• Journal of Advanced Marine Engineering and Technology
• /
• v.41 no.3
• /
• pp.251-257
• /
• 2017

In this paper, an algorithm for detecting defects in thin-film-transistor liquid-crystal display (TFT-LCD) cell images is presented. TFT-LCD cell images typically contain periodic cell patterns that make it difficult to detect defects. We propose an efficient and powerful algorithm for eliminating the cell patterns using magnitude spectrum analysis. The first step was to obtain a spectrum for a cell image using the Fourier transform while eliminating larger coefficients using an adaptive filter. Next, an image without the cell pattern was obtained by using the inverse Fourier transform. Finally, the defect pixels were detected using the STD algorithm. The validity of the proposed method was investigated using real TFT-LCD cell images. The experimental results indicate that the proposed technique is extremely effective for detecting defects in TFT-LCD cell images.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.3
• /
• pp.385-396
• /
• 1993

In this paper, a improved method of digital image analysis required in basic medical science for diagnosis of cells was proposed. The object image was the thyroid gland cell image, and the purpose was automatic discrimination of three classes cells(normal cell, follicular neoplastic cells, and papillary neoplastic cells) by difference of chromatin patterns. To segment the cell nucleus from background, the region segmentation algorithm by edge tracing was proposed. And feature parameter was obtained from discrete Fourier transformation of image. After construct a feature sample group of each cells, experiment of discrimination was executed with any verification cells. As a consