• The KIPS Transactions:PartB
• /
• v.17B no.6
• /
• pp.421-428
• /
• 2010

It takes a long time for the users to view a whole image from the image server under the low-bandwidth internet environments or in case of a big sized image. In this case, as there needs a technique that preferentially transfers a part of image, JPEG2000 offers a ROI(Region-of-Interest) coding. In ROI coding, the users see the thumbnail of image from the server and specifies some regions that they want to see first. And then if an information about the regions are informed to the server, the server preferentially transfers the regions of the image. The existing methods requested a huge time to compute the mask information, but this thesis approximately computes the regions and reduces the creating time of the ROI masks. If each code block is a mixed block which ROI and background are mixed, the proper boundary points should be acquired. Searching the edges of the block, getting the two points on the edge, to get the boundary point inside the code block, the method searches a mid point between the two edge points. The proposed method doesn't have a big difference compared to the existing methods in quality, but the processing time is more speedy than the ones.

• The Journal of Information Technology
• /
• v.10 no.3
• /
• pp.15-31
• /
• 2007

Region-of-Interest is the region within the image selected for the users needs. The development of multimedia has made the expectation of image telecommunication higher, but the usage of the image, image transmission time, and image storage create problems. When transmitter or the receiver stops transmission at some point, we can still see the general image and the ROI maintains better image quality if the ROI is specified beforehand. In this paper, three methods are proposed and constructed for the transmission of ROI. In the first method, the ROI and the background are separated and then encoded as described above. The second method is to encode without separating the ROI and the background. The masked region is scaled and the coefficients are increased, then the region is transmitted first. The third method is the loseless coding of the ROI. For loseless coding, real number tap cannot be restored perfectly due to the rounding error, so the method of using integers is used. The proposed method shows a better performance than EZW even in case of ROI's PSNR at quality of 40 dB.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04b
• /
• pp.1103-1106
• /
• 2002

현재, 컨베이어 벨트시스템에 소포를 직재하고, 우편번호를 운영자가 입력하여 구분한다. 구분된 소포 중에서 기록관리 대상의 경우에는 바코드를 판독하여 처리하고 있다. 이에 따라, 본 논문에서는 2m/sec 이내로 이송되는 소포를 라인 CCD(Charged Coupled Device) 카메라에 의해 이미지 획득한 후, 바코드 ROI 추출 방법을 위해 $32{\times}32$ 미세블룩 검사 방법을 적용하였다. ROI 추출 절차는 최대-최소 차이값과 동적 인계값 기준으로 바탕면 제거, 문자열과 바코드 영역을 판단하기 위한 대각선(diagonal) 검사방법 적용, 바코드 영역인지 검증하기 위해 수평으로 5 라인을 검사하고 에지의 수와 폭의 변화량 비교 등의 과정으로 수행하였다. 그리고 바코드 ROI 추출은 레이블링 과정에 의해 바코드 영역의 보정과 그룹크기 비교에 의한 ROI 영역의 구체화와 정보 해석을 위하여 ROI 외곽좌표 8개중에서 가장 간 중심축 라인으로 생성하는 방법 등을 적용하였다. ROI 추출과 중심축 시험결과에 의하면 $50{\sim}180msec$이내에 가능하게 되었다. 그리고, ROI 추출의 정확도는 99.994% 이상을 만족한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.511-513
• /
• 2016

본 논문에서는 세라믹 영상에서 사람의 눈으로 판단하기 어려운 결함 영역을 검출하기 위해 배경을 제거한 후에 지역 기반 오츠 이진화와 양방향 소벨 마스크를 적용하여 세라믹 영상의 윤곽선을 검출한다. 윤곽선이 검출된 영상을 수평으로 4등분하고, 각각의 영역에서 밝기 값이 변화는 지점을 탐색한다. 탐색된 좌표 중에서 최대 명암도 값을 이용하여 ROI 영역을 추출한다. 결함 영역 검출의 효율성을 높이기 위한 전 단계로 배경을 제거하기 위해 ROI 영역과 최소값 필터가 적용된 ROI 영역 간의 명암도의 차이를 이용하여 배경을 제거한다. 명암도의 차이를 통해 배경이 제거된 ROI 영역에서 개선된 명암 대비 스트레칭 기법을 적용하여 ROI 영역의 명암 대비를 강조한다. 명암이 강조된 ROI 영역에서 10mm, 11mm, 16mm, 22mm 영상의 결함 영역을 검출하기 위해 히스토그램 이진화 기법을 적용하여 결함의 후보 영역을 추출한다. 결함 후보 영역이 검출된 ROI 영역에서 미세 잡음을 제거하기 위해 중간값 필터와 침식과 팽창을 적용한 후에 최종적인 결함 영역을 검출한다. 제안된 방법을 8mm, 10mm, 11mm, 16mm, 22mm 세라믹 영상을 대상으로 실험한 결과, 제안된 검출 방법이 기존의 검출 방법보다 모든 mm 세라믹 영상에서 효과적으로 결함 영역이 검출되는 것을 확인하였다.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2319-2322
• /
• 2003

We propose ROI(region of interest) image coding application to still image using PSBS(partial significant bitplane shift)method combined with human face region detecting system. PSBS is an encoding algorithm for ROI image coding in JPEG2000, and takes advantages of both generic scaling based method and maximum shift method defined in JPEG2000. The Powerful advantages of PSBS are able to adjusting image quality in ROI and background flexibly, and support arbitrarily shaped ROI coding without coding the shape. In this letter, we show how to compress an image for human face region using PSBS method combined with human face region detecting system, and propose its application.

