http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
최용수 한국소프트웨어감정평가학회 2024 한국소프트웨어감정평가학회 논문지 Vol.20 No.4
디지털 컨텐츠(이미지, 오디오, 비디오 등)에 대한 위변조 검출 기술은 오랜시간 동안 연구가 되어져 왔으나 디지털 문서에 대한 위변조 검출기술에 대한 연구는 많지 않았다. 문서에 대한 위조는 문서를 거짓된 정보로 생성하는 것이며 변조는 정상적으로 만들어진 문서에 대해 지우기, 복사-붙여넣기, 추가하기 등의 과정을 통해 의도적인 정보의 오류를 생성해내는 것이다. 본 논문에서는 실제 전자화된 문서의 위변조 검출을 다루고자 한다. 디지털 문서의 위변조는 사회적으로 다양한 분야에서 발생한다. 특히, 디지털 문서는 워드 프로세서에 의해 생성된 전자문서와 스캐너 등에 의해 생성되는 전자화 문서로 나눌 수 있어 분리된 기술적 접근이 필요하다. 본 논문을 통해 전자화문서에서 실제 위변조에 의한 특징을 찾아낼 수 있는지 그리고 유의미한 위변조 특징으로서의 가치를 가지는지 확인하고자 한다. 디지탈문서의 단순 위변조 현상을 측정한 결과약 39% 픽셀에 에너지 변화가 발생하며 픽셀 평균 2.29정도의 픽셀 값 변화가 발생하는 것을 측정하였다. Forgery detection technology for digital contents (images, audio, video, etc.) has been studied for a long time, but there has been little research on forgery detection technology for digital documents. Fabrication of documents is the creation of false information in documents, and Falsification is the creation of intentional information errors through processes such as erasing, copying, and adding to normally created documents. This paper deals with the detection of falsification rather than fabrication. Forgery of digital documents occurs in various social fields. In particular, digital documents can be divided into electronic documents created by word processors and electronized(scanned) documents created by scanners or word processor, etc., and therefore require separate technical approaches. Through this paper, we aim to verify whether it is possible to find characteristics due to actual forgery in electronic documents and whether they have value as meaningful forgery characteristics. Through metrics, we measured that energy changes occur in approximately 39% of pixels and an average pixel value change of approximately 2.29 occurs in pixels simply by copying objects in digital documents.
Drive-Thru매장 Touch Panel의 편의성을 위한 주문자 높이 검출 시스템
최용수 한국소프트웨어감정평가학회 2022 한국소프트웨어감정평가학회 논문지 Vol.18 No.1
Drive-thru stores have been structured for the convenience of service providers users. However, there were few technical attempts for user convenience and service provider efficiency in actual usage. In this paper, we aim to develop an efficient ordering system for efficient operation for service providers and improvement of user satisfaction in drive-thru stores. In particular, in order to exclude the use of additional sensors, most services were implemented using the image recognition technology of the camera. The efficiency of drive-thru use has been improved through proposed automation including vehicle entry, vehicle type classification, and screen output(menu display) location of the touch pannel.
L0 Norm 기반의 LE(Local Effect) 연산자를 이용한 디지털 이미지 위변조 검출 기술 개발
최용수 한국소프트웨어감정평가학회 2020 한국소프트웨어감정평가학회 논문지 Vol.16 No.2
Digital image forgery detection is one of very important fields in the field of digital forensics. As the forged images change naturally through the advancement of technology, it has made it difficult to detect forged images. In this paper, we use passive forgery detection for copy paste forgery in digital images. In addition, it detects copy-paste forgery using the L0 Norm-based LE operator, and compares the detection accuracy with the forgery detection using the existing L2, l1 Norm-based LE operator. In comparison of detection rates, the proposed lower triangular(Ayalneh and Choi) window was more robust to BAG mismatch detection than the conventional window filter. In addition, in the case of using the lower triangular window, the performance of image forgery detection was measured increasingly higher as the L2, L1 and L0 Norm LE operator was performed.