• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• Journal of Korea Multimedia Society
• /
• v.18 no.10
• /
• pp.1189-1196
• /
• 2015

In this paper, we proposed automatic extraction of brain tumor using morphological operation and statistical tumors size in MR images. Neurosurgery have used gamma-knife therapy by MR images. However, the gamma-knife plan systems needs the brain tumor regions, because gamma-ray should intensively radiate to the brain tumor except for normal cells. Therefore, gamma-knife plan systems spend too much time on designating the tumor regions. In order to reduce the time of designation of tumors, we progress the automatical extraction of tumors using proposed method. The proposed method consist of two steps. First, the information of skull at MRI slices remove using statistical tumors size. Second, the ROI is extracted by tumor feature and average of tumors size. The detection of tumor is progressed using proposed and threshold method. Moreover, in order to compare the effeminacy of proposed method, we compared snap-shot and results of proposed method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.2 s.7
• /
• pp.1-11
• /
• 2005

Automatic tracking of vehicles is important to accurately estimate the vehicle speeds in video-based traffic measurement systems and to analyze traffic flows for road construction. This paper proposes a carefully designed rule-based tracking scheme that considers the possible cases that can be appeared in the video-based vehicle racking. The proposed scheme is fast and outperforms the Mean-Shift scheme in terms of accuracy. The accuracy and the speed of the scheme would be increased by combining it with color-based searching and Kalman filters.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.8
• /
• pp.1424-1429
• /
• 2016

Segmentation is one of the first steps in most diagnosis systems for characterization of dental caries in an early stage. The purpose of automatic dental cavity detection system is helping dentist to make more precise diagnosis. We proposed the semi-automatic method for the segmentation of dental caries on digital x-ray images. Based on a manually and roughly selected ROI (Region of Interest), it calculated the contour for the dental cavity. A snake algorithm which is one of active contour models repetitively refined the initial contour and self-examination and correction on the segmentation result. Seven phantom tooth from incisor to molar were made for the evaluation of the developed algorithm. They contained a different form of cavities and each phantom tooth has two dental cavities. From 14 dental cavities, twelve cavities were accurately detected including small cavities. And two cavities were segmented partly. It demonstrates the practical feasibility of the dental lesion detection using Computer-aided Detection (CADe).

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.1
• /
• pp.63-66
• /
• 2009

Purpose: ACR (American College of Radiology) offers variable parameters to PET/CT quality control by using ACR Phantom. ACR Phantom was made to evaluate parameters which are uniformity, attenuation, scatter, contrast and resolution. Manual analysis method wasn't good for the use of QC because values of parameter were changed as it may user and it takes long time to analysis. Ki-Chun Lim, a nuclear scientist in AMC, developed program that automatically analysis values of parameter by using ACR Phantom to overcome above problems. In this study, we evaluated automatic analysis program's usability, through the comparing SUV of each method, reproducibility of SUV when repeated analysis and the time required. Materials and Methods: Using Flangeless Esser PET Phantom, the ideal ratio of 4 : 1 hot cylinder and BKG but it actually showed a ratio of 3.89 to 1 hot cylinder and BKG. SIEMENS Biograph True Point 40 was used in this study. We obtained images using ACR phantom at Fusion WB PET Scan condition (2 min/bed) and 120 kV, 100 mAs CT condition. Using True X method, 3 iterations, 14 subsets, Gaussian filter, FWHM 4 mm and Zoom Factor 1.0, $168{\times}168$ image size. We obtained Max. & Min. SUV and SUV Mean values at Cylinder (8, 12, 16, 25 mm, Air, Bone, Water, BKG) by automatic program and obtained SUV by manual method. After that, we compared manual and automatic method. we estimate the time required from opened the image data to final work sheet was completed. Results: Automatic program always showed same result and same the time required. At 8, 12, 16 and 25 m cylinder, manual method showed 6.69, 3.46, 2.59, 1.24 CV values. The larger cylinder size became, the smaller CV became. In manual method, bone, air, water's CV were over 9.9 except BKG (2.32). Obtained CV of Mean SUV showed BKG was low (0.85) and bone was high (7.52). The time required was 45 second, 882 second respectably. Conclusions: As a result of difference automatic method and manual method, automatic method showed always same result, manual method showed that the smaller hot cylinders became, the lager CV became. Hot cylinders mean region size, the smaller hot cylinder size becomes we had some trouble in doing ROI poison setting. And it means increase in variation of SUV. The Study showed the time required of automatic method was shorten then manual method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.808-810
• /
• 2004

