• 한국콘텐츠학회논문지
• /
• 제10권11호
• /
• pp.48-57
• /
• 2010

기존의 우편 영상의 인식 연구는 수신인의 주소 정보를 인식하는데 초점이 맞춰 있었다. 상대적으로 발송인의 주소 정보를 인식하려는 연구는 적었다. 다량우편물 발송 업체의 우편물의 인쇄품질 검증 처리 및 반송 처리 등 송신자 정보를 이용한 서비스 및 응용을 위하여 송신자 정보의 인식 연구는 필요하다. 이 논문은 SIFT (Scale Invariant Feature Transform)을 이용하여 우편 영상의 송신자를 인식하는 방법을 제안하고 인식 실험을 하였다. SIFT 방법은 우수한 인식률을 보이나 등록한 모델수에 비례하여 keypoint들을 매칭하는데 소요하는 시간도 증가하는 시간 문제와 우편 영상의 특성상 서로 다른 모델일지라도 유사한 keypoint가 많아 오인식되는 문제가 있었다. 이를 해결하기 위해 거리함수를 추가한 SIFT를 제안하고 시간과 성능을 비교 실험 하였다. 또한 모델을 등록하는 수작업 과정 없이 자동으로 모델을 등록하고 분류하는 방법도 제안한다.

• 한국정보처리학회논문지
• /
• 제6권4호
• /
• pp.968-976
• /
• 1999

현재 유편봉투의 상태를 점검한 후, 우편 자동처리 센터(우편집 중국)에서 거의 대부분 OCR(Optical Character Recognition)로 우편주소 및 우편번호를 판독하여 3 of 5 형광(발광) 바코드로 7자리를 인쇄하고, 바코드 구분기(Barcode Sorter)에서 우편물을 자동구분 처리하고 있다. 일반적으로 자동처리 중에 우편주소 및 우편번호 잘못 기재, 주소 및 바코드 인쇄품질의 불량 등에 의하여 오류로 구분되어지는 우편 물량은 전체 우편물량의 31∼35%를 차지하고 있다. 본 논문에서는 이러한 문제점을 해결하기 위하여 도입될 고객 바코드 인쇄제도를 지원하기 위한 우편용 3 of 5 고객 바코드 및 우편주소 검증시스템을 개발하였다. 고객 바코드 검증시스템은 정해진 규격에 의해 고객 바코드가 정확하게 인쇄되었는지 검사하는 검증자 3 of 5 고객 바코드 검증시스템, 바코드 판독결과에 의하여 우편주소가 올바르게 작성되었는지 검사하는 우편주소 검증시스템을 제공하는 것이다.

• 창의정보문화연구
• /
• 제5권2호
• /
• pp.145-156
• /
• 2019

본 연구에서는 명명된 실체 인식 기법에 기초한 정보 추출 모듈을 개발하고 평가하였다. 본 논문의 제시된 목적을 위해, 모듈은 사전 지식 없이 임의의 문서에서 우편 주소 정보를 추출하는 문제에 적용하도록 설계되었다. 정보 기술 실무의 관점에서, 우리의 접근방식은 유니그램 기반 키워드 매칭과 비교하여 일반화된 기법인 확률론적 n-gram(바이오그램 또는 트리그램) 방법이라고 말할 수 있다. 모델을 순차적으로 적용하지 않고 문장검출, 토큰화, POS 태그를 재귀적으로 적용하는 것이 우리의 접근법과 자연어 처리에 채택된 전통적인 방법 사이의 주요한 차이점이다. 이 논문에서는 약 2천 개의 문서를 포함한 시험 결과를 제시한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(3)
• /
• pp.37-40
• /
• 2000

A fast method of Hangul address word verification is presented in this Paper. Pre-segmentation and recognition by DP matching is adopted in this paper. An address line image is over-segmented by analyzing the topology of connected components and the projection profile. A fast individual Hangul character verifier was developed by applying SVM (Support Vector Machine). The segmentation hypothesis was represented by lattice structure, and a best path search by dynamic programming generates the most probable segmentation path and the final verification score. The word verifier was tested on 310 address image DB, and it show the possibility of improvements of this method.