• International Journal of Computer Science & Network Security
• /
• v.23 no.2
• /
• pp.39-46
• /
• 2023

The purpose of this study is to introduce a proposed Framework for Evaluating the Return on Investment (ROI) of E-Learning Programs at Saudi Universities. To achieve this goal, the descriptive analysis methodology is used to analyze the literature review about e-learning and its evaluation from different viewpoints, especially from the ROI-related perspective. As well as the literature reviews related to ROI and the methods of calculating it inside society institutes. This study suggests a conceptual framework for evaluating the ROI of E-Learning Programs at Saudi Universities. This framework is based on the merging process among the analyze, design, develop, implement, and evaluate (ADDIE) model for designing e-learning programs, which gives detailed procedures for executing the program, several evaluating models for e-learning, and the Kirkpatrick model for evaluating the ROI of e-learning. It consists of seven stages (analysis, calculating the costs, design, development, implementation, calculation of the benefits, and calculation of the final ROI).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.387-390
• /
• 2007

CMMI 도입은, 추진 이후 프로세스가 조직 내에 내재화되기까지, 상당한 기간과 인력이 소요되는 고비용의 조직 활동이다. 따라서 CMMI 도입 결정에 앞서 ROI 분석을 통한 정확한 의사결정이 필요하다. 지금까지의 CMMI 도입과 관련한 ROI산정방식은, CMMI 의 효과산정방식이 구체적이지 않고, 비용측면에 있어서도 프로세스 정의 및 수행비용을 중심으로 산정할 뿐, 지속적인 내재화에 소요되는 비용을 간과하고 있어, 의사결정지표로서 정확성이 결여되었다. 이에 본 논문은 수익성 개선과 생산성 개선에 기반을 두어 효과를 산정하고, 비용 산정은 프로세스 내재화에 따른 지속적 관리활동이라는 특징을 반영하여, 보다 실제적이고 정확한 ROI 분석 방법인 iROI 산정방법을 제안한다. 증명이 어려운 CMMI 투자성과 분석에 활용될 수 있으며, 타 투자분야와 비교할 수 있는 공정한 의사결정 판단근거로서 활용될 수 있다.

• Journal of radiological science and technology
• /
• v.29 no.4
• /
• pp.229-236
• /
• 2006

Purpose: This study was conducted to search for the type of technical error in DEXA(dual-energy X-ray absorptiometry) and the effect of error to measurement of BMD. Materials and Methods: The changes of BMD($g/cm^2$, T-score) by patients information(Age, Weight, Height, Manopause age) input error and Confirming ROI error were investigated. Using spine phantom, we canned 10 times by age(5, 10), weight(10, 20 kg), height(5, 10 cm), manopause age(5, 10) increase & decrease respectively. Scanning region(L-spine, femur, Forearm) of 10 patients was calculated by changing ROI respectively. Analysis of difference for mean(precision 1%) were carried out. Results: The error of patient information(Age, Weight, Height, Manopause age) was not changed differently. In confirming ROI, the BMD and T-score of L-spine involving T-12 was decreased to $0.063\;g/cm^2$, 0.3 and involving L-5 increased to $0.077\;g/cm^2$, 0.5. In narrowing 1 cm of vertical line of ROI, the BMD and T-score decreased to $0.006\;g/cm^2$, 0.1 and in 2 cm, $0.021\;g/cm^2$, 0.15, each. In hip ROI, Upper and left shift(0.5 cm) of line was not influenced BMD and T-score. In 0.5 cm lower shift(lesser trochanter below), the BMD and T-score increased $0.031\;g/cm^2$, 0.3 and in 1 cm $0.094\;g/cm^2$, 0.65, each. In forearm ROI, the BMD and T-score decreased $0.042\;g/cm^2$, 0.9 involving 1 cm lower wrist. And expanding 1 cm of vertical line, the BMD and T-score decreased $0.008\;g/cm^2$, 0.1 and in 2 cm, $0.021\;g/cm^2$, 0.3, each. The L-spine, hip, forearm ROI error was changed differently. Conclusion: There are so many kinds of technical error in BMD processing. Errors according to age, weight, height, manopause age did not influent to $BMD(g/cm^2)$ and T-score. There are mean differences BMD and T-score in confirming ROI. For the precision exam, in L-spine processing, L1-4 have to confirmed without shift of ROI vertical line. In hip processing, the ROI have to included greater trochanter, femur head and lesser trochanter. In forearm processing, the ROI have to included wrist, radius and ulnar.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.54-65
• /
• 2006

In this paper, we propose a new functionality to Scalable Video Coding (SVC), which is the support of multiple ROIs for heterogeneous display resolution. Scalable video coding is targeted at giving temporal, spatial, and quality scalability for the encoded bit stream. Region of interest (ROI) is an area that is semantically important to a particular user, especially users with heterogeneous display resolutions. The bitstream containing the ROIs could to be extracted without any transcoding operations, which may be one of way to satisfy QoS. To define multiple ROI in SVC, we adapted FMO, a tool defined in H.264, and based on it, we propose a way to encode and decode ROIs. The proposed method is implemented on the JSVM1.0 and the functionality is verified using it.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.253-264
• /
• 2009

This paper presents an algorithm, aims at practical applications, for the high speed processing and performance enhancement of lane detection base on vision processing system. As a preprocessing for high speed lane detection, the vanishing line estimation and the optimal extraction of region of interest for lane boundary (ROI-LB) can be processed to reduction of detection region in which high speed processing is enabled. Image feature information is extracted only in the ROI-LB. Road lane is extracted using a non-parametric model fitting and Hough transform within the ROI-LB. With simultaneous processing of noise reduction and edge enhancement using the Laplacian filter, the reliability of feature extraction can be increased for various road lane patterns. Since outliers of edge at each block can be removed with clustering of edge orientation for each block within the ROI-LB, the performance of lane detection can be greatly improved. The various real road experimental results are presented to evaluate the effectiveness of the proposed method.