• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.568-571
• /
• 1997

Recently, the number of techniques for analyzing medical images has been increasing in computer vision, employing X-ray CT images, ultrasound images, MR images, moire topographic images, etc. Spinal deformity is a serious problem especially for teenagers and medical doctors inspect moire topographic images of their backs visually for the primary screening. If a subject is normal, the moire image is almost symmetric with respect to the middle line of the subject's back, otherwise it shows asymmetric shape. In this paper, an image analysis technique is described for discriminating suspicious cases from normal in human spinal deformity by recognizing asymmetric moire images of human backs. The principal axes which are sensitive to asymmetry of the moire image are extracted at two parts on a subject's back and their angles are evaluated with respect to the detected middle line of the back. The two angles compose a 2-D feature space and inspected cases are divided into two clusters in the space by a linear discriminant function based on the Mahalanobis distance. Given 120 cases, 60 normal and 60 abnormal, the leave-out method was applied for the recognition and 75% recognition rate was achieved.

• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.244-247
• /
• 1995

A technique is presented for evaluating spinal deformity of a human back by extracting a spinal line based on 3-D topograpic reconstruction of the back from its moire image. A given moire image is differentiatedby DOG filter to extract moire stripes. The stripes are then assigned labels and the labels are interpolated by the Lagrange polynomial to yield the undulation of the back which gives a relative 3-D shape of the back. A valley is searched on the undulation near the middle part of the back and the valley line is finally extracted as an approximated spinal line. The mean differenceand the variance between the spinal line and the middle line are calculated and reported. Experiment is performed employing real moire images ofjunior-high school students' backs and some of the results are shown with discussion.

• Journal of radiological science and technology
• /
• v.40 no.4
• /
• pp.575-580
• /
• 2017

Because moire artifacts overlap with fine lesions and frequency bands, image processing software that removes moire artifacts can lead to loss of micro lesions. In this study, microscopic lesions such as microcalcification and microfracture were randomly formed on SD (Sprague Dawley) rats and image and optimized grid images were compared and analyzed using reference image and grid suppression software. The images were read by two consecutive radiologists using a McNemar's test. Among the 73 microcalcifications, in the 13 cases after grid suppression, the image of the optimized grid shows the loss of image in 3 cases, and the image after grid suppression shows statistically significant image loss (p=0.021). In all 53 fracture lines, there were 19 cases of image loss after the grid suppression, and only one case of the optimized grid showed no image loss. Therefore, the use of grid suppression software to remove moire artifacts should be carefully considered in the diagnosis of micro lesions.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.3-13
• /
• 2021

We propose a moire artifacts removal algorithm for screen-shot images using multiple domain learning. First, we estimate clean preliminary images by exploiting complementary information of the moire artifacts in pixel value and frequency domains. Next, we estimate a clean edge map of the input moire image by developing a clean edge predictor. Then, we refine the pixel and frequency domain outputs to further improve the quality of the results using the estimated edge map as the guide information. Finally, the proposed algorithm obtains the final result by merging the two refined results. Experimental results on a public dataset demonstrate that the proposed algorithm outperforms conventional algorithms in quantitative and qualitative comparison.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.11b
• /
• pp.47-52
• /
• 1999

The visualization of Moire or laser-scanned data has been explored by many researchers and has been an important issue on computer graphics research. In this paper, we present various techniques that handle tremendous amount of 3D range data which are generated by the ETRI- Moire Scanner. The techniques include constructing an efficient data structure, constructing triangle meshes and decimation and registration of multiple-view range images and textures.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.15 no.2
• /
• pp.57-76
• /
• 1997

A color halftoning is the process of generating halftone images for the different color plans, for example, cyan, magenta, yellow, and black for a offset printing device. A conventional halftone technique, so called AM screening, is simple and easy to implement, but the halftoned dot patterns by using this method is not free for the moire` fringe. Moire` patterns are caused the power spectrum distribution on low spatial frequency domain. To avoid Moire` patterns, the conventional screen require the different screen angles for each color plans. Recently, Ultra-fine and 7 color printing methods are developed to expend the color gamut. In 7 color printing method must be used the halftone technique of random and blue noise characteristic to avoid Moire` fringe.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.105.1-105
• /
• 2001

In this paper, a technique is described for classifying normal cases and abnormal cases in automatic spinal deformity detection by computer based on moire topographic images of human backs. Displacement is evaluated statistically between the middle line extracted from the entire moire image and the middle line obtained from a small rectangle area defined on the moire image. The middle line is calculated employing a developed potential symmetry analysis technique. The displacement is calculated in several regions and the mean and the standard deviation of the displacement values are chosen as two features. A linear discriminant function (LDF) is defined on the 2-D feature space based on the Mahalanobis distance and the features are classified into two categories, i.e., normal and ...

• Journal of radiological science and technology
• /
• v.41 no.2
• /
• pp.149-155
• /
• 2018

Quantitative analysis was performed to confirm that moire artifact was removed without loss of image when using grid suppression software in the diagnosis of micro lesions. we showed that grid suppression images can be morphologically different from original images as they are significantly lower than those of the optimized grid in the similarity analysis with reference images in mammographic phantom images. We were confirmed that images of microcalcification with smaller signal than noise were lost because the pixel values of all lesions increased significantly after the grid suppression, The change in contrast using the NORMI 13 X-ray test phantom was reduced to 30% of the reference image, This result was significantly lower than the 90% when using the optimized grid. In conclusion, the use of grid suppression software in clinical images should be carefully considered because of the possibility of misdiagnosis due to micro lesion loss and morphological changes.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.16 no.12S
• /
• pp.1261-1267
• /
• 2003

Since the grating optical low-pass fillet degrades the resolution of images, we developed a hologram optical low-pass filter that show low degradation of the image and studied its characteristics. We designed the hologram that divides input beam into circular shaped 21 beams with a Monte-Carlo based hologram generation program and calculated its MTE characteristics to compare it with that of a grating filter. The hologram was manufactured through the optical lithography process and attached to a digital imaging device (Zoran 732212) for measurement. The moirfiltering is compared with zone plate images and the resolution loss is measured with USAF resolution chart. The hologram optical low-pass filter showed better characteristics in both moly filtering and resolution.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.438-441
• /
• 1996

Spinal deformity is a serious disease especially for teenagers and it is desirable for school children to be checked possible spinal deformity by moire photographic inspection method. The moire images of children's backs are visually inspected by doctors, which may cause misjudge because of a large amount of data they have to examine. A technique is proposed in this paper for automating this inspection by computer. Two characteristic axes, a potential symmetry axis approximating the human middle line and a principal axis representing the direction of a moire pattern are employed. Two principal axes are extracted locally on a back and their gradients against the potential symmetry axis are calculated. These gradients compose a 2D feature space and a linear discriminant function (LDF) is defined there which separates normal cases from suspicious cases. The LDF defined by 40 training, data was employed in the experiment to examine 40 test data and 77.5% of them were classified correctly. This amounts to 88.8% if the training data is included.