• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.201-204
• /
• 1997

최근 주소를 자동으로 인식하여 우편물 분류와 같은 업무를 효과적으로 수행하기 위한 연구가 진행되고 있다. 기존 연구들은 낱자 단위의 인식을 수행한 후 사전 형태의 간단한 DB를 통해 최종의 결과를 생성한다. 그러나 한글과 같은 복잡한 구조의 필기 문자에 대한 인식기의 성능은 아직도 미흡한 상태이다. 따라서 낱자 인식기의 성능에 의존하는 현재와 같은 방법으로는 만족할 만한 결과를 얻기가 힘들 것으로 생각된다. 본 논문에서는 낱자 인식 결과에 크게 의존하지 않고 주소에 나타나는 단어의 낱자들 사이간 연결 정보를 이용하여 단어를 인식할 수 있는 시스템을 제안한다. 본 시스템은 통계적 인식기를 사용하여 낱자를 인식하는 부분과 낱자 인식 결과를 조합하여 단어 수준의 인식과정을 통해 최종의 결과를 생성하는 부분으로 구성된다. 통계적 인식기는 Nearest neighborhood 방법을 사용하여 간단한 형태로 구현하였다. 단어인식 모듈은 단어에서 모든 문자간의 관계를 표현할 수 있도록 HMM 모형을 사용하여 어휘정보 네트워크를 구성하고 이를 이용하여 주소에 나타나는 단어를 인식하도록 하였다. PE92 한글 문자 데이터를 이용하여 실험을 수 璿\ulcorner 결과, 통계적 인식기의 성능이 저조함에도 불구하고 HMM을 이용한 어휘정보 네트워크가 이를 보완함으로써 좋은 결과를 얻었다. 이러한 단어 인식 방법을 주소 이외의 다른 단어 집합에 대해서도 쉽게 적용될 수 있을 것으로 예상된다.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.429-442
• /
• 2003

In this paper, we describe an address image recognition system for automatic processing of standard- size letter mail. The inputs to the system are gray-level mail piece images and the outputs are delivery point codes with which a delivery sequence of carrier can be generated. The system includes five main modules; destination address block location, text line separation, character segmentation, character recognition and finally address interpretation. The destination address block is extracted on the basis of experimental knowledge and the line separation and character segmentation is done through the analysis of connected components and vortical runs. For recognizing characters, we developed MLP-based recognizers and dynamical programming technique for interpretation. Since each module has been implemented in an independent way, the system has a benefit that the optimization of each module is relatively easy. We have done the experiment with live mail piece images directly sampled from mail sorting machine in Yuseong post office. The experimental results prove the feasibility of our system.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.3-10
• /
• 1999

This paper describes the development and evaluation of a Korean address input system employing automatic speech recognition technique as user interface for input Korean address. Address consists of cities, provinces and counties. The system works on a window 95 environment of personal computer with built-in soundcard. In the speech recognition part, the Continuous density Hidden Markov Model(CHMM) for making phoneme like units(PLUs) and One Pass Dynamic Programming(OPDP) algorithm is used for recognition. For address recognition, Finite State Automata(FSA) suitable for Korean address structure is constructed. To achieve an acceptable performance against the variation of speakers, microphones, and environmental noises, Maximum a posteriori(MAP) estimation is implemented in adaptation. And to improve the recognition speed, fast search method using variable pruning threshold is newly proposed. In the evaluation tests conducted for the 100 connected words uttered by 3 males the system showed above average 96.0% of recognition accuracy for connected words after adaption and recognition speed within 2 seconds, showing the effectiveness of the system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.619-621
• /
• 2004

ARP는 IP 네트워크 상에서 IP 주소를 물리적 네트워크 주소로 대응시키기 위해 사용되는 프로토콜이다. 네트워크에서 데이터를 전송할 때는 컴퓨터간의 물리적 주소를 이용하여 전승하는데 이 물리적 주소는 각각의 랜카드마다 고유하게 갖는 값으로 네트워크에서는 실제로 데이터를 전달할 때 네트워크 카드가 가진 물리적 주소를 이용하여 전달 하지만 소프트웨어 차원에서는 IP 주소라는 것을 사용한다. ARP 프로토콜은 IP 주소를 실질적인 네트워크 어댑터의 물리적 주소와 연관시킬 때 사용되는 것이다. 본 논문에서는 ARP 동보 패킷을 이용한 네트워크 강시 대상 노드들의 정보를 자동적으로 구축하는 기능을 갖는 네트워크 모니터링 시스템을 설계하고 구현한다. 본 네트워크 모니터링 시스템은 ARP 동보 패킷을 분석하여 네트워크 감시 대상 노드들을 인식하고 NETBIOS 모듈을 이용한 노드 이름 확인과 Ping 모듈을 이용한 노드 상태 및 정보를 표시하며 주기적인 업데이트를 통해 노드 정보를 표시하는 기능을 갖는다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.74-88
• /
• 2007

In order to automate the process of mail sorting by delivery sequence, it is necessary to prepare a postal address database and to interpret written addresses on the mail-pieces with the database and OCR technology. The address database is a critical factor of automation and informatization of postal service since it could be used not only in address recognition but also in various mail processing. In this study, we design the schema of postal address database, design the postal address file based on it and explain the method of address interpretation and retrieval using it. We analyze infonnation requirements for transformation of postal address into the standardized format and consider them in the process of design. The postal address file can be used by address matching or retrieval system as well as by Hangul address recognition system for automation of delivery sequence mail-sorting.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.703-708
• /
• 2004

Currently the amount of general letter mail in Korea is on an increasing trend; especially it shows the seasonality that is concentrated in the end of the month or the year. However, the situation is not treated appropriately Moreover. manpower insufficiency if the carriers causes the poor service and the heavy burden of work. Under the existing conditions, the various efforts such as development of the automatic sequence sorting system and construction of the address database are given in order to quicken mall process and lighten the carriers' burden But the inconsistent addressing and the various expressions of address drop the systems and the carriers off in efficiency. In this study, we present the Korean postal addressing standards to make it possible to improve the performance of address recognition and help postmen to sort the mail; particularly focusing on the substance. After analyzing the domestic system, the information structure and the problems of postal address, we propose four fundamentals and the standards including synonyms and acronyms. In addition, we suggest several considerations for mail format. We expect that this study could support the postal service in Korea as a basic standard.

