• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.121-124
• /
• 2004

This paper proposed the method of creating image mosaic in automated fashion. It is well known that geometric and radiometric balance in adjacent images should be maintained in mosaicking process. The seam line to minimize geometric discontinuity was extracted using Minimum Absolute­Gray-Difference Sum considering constraint condition in search width. To maintain the radiometric balance of images acquired at different time, we utilized Match Cumulative Frequency, Match Mean and Standard Deviation and Hue Adjustment algorithm. The mosaicked image prepared by the proposed method was compared with those of commercial software. Experiments show that seam lines were extracted significantly well from roads, rivers. ridgelines etc. and Match Cumulative Frequency algorithm was performed pretty good in histogram matching

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권3호
• /
• pp.225-230
• /
• 2008

In this paper we embody a system that recognizes printed alphabet, numeral figures and symbols written on the keyboard for the recognition of English sentences. The image of the printed sentences is inputted and binarized, and the characters are separated by using histogram method that is the same as the existing character recognition method. During the abstraction of the individual characters, we classify one group that has not numerical information by the projection of the vertical center of the character. In case of another group that has the longer width than the height, we assort them by normalizing the width. The other group normalizes the height of the images. With the reverse application of the basic principle of the Japanese Puzzle to a normalized character image, the proposed system classifies and recognizes the printed numeral figures, symbols and characters, consequently we meet with good result.

• 한국정밀공학회지
• /
• 제10권3호
• /
• pp.168-174
• /
• 1993

A new digital image processing method for measuring of the flank wear of cutting tool is presented. The method is based on computer vision technology in which the tool is illuminated by two halogen lamps and the wear zone is visualized using a CCD camera. The image is converted into digital pixel and processed to detect the wearland width. As a conclusion, it has been proved that the average wearland area and mzximum peak values of the flank wear width can monitored effectively to a measuring resolution of 0.01mm.

• 한국의상디자인학회지
• /
• 제14권2호
• /
• pp.89-100
• /
• 2012

The purpose of this research is to compare the body proportion of the Mongolian and Korean men and women in their 20' s by comparing the characteristics of the body type that uses the body indexes, in order to provide the base data for the increased fit of the apparels. The results are as follows. 1) Histogram of the Rohrer' s Index for the Mongolian men and women in their 20s was examined. the Mongolian men, normal body type took up 48.0% while small body type comprised 50.0% and obese body type comprised 2.0%. the Mongolian women, normal body type comprised 61.5%, small body type comprised 22.1% and obese body type comprised 16.4%. 2) The body proportion of Korean men has 1:1.62 with upper body and low body part on a waist basis, and Mongolian men has 1:1.65. Thus Mongolian men has longer pan of lower body than Korean men. 3) Mongolian women has longer part of lower body and has higher rates of hip height, crotch height, knee height than Korean women. Mongolian women has high rate of hip line and calf length. 4) As a result comparison using the body index of Mongolian and Korean women (bust thickness/ bust width, waist thickness / waist width, hip thickness / hip width, when regarding the height as 100 ), it was found that Mongolian women are flatter than korean women.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1679-1689
• /
• 2016

Recently, due to the rapid development of multimedia technologies, as image data has been extensive and large-scaled, the problem of increasing the time needed to retrieve the desired image is gradually critical. Image retrieval system that allows users to quickly and accurately search for the desired image information has been researched for a long time. However, in the case of content-based image retrieval representative Color Histogram, Color Coherence Vectors (CCV), Scale Invariant Feature Transform (SIFT) used in sensitive to changes in brightness, rotation, there is a problem that can occur misrecognized division off the power. In this paper, in order to evaluate the video retrieval system proposed, no change in brightness, respectively 0°, 90°, 180°, 270° rotated brightness up based on the case of changing, when the brightness down the results were compared with the performance evaluation of the system is an average of about 2% to provide the difference in performance due to changes in brightness, color histogram is an average of about 12.5%, CCV is an average of about 12.25%, it appeared in the SIFT is an average of about 8.5%, Thus, the proposed system of the variation width of the smallest in average about 2%, was confirmed to be robust to changes in the brightness and rotation than the existing systems.

• Imaging Science in Dentistry
• /
• 제43권3호
• /
• pp.153-161
• /
• 2013

Purpose: To prevent low bone mineral density (BMD), that is, osteoporosis, in postmenopausal women, it is essential to diagnose osteoporosis more precisely. This study presented an automatic approach utilizing a histogram-based automatic clustering (HAC) algorithm with a support vector machine (SVM) to analyse dental panoramic radiographs (DPRs) and thus improve diagnostic accuracy by identifying postmenopausal women with low BMD or osteoporosis. Materials and Methods: We integrated our newly-proposed histogram-based automatic clustering (HAC) algorithm with our previously-designed computer-aided diagnosis system. The extracted moment-based features (mean, variance, skewness, and kurtosis) of the mandibular cortical width for the radial basis function (RBF) SVM classifier were employed. We also compared the diagnostic efficacy of the SVM model with the back propagation (BP) neural network model. In this study, DPRs and BMD measurements of 100 postmenopausal women patients (aged >50 years), with no previous record of osteoporosis, were randomly selected for inclusion. Results: The accuracy, sensitivity, and specificity of the BMD measurements using our HAC-SVM model to identify women with low BMD were 93.0% (88.0%-98.0%), 95.8% (91.9%-99.7%) and 86.6% (79.9%-93.3%), respectively, at the lumbar spine; and 89.0% (82.9%-95.1%), 96.0% (92.2%-99.8%) and 84.0% (76.8%-91.2%), respectively, at the femoral neck. Conclusion: Our experimental results predict that the proposed HAC-SVM model combination applied on DPRs could be useful to assist dentists in early diagnosis and help to reduce the morbidity and mortality associated with low BMD and osteoporosis.

