• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.213-221
• /
• 2022

Intelligent Character Recognition System for Account Payable (ICRS AP) Automation represents the process of capturing text from scanned invoices and extracting the key fields from invoices and storing the captured fields into properly structured document format. ICRS plays a very critical role in invoice data streamlining, we are interested in data like Vendor Name, Purchase Order Number, Due Date, Total Amount, Payee Name, etc. As companies attempt to cut costs and upgrade their processes, accounts payable (A/P) is an example of a paper-intensive procedure. Invoice processing is a possible candidate for digitization. Most of the companies dealing with an enormous number of invoices, these manual invoice matching procedures start to show their limitations. Receiving a paper invoice and matching it to a purchase order (PO) and general ledger (GL) code can be difficult for businesses. Lack of automation leads to more serious company issues such as accruals for financial close, excessive labor costs, and a lack of insight into corporate expenditures. The proposed system offers tighter control on their invoice processing to make a better and more appropriate decision. AP automation solutions provide tighter controls, quicker clearances, smart payments, and real-time access to transactional data, allowing financial managers to make better and wiser decisions for the bottom line of their organizations. An Intelligent Character Recognition System for AP Automation is a process of extricating fields like Vendor Name, Purchase Order Number, Due Date, Total Amount, Payee Name, etc. based on their x-axis and y-axis position coordinates.

• 대한예방한의학회지
• /
• 제5권1호
• /
• pp.10-30
• /
• 2001

Oriental medicine needs to be armed with theories on health-improvement concept under it and basic data matching its views, in order to participate in the health-improvement service in industrial work places. The Orient medicine health-improvement program defines factors that determine individuals' lifestyle, and provides information and technologies for workers to practice in life. To that end, this research compares and analyzes health-improvement concept and health care, defines relations between individuals' health state and their lifestyle as the basic data needed to perform health-improvement business for workers. 1. The subjects employed for this research is categorized into; by gender, males 52.1% and females 47.9% with no big difference between them; and by age, 20s, 6.1%, 30s. 33.9%, 40s, 34.1%, and 50s, 24.8% with 30-50 accounting for most of it. By marriage status, unmarried represents 7.1%, and married 79.1% with most of them married; by revenue, under one million won represents 3.0%, 1-2 million won 26.4%, 2-2.49 million won 11.2%, above 2.5 million won 11.2%, and 1-2.5 million won a majority. By living location, owned houses represents 65.4%, rented houses 14.7%, monthly-rented 9.5%; and by education, elementary and middle school represent 16.9%, high school and its dropouts 22.6%, and junior college and higher 51.6%, with high school and higher occupying most of the group. 2. By job, office workers and managerial workers represent 12.3%, part-timers 21.0%, manual workers 11.4%, jobless 0.6%, professionals 35.6%, service 0.6%, housewives 8.4%, and equipment/machinery operation/assemblers 10.1%. Of this, jobless and part-timers, totaling three, are dropped from this research. By years worked, 0-3.9 years represents 9.7%, 4-7.9 years 6.7%, 8-14.9 years 18.4%, above 15 years 28.7%, and no respondents 36.5%. 3. The degree of the subjects practicing life-improvement lifestyle, on a scale of 1 to 4, is an average of 2.69, personal relations 3.04, self-realization 2.92, stress management 2.76, nutritional state 2.73, responsibility for health 2.47, and athletic activities 2.18, with personal relations earning the highest points and athletic activities the lowest. As for factors influencing health-improvement lifestyle, there is no significant difference between gender, age, and marriage status. Meanwhile, there is significant difference between revenue, dwelling pattern, education level, etc. That is, higher income-bracket, owned houses, rented houses, monthly-rented houses, and higher-educated, in this order, show higher average in health-enhancement lifestyle. By job, housewives, manual workers, office workers, professionals, equipment/ machinery operation/ assemblers, and part-timers, in this order show higher points, while there is no difference with significance by years worked. 4. Factors that affect health-improvement lifestyle are shown below. Self-realization is influenced by age, marriage status, type of dwellings, and level of education; responsibility for health by type of dwellings; athletic activities by gender and age; nutrition by age, marriage status and type of dwellings; personal relations by marriage status; and stress management by type of dwellings. 5. Areas with high points by job show this: in self-realization, office workers, manual workers, housewives, professionals, equipment/ machinery operation/ assemblers, in this order, show difference with significance; in the area of responsibility for health, manual workers, housewives, equipment/ machinery operation/ assemblers, professionals, office workers and part-timers, in this order, do. In athletic activities, manual workers, housewives, office workers, professionals, equipment/ machinery operation/ assemblers, and part-timers, in this order, show difference with significance; in nutrition, housewives, office workers, manual workers, professionals, equipment/ machinery operation/ assemblers, and part-timers, in this order do; and in stress, housewives, office workers, manual workers, professionals, equipment/ machinery operation/ assemblers, part-timers, in this order do. By years worked, more years showed higher points in the area of responsibility for health and nutrition; in the area of athletic activities, above 15 years, 4-8 years, below 4 years and 8-14 years, in this order, show higher points; and no difference shows in realization, personal relation, and stress area. 6. To look at correlation between overall and divisional health-improvement practice degree, this researcher has analyzed it using Person's correlation coefficient. Self-realization, responsibility for health, athletic activities, nutrition, support for personal relations, and stress management show significant correlation with the sub-divisions, while all health-improvement lifestyle shows significant correlation with the six sub-divisions.

