image obtained previous step. Finally individual character area is extracted from the binary image. Also experiments are conducted to verify the efficiency of the proposed method. The results show that the proposed method partitions the character region correctly from container images.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.412-416
• /
• 2007

본 논문에서는 OCR(Optical Character Recognition)의 정확도를 위해 인쇄체 한글 문서 영상에 대한 자동 평가방법을 제안한다. 자동 평가방법은 문서가 스캔된 상태에 따라 낮은 해상도, 영상 자체의 기울어짐, 많은 잡음 등을 판단하여 인식하지 않고도 인식률을 추측할 수 있다. 평가방법은 영상 자체의 밝기, 기울기, 영역의 특징, 문자의 상태 등을 특징 항목으로 만들어 점수를 산출한다. 각 항목의 점수는 가장 높은 인식률을 가지는 영상의 특징 값을 기준으로 삼는다. 각각의 특징에 대해 점수가 산출되면 인식률에 높은 비중을 차지하는 특징에 높은 가중치를 적용하여 최종 점수를 산출한다. 영상 평가방법을 통해 높은 점수를 얻은 영상은 상용 인식기를 통해 인식한 결과 높은 인식률을 나타냈고, 평가방법에서 낮은 점수를 받은 영상은 상대적으로 낮은 인식률을 나타냈다. 본 논문에서 제안하는 문서영상을 위한 자동 평가방법은 인식기를 사용하지 않고 영상의 품질을 측정하기 때문에 빠른 시간에 인식률을 추측할 수 있고, 낮은 인식률을 보일 수 있는 영상에 대해서는 항목별 점수를 피드백으로 사용할 수 있어 인식하기전 문서 영상의 전처리에 과정에 도움을 줄 수 있다.

• Journal of Biomedical Engineering Research
• /
• v.12 no.2
• /
• pp.99-106
• /
• 1991

For the automatic detection of pulmonary blood vessels, a new algorithm is proposed using the fact that human recognizes a pattern orderly according to their size. This method simulates the human recognition process by the pyramid images. For the detection of vessels using multilevel image, large and wtde ones are detected from the most compressed level, followed by the detection of small and narrow ones from the less compressed images with FCM(fuzzy c means) clustering algorithm which classifies similar data into a group. As the proposed algorithm detects blood vessels orderly according to their size, there is no need to consider the variation of parameters and the branch points which should be considered in other detection algirithms. In the detection of patterns whose size changes successively like pulmonary blood vessels, this proposed algorithm can be properly applied