http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Altansukh Sengee,Nyamlkhagva Sengee,Heung-Kook Choi,Myung-Ja Tak,Sae-Hong Cho 한국멀티미디어학회 2011 한국멀티미디어학회 국제학술대회 Vol.2011 No.-
This study objective was to compare popular image reconstruction methods which are the filtered backprojection (FBP) and maximum likelihood expectation maximization (MLEM) on some medical and phantom images with noise. Peak signal noise ratio (PSNR) is used to evaluate the methods. Experimental result shows that FBP and MLEM are closely similar result but MLEM is better than FBP in noisy images.
Altansukh Sengee,Nyamlkhagva Sengee,Heung-Kook Choi 한국멀티미디어학회 2010 한국멀티미디어학회 학술발표논문집 Vol.2010 No.2
In this work, two image reconstruction methods which are the filtered back projection (FBP) and the maximum likelihood expectation maximization (ML-EM) are compared on some computer tomography (CT) images with noise. To evaluate those methods, we used one evaluation measurement which is called a peak signal-to-noise ratio. We tested the methods with three sample images of computer tomography. Experimental result shows that FBP and ML-EM are closely similar result but FBP is better than ML-EM in noisy images.
Contrast Enhancement for Segmentation of Hippocampus on Brain MR Images
Sengee, Nyamlkhagva,Sengee, Altansukh,Adiya, Enkhbolor,Choi, Heung-Kook Korea Multimedia Society 2012 멀티미디어학회논문지 Vol.15 No.12
An image segmentation result depends on pre-processing steps such as contrast enhancement, edge detection, and smooth filtering etc. Especially medical images are low contrast and contain some noises. Therefore, the contrast enhancement and noise removal techniques are required in the pre-processing. In this study, we present an extension by a novel histogram equalization in which both local and global contrast is enhanced using neighborhood metrics. When checking neighborhood information, filters can simultaneously improve image quality. Most important is that original image information can be used for both global brightness preserving and local contrast enhancement, and image quality improvement filtering. Our experiments confirmed that the proposed method is more effective than other similar techniques reported previously.
A Novel Approach for Brightness Preserving Local Contrast Enhancement based on Distinction Metric
Nyamlkhagva Sengee,Altansukh Sengee,Heung-Kook Choi 한국멀티미디어학회 2011 한국멀티미디어학회 국제학술대회 Vol.2011 No.-
We propose a new extension of bi-histogram equalization called Dualistic Sub-Image Histogram Equalization with Distinction Metric (DSHEDM). DSHEDM consists of two stages. First, large histogram bins that cause washout artifacts are divided into sub-bins using neighborhood metrics; the same intensities of the original image are arranged by neighboring information. In the second stage, the histogram of the original image is separated into two sub-histograms based on the median of the histogram of the original image; the sub-histograms are equalized independently using refined histogram equalization. In an experimental trial, DSHEDM simultaneously preserved the brightness and enhanced the local contrast of the original image.