• 한국소음진동공학회논문집
• /
• 제17권11호
• /
• pp.1050-1055
• /
• 2007

P.A.(public address) system is considered as an useful active soundscape appliance which can gives a place identity and vitality by introducing conventional musics, environmental musics, bird singing sounds etc. In this study, the main aim is to know the optimistic distance from the speaker and sound pressure level range of introducing sound. So, the sound pressure level of P.A. system due to distances were measured and subjects' responses with level variations were checked. The main results are as follows. Level range from 64 dB to 71 dB is comfortable for subjects. And the optimal level of introducing sound is related with sound source characteristics. The results of this study could be used for street furniture location design and P.A. system output level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권2호
• /
• pp.763-774
• /
• 2015

Hand posture recognition has been a wide region of applications in Human Computer Interaction and Computer Vision for many years. The problem arises mainly due to the high dexterity of hand and self-occlusions created in the limited view of the camera or illumination variations. To remedy these problems, a hand posture recognition method using 3-D point cloud is proposed to explicitly utilize 3-D information from depth maps in this paper. Firstly, hand region is segmented by a set of depth threshold. Next, hand image normalization will be performed to ensure that the extracted feature descriptors are scale and rotation invariant. By robustly coding and pooling 3-D facets, the proposed descriptor can effectively represent the various hand postures. After that, SVM with Gaussian kernel function is used to address the issue of posture recognition. Experimental results based on posture dataset captured by Kinect sensor (from 1 to 10) demonstrate the effectiveness of the proposed approach and the average recognition rate of our method is over 96%.

• ETRI Journal
• /
• 제41권6호
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• Journal of the Korean Physical Society
• /
• 제73권12호
• /
• pp.1908-1917
• /
• 2018

The binding affinity between the T-cell receptors (TCRs) and antigenic peptides mainly determines immunological recognition. It is not a trivial task that T cells identify the digital sequences of peptide amino acids by simply relying on the integrated binding affinity between TCRs and antigenic peptides. To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides. A pair of TCR and peptide sequences correspond to the input for ANNs, while the success or failure of the immunological recognition correspond to the output. The output is obtained by both theoretical model and experimental data. In either case, we confirmed that ANNs could learn the immunological recognition. We also found that a homogenized encoding of amino acid sequence was more effective for the supervised learning task.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.540-553
• /
• 2023

The hollow letter CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is an optimized version of solid CAPTCHA, specifically designed to weaken characteristic information and increase the difficulty of machine recognition. Although convolutional neural networks can solve CAPTCHA in a single step, a good attack result heavily relies on sufficient training data. To address this challenge, we propose a seed filling algorithm that converts hollow characters to solid ones after contour line restoration and applies three rounds of detection to remove noise background by eliminating noise blocks. Subsequently, we utilize a support vector machine to construct a feature vector for recognition. Security analysis and experiments show the effectiveness of this algorithm during the pre-processing stage, providing favorable conditions for subsequent recognition tasks and enhancing the accuracy of recognition for hollow CAPTCHA.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.27-32
• /
• 2024

Recently, there has been a growing interest in integrating physical toys into video gaming within the game content business. This paper introduces a novel method that leverages low-cost camera as an alternative to using sensor attachments to meet this rising demand. We address the limitations associated with low-cost cameras and propose an optical design tailored to the specific environment of model car recognition. We overcome the inherent limitations of low-cost cameras by proposing an optical design specifically tailored for model car recognition. This approach primarily focuses on recognizing the underside of the car and addresses the challenges associated with this particular perspective. Our method employs a transfer learning model that is specifically trained for this task. We have achieved a 100% recognition rate, highlighting the importance of collecting data under various camera exposures. This paper serves as a valuable case study for incorporating low-cost cameras into vision systems.