• The KIPS Transactions:PartD
• /
• v.8D no.3
• /
• pp.273-284
• /
• 2001

A systematic approach for interpreting Korean addresses based on postal code is presented in this paper. The implementation is focused on producing the final delivery point code from various types of address recognized. There are two stages in the address interpretation : 1) agreement verification between the recognized postal code and upper part of the address and 2) analysis of lower part of the address. In the agreement verification procedure, the recognized postal code is used as the key to the address dictionary and each of the retrieved addresses is compared with the words in the recognized address. As the result, the boundary between the upper part and the lower part is located. The confusion matrix, which is introduced to correct possible mis-recognized characters, is applied to improve the performance of the process. In the procedure for interpreting the lower part address, a delivery code is assigned using the house number and/or the building name. Several rules for the interpretation have been developed based on the real addresses collected. Experiments have been performed to evaluate the proposed approach using addresses collected from Kwangju and Pusan areas.

• Journal of KIISE:Software and Applications
• /
• v.30 no.10
• /
• pp.904-911
• /
• 2003

In this paper, we propose an effective method for the distinction between machine-printed and handwritten Korean address images. It is important to know whether an input image is handwritten or machine-printed, because methods for handwritten image are quite different from those of machine-printed image in such applications as address reading, form processing, FAX routing, and so on. Our method consists of three blocks: valid connected components grouping, feature extraction, and classification. Features related to width and position of groups of valid connected components are used for the classification based on a neural network. The experiment done with live Korean address images has demonstrated the superiority of the proposed method. The correct classification rate for 3,147 testing images was about 98.85%.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.15-24
• /
• 2007

The recognition of postal address images is indispensable for the automatic sorting of postal envelopes. The process of the address image recognition is composed of three steps-address image preprocessing, character recognition, address interpretation. The extracted character images from the preprocessing step are forwarded to the character recognition step, in which multiple candidate characters with reliability scores are obtained for each character image extracted. aracters with reliability scores are obtained for each character image extracted. Utilizing those character candidates with scores, we obtain the final valid address for the input envelope image through the address interpretation step. The envelope sorting rate depends on the performance of all three steps, among which character recognition step could be said to be very important. The good character recognizer would be the one which could produce valid candidates with very reliable scores to help the address interpretation step go easy. In this paper, we propose the method of generating character candidates with reliable recognition scores. We utilize the existing MLP(multilayered perceptrons) neural network of the address recognition system in the current automatic postal envelope sorters, as the classifier for the each image from the preprocessing step. The MLP is well known to be one of the best classifiers in terms of processing speed and recognition rate. The false alarm problem, however, might be occurred in recognition results, which made the address interpretation hard. To make address interpretation easy and improve the envelope sorting rate, we propose promising methods to reestimate the recognition score (confidence) of the existing MLP classifier: the generation method of the statistical recognition properties of the classifier and the method of the combination of the MLP and the subspace classifier which roles as a reestimator of the confidence. To confirm the superiority of the proposed method, we have used the character images of the real postal envelopes from the sorters in the post office. The experimental results show that the proposed method produces high reliability in terms of error and rejection for individual characters and non-characters.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.589-592
• /
• 2001

본 논문에서는 고속 필기 한글 주소 인식을 위한 낱자 인식기를 제안한다. 인식 대상은 우편번호 여섯 자리에 할당된 주소에 출현 빈도가 높은 필기 한글 469 자이다. 제안된 방법은 낱자 인식 기법을 채택하고 있으며, 인식률과 처리속도를 향상시키기 위하여 2 단계 인식 전략을 채택하였다. 인식기로는 다층퍼셉트론, 최소거리분류기, Subspace 방법을 고려한다. 다층퍼셉트론은 비교적 높은 인식률과 처리속도를 보유하지만 출력값이 확률이 아님으로써 후처리를 필요로 하는 시스템에서 사용하기 어렵다. 최소거리분류기는 간단한 알고리즘으로 처리속도가 높고 확률을 출력하는 장점을 갖지만 인식률이 낮아 활용되기 어렵다. 또한 Subspace 방법은 인식률이 높고 확률을 출력하지만 처리속도가 매우 느리다는 단점이 있다. 따라서 제안방법에서는 처리속도가 높은 인식기 - 다층퍼셉트론, 최소거리분류기 - 를 사용하여 선인식을 수행한 후, 이 결과를 활용하여 인식 대상을 제한한 후 Subspace 방법을 사용하여 정확하게 인식하는 전략을 도입함으로써, 높은 인식결과를 유지하면서 처리속도를 높이고 후처리에 적합하도록 하였다. PE92 데이터베이스를 사용하여 실험한 결과 제안방법이 한글 469 자에 대하여 비교적 높은 인식률과 처리속도를 갖음을 알 수 있었다.