• 정보처리학회논문지D
• /
• 제11D권5호
• /
• pp.1063-1072
• /
• 2004

ASP(Application Service Provider) 사업에서 응용프로그램이 데이터베이스를 사용해야 하고 이 데이터베이스가 ASP 고객의 데이터베이스로부터 일련의 데이터를 제공받아야 하는 경우가 점점 더 증가하고 있다. 이를 위한 방법으로 엑셀(EXCEL)과 같은 파일 형태가 이용되는데 고객의 데이터베이스로부터 수작업으로 추출되어진 데이터가 엑셀 파일로 ASP사업자에게 전달된다. 이는 다시 애플리케이션이 이용하는 데이터베이스의 테이터내로 수작업 처리되어 저장된다. 본 연구는 두 데이터베이스 연동 시에 이러한 엑셀 파일 등을 이용하여 발생하는 데이터 추출과 저장시의 데이터베이스 수작업 조작의 비효율성을 극복하는데 있다. 이 때 두 데이터베이스 상의 속성명은 상이한 경우를 일반적인 경우로 전제하였으며 또한 웹 상에서 두 데이터베이스의 연동 시에 피할 수 없는 고객 데이터베이스의 경로 정보를 ASP 사업자에게 노출을 피하도록 한다. 제안된 방법은 두 단계로 걸쳐 데이터 프로세싱이 이루어지는데 먼저, ASP 사이트로부터 다운로드받은 프로그램을 이용하여, 고객데이터베이스를 접속한 후 프로그램의 유저 인터페이스를 이용하여 용이하게 속성 매칭하고 속성치를 XML 파일 형태로 자동 추출하는 단계와 추출된 XML 파일을 웹 상에서 ASP 서버에 접속하여 전송하고 ASP 데이터베이스에 자동 저장하는 후처리 프로세싱 단계로 구성된다. 본 연구에서는 이러한 방법에 맞는 프로토타입 시스템을 구현하여 데이터베이스 연동의 타당성을 검증하였으며, 제안된 방법은 ASP 고객의 데이터베이스를 이용해야 하는 ASP사업의 활성화에 기여할 수 있다.

• 대한공간정보학회지
• /
• 제24권4호
• /
• pp.115-123
• /
• 2016

지난 2012년부터 도로명주소가 본격 시행 및 활용되고 있지만, 아직도 상당 부분에서는 기존의 지번주소가 많이 통용되고 있다. 이는 일반인들의 공간 인식체계와 도로명주소의 공간 구조화 방식의 간극으로 인한 문제이다. 따라서 도로명주소 기반의 공간 인식 체계가 자리잡기 위해서는 생활 속에서 활용되는 각종 공간정보들이 도로명에 의하여 주소정보를 부여받을 수 있어야 한다. 본 연구는 공간 인식 과정이 가장 중요하게 나타나는 길찾기 과정에서의 도로명주소 체계의 연계를 목적으로, 이를 위하여 필요한 공간데이터의 기하학적 매칭 방법론을 설계 및 구현하였다. 도로명주소 기본도의 도로구간 레이어와 보행자용 도로 네트워크에 대하여, 개별 도로 객체를 중심으로 네트워크 이웃을 생성하였다. 그 다음, 생성된 이웃 집합 간의 기하학적 유사도 비교를 통하여, 네트워크 데이터의 각 객체에 매칭되는 도로구간을 탐색하였다. 매칭 성능은 F0.5 값을 기준으로 0.936의 결과를 얻었으며, 유사도 값을 기준으로 10% 수동 검사를 수행한 결과 이 값을 0.978까지 향상시킬 수 있었다. 이렇게 생성된 매칭 대응관계를 이용하여, 보행자용 도로 네트워크 데이터에 도로명 정보를 부여하였다. 이러한 방법론을 통하여, 도로명주소를 기반으로 한 길찾기 서비스 제공 및 공간 인식체계 정착에 도움을 줄 수 있다.

• 대한토목학회논문집
• /
• 제37권2호
• /
• pp.445-449
• /
• 2017

현재까지의 드론을 이용한 대부분의 연구는 지상에서의 활용 및 규제에 관한 연구가 주로 이루어 졌다. 비행시간과 영상정합의 한계로 해양에서의 드론은 거의 사용되지 않는다. 본 연구는 수상에서 드론을 이용한 영상정합을 위한 기초 연구로 부표를 이용한 임의의 수상기준점을 통해 영상을 정합하고 정확도를 분석하였다. 수상기준점을 이용한 영상정합의 정확도는 항공사진측량과 동일하게 기준점의 정확도에 영향을 받으며, 수상에 설치된 임의의 수상기준점은 풍속, 유속 등 다양한 환경요소의 영향으로 위치가 계속 변화한다. 움직이는 수상기준점의 좌표는 Total Station과 VRS를 이용해 중복 측량하였다. 실험은 김해시 저수지 2곳에서 수행하였으며, 수상기준점을 활용한 수동영상정합 정확도는 각각 40 cm와 80 cm 이다. 해양경계측량의 허용오차가 ${\pm}2m$ 이므로 본 연구 결과는 충분히 활용 가능한 것으로 평가된다. ${\pm}2m$ 이내의 정확도를 확보하기 위한 수상기준점의 최대 위치오차는 1.8 m 이다.