• 정보과학회 논문지
• /
• 제45권3호
• /
• pp.288-293
• /
• 2018

최근 공개되는 데이터에 적용하는 다양한 프라이버시 보호 기법들이 연구가 되어왔다. 그 중 차분 프라이버시는 본래의 데이터에 확률적인 노이즈를 더하여 공격자의 사전 지식에 상관없이 개인 정보를 보호한다. 기존 차분 프라이버시를 만족하는 k-평균 클러스터링은 데이터로부터 차분 프라이버시를 만족하는 히스토그램 형태로 바꾼 뒤. k-평균 클러스터링 알고리즘을 수행한다. 하지만 이는 데이터의 분포와 상관없이 등간격으로 히스토그램을 만들기 때문에 노이즈가 삽입되는 버킷이 많아지는 단점이 있다. 이를 해결하기 위해 본 논문에서는 데이터의 분포를 더 적은 버킷으로 나타낼 수 있는 쿼드 트리를 이용하여 히스토그램을 만든 뒤 k-평균을 찾는 알고리즘을 제안한다. 또한, 실험을 통해 기존의 알고리즘보다 더 좋은 성능을 가지는 것을 보인다.

• 대한수의학회지
• /
• 제38권4호
• /
• pp.918-928
• /
• 1998

The present study was done with two aims. First, to evaluate the radiographic measurements of liver volumes in normal and hepatomegaly dogs induced by carbon tetrachloride. Second, to investigate quantitative tissue echo pattern by ultrasonography. Gray level histogram of the normal liver and the kidney were estimated with carbon tetra-chloride intoxication. In normal, r-square for liver volume to body weight was 0.93372, and this showed direct linear regression. Gray level histograms of the normal liver and the kidney were $19.150{\pm}2.490$(mean${\pm}$SD) and $13.175{\pm}2.686$(mean${\pm}$SD) respectively(p < 0.01). Liver parenchymal echogenicity was more hyperechogenic than kidney cortex echogenicity. Liver/Kidney ratio was $1.504{\pm}0.313$ and it can be used relative comparison of liver and kidney parenchymal echogenicity. In carbon-tetrachloride($CCl_4$) intoxication, changes of liver volume appeared to increase up to 24 hours after administration (p < 0.05), and decreased gradually to normal level after 2~5 days. Gray level histogram of liver parenchyma decreased up to 24hours (p < 0.01) after intoxication and then gradually increased to normal level. But that of kidney cortex had no significant change. Liver/Kidney ratio also decreased by 2 days(p < 0.01) and then gradually increased to normal level. On histopathologic features of hepatic tissues in carbon tetrachloride intoxication, both coagulative necrosis of hepatic cell and hemorrhage of centrilobular & midzonal area were identified. Conclusively, plain radiography is a useful diagnostic method for evaluating liver volume in mild hepatomegaly. Especially, it is considered that an adequate numerical processing of the liver length, depth and thoracic width and depth measurement would be helpful. Using gray level histogram, ultrasonographic evaluation was useful objective methods in early diagnosis of diffuse hepatic disease.

• 한국콘텐츠학회논문지
• /
• 제18권4호
• /
• pp.398-405
• /
• 2018

HCI 분야에서 대표적인 손 제스처 인식은 IT기기의 개발과 더불어 사용자와 기기 간의 상호작용 및 정보교환을 위한 방법으로 주목받고 있다. 영상 처리를 통한 손 제스처 인식에서 손바닥 영역 검출은 처리속도 및 인식률 향상에 기여하는 핵심 처리 과정이다. 본 논문에서는 손바닥 영역 검출(palm area detection)을 위해 손과 손목을 영상 분할(image segmentation) 하는 새로운 방법을 제안한다. 손의 해부학적 특성으로 가장 넓은 폭이 발생하는 엄지와 소지의 장골 간격을 손 영상의 수평 투사 히스토그램으로 계산 후 이 간격을 지름으로 하는 원을 그려 손바닥 영역을 검출한다. 이 방법의 우수성을 검증하기 위하여 다단 형판정합(multiple stage template matching)을 사용해 10가지 손 제스처에 대해 기존 방법 4가지와 인식 성능을 비교 평가한다. 손 제스처 인식에 관련한 연구가 다양하나 손바닥 영역 검출에 특화된 성능 비교 문헌이 저조함을 강조한다.