왜소증 조기진단을 위한 왼쪽 손의 방사선 영상을 통한 방법은 일반적으로 나이와 성별에 따른 방사선 영상들과 비교하여 의사가 직접 눈으로 비슷한 영상을 찾아 뼈 나이를 추정한다. 하지만 나이, 성별, 민족 등 여러 요인에 따라서 측정결과가 달라질 수 있고 각 나라별로 독자적인 기준이 필요하므로 본 논문에서는 한국인의 Carpal bone 분석과 이에 따른 Computerized Bone Age System을 제안한다. 뼈 나이 측정을 위해 6개의 연골을 측정하고, 분석할 6개의 연골 ROI(Region of Interest)를 찾기 위하여 연골들의 에지를 검출하였다. 영상의 에지를 검출하기 위하여 DoG (Difference of Gaussian) Filtering을 사용하였으며, Carpal Bone을 분석한 뒤 2차원 특징들로 ㅂW 나이 추정에 대한 진단의 정확도를 확인 할 수 있었다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.12
• /
• pp.1678-1684
• /
• 2018

Dental caries is one of the most popular oral disease. The aim of automatic dental cavity detection system is helping dentist to make accurate diagnosis. It is very important to separate cavity from the teeth in the detection system. In this paper, We compared two active contour algorithms, Snake and DRLSE(Distance Regularized Level Set Evolution). To improve performance, image is selected ROI(region of interest), then applied bilateral filter, Canny edge. In order to evaluate the algorithms, we applied to 7 tooth phantoms from incisor to molar. Each teeth contains two cavities of different shape. As a result, Snake is faster than DRLSE, but Snake has limitation to compute topology of objects. DRLSE is slower but those of performance is better.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2121-2127
• /
• 2017

In this paper, we propose a computer vision based automatic defect detection method from ceramic image for non-destructive testing. From region of interest of the image, we apply brightness enhancing stretching algorithm first. One of the strength of our method is that it is designed to detect defects of images obtained from various thicknesses, that is, 8, 10, 11, 16, and 22 mm. In other cases we apply histogram based binarization algorithm. However, for 8 mm case, it may have false positive cases due to weak brightness contrast between defect and noise. Thus, we apply modified fuzzy binarization algorithm for 8 mm case. From the experiment, we verify that the proposed method shows stronger result than our previous study that used Blob labelling for all five thickness cases as expected.

• Journal of Biomedical Engineering Research
• /
• v.25 no.2
• /
• pp.111-117
• /
• 2004

Most of digital subtraction methods in dental radiography are based on registration using manual landmarks. We have developed an automatic registration method without using the manual selection of landmarks. By restricting a geometrical matching of images to a region of interest (ROl), we compare the cross-correlation coefficient only between the ROIs. The affine or perspective transform parameters satisfying maximum of cross-correlation between the local regions are searched iteratively by a fast searching strategy. The parameters are searched on the 1/4 scale image coarsely and then, the fine registration is performed on the original scale image. The developed method can match the images corrupted by Gaussian noise with the same accuracy for the images without any transform simulation. The registration accuracy of the perspective method shows a 17% improvement over the manual method. The application of the developed method to radiography of dental implants provides an automatic noise robust registration with high accuracy in almost real time.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.6
• /
• pp.231-236
• /
• 2014

The transit time of contrast agents and the parameters of time-intensity curves in ultrasonography are important factors to diagnose various diseases of a digestive organ. We have implemented an automatic parametric imaging method to overcome the difficulty of the diagnosis by naked eyes. However, the micro-bubble noise and the respiratory motions may degrade the reliability of the parameter images. In this paper, we introduce an optimization technique based on MRF(Markov Random Field) model to enhance the quality of the parameter images, and present an image tracking algorithm to compensate the image distortion by respiratory motions. A method to extract the respiration periods from the ultrasound image sequence has been developed. We have implemented the ROI(Region of Interest) tracking algorithm using the dynamic weights and a momentum factor based on these periods. An energy function is defined for the Gibbs sampler of the image enhancement method. Through the experiments using the data to diagnose liver lesions, we have shown that the proposed method improves the quality of the parametric images.