• Genomics & Informatics
• /
• 제18권2호
• /
• pp.23.1-23.6
• /
• 2020

The Human Phenotype Ontology (HPO) is the de facto standard ontology to describe human phenotypes in detail, and it is actively used, particularly in the field of rare disease diagnoses. For clinicians who are not fluent in English, the HPO has been translated into many languages, and there have been four initiatives to develop Japanese translations. At the Biomedical Linked Annotation Hackathon 6 (BLAH6), a rule-based approach was attempted to determine the preferable Japanese translation for each HPO term among the candidates developed by the four approaches. The relationship between the HPO and Mammalian Phenotype translations was also investigated, with the eventual goal of harmonizing the two translations to facilitate phenotype-based comparisons of species in Japanese through cross-species phenotype matching. In order to deal with the increase in the number of HPO terms and the need for manual curation, it would be useful to have a dictionary containing word-by-word correspondences and fixed translation phrases for English word order. These considerations seem applicable to HPO localization into other languages.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.735-739
• /
• 2005

This paper presents a new system to estimate the head pose of human in interactive indoor environment that has dynamic illumination change and large working space. The main idea of this system is to suggest a new morphological feature for estimating head angle from stereo disparity map. When a disparity map is obtained from stereo camera, the matching confidence value can be derived by measurements of correlation of the stereo images. Applying a threshold to the confidence value, we also obtain the specific morphology of the disparity map. Therefore, we can obtain the morphological shape of disparity map. Through the analysis of this morphological property, the head pose can be estimated. It is simple and fast algorithm in comparison with other algorithm which apply facial template, 2D, 3D models and optical flow method. Our system can automatically segment and estimate head pose in a wide range of head motion without manual initialization like other optical flow system. As the result of experiments, we obtained the reliable head orientation data under the real-time performance.

• 한국통신학회논문지
• /
• 제15권5호
• /
• pp.374-383
• /
• 1990

시각조사의 일은 대부분 숙련된 조사자에 의해 이루어지므로 시간이 경과 할수록 조사의 질은 감소한다. 그러므로 조사과정의 자동화가 요구되고 있으며, 실용적인 시각조사시스템을 위해서는 실시간에서의 데이터 처리능력, 다양한 입력물체에 대한 유연성 및 저렴한 시설비가 요구된다. 본 논문에서는 이러한 요구에 적합한 조사방법을 제안한다. 기존의 하드웨어 방식과는 달리 소프트웨어에 의해 조사데이터를 처리함으로써 조사시스템을 유연성 있게 하기 위하여 피라미드 데이터구조를 이용한 divide-and-conquer 기술과 간소화된 패턴 매칭방법을 결합한 시각조사 알고리즘을 제시한다. 이 방법에 의해 비교되는 패턴의 데이터 수를 감소시킬 수 있었고, 그 결과 조사속도를 줄일 수 있었다.

• 대한조선학회논문집
• /
• 제51권5호
• /
• pp.356-361
• /
• 2014

Accurate block shape assessment is critical for ship manufacturing and a careful assessment of the shape of a fabricated block against the design shape is a core issue. However, in current fabrication practice, the shape of each block is evaluated manually using rigid body transformation. This manual evaluation process entirely depends on workers' experiences and knowledge and makes automation of block shape assessment difficult. In this paper we propose a computation method on the registration for shape assessment of a block during the fabrication process and for evaluation of its completion against the design shape. A conversion on matching method by adding DOF(degree of freedom) restriction is required to reach the goals. We test our method using a real block quality assessment data to demonstrate its applicability to real ship manufacturing process.

• Advances in materials Research
• /
• 제6권3호
• /
• pp.233-243
• /
• 2017

This paper describes an investigation on the effect of using three different filler metals on fatigue behavior of mechanical structures welded. The welding is carried out on the steel A510AP used for the manufacture of gas cisterns and pipes. The welding process used is manual welding with coated electrodes and automatic arc welding. Compact tension CT50 specimen has been used. The three zones of welded joint; filler metal FM, heat affected zone HAZ and base metal BM have been investigated. The results show that the crack growth rate CGR is decreasing respectively in BM, FM and HAZ; however, this variation decreases when stress intensity factor SIF increases. For low values of SIF, the CGR is inferior in the over-matched filler metal of which the value of mismatch M is near unity, but for high values of M the CGR is superior, and the effect of the over-matching on CGR becomes negative. No deviation of the crack growth path has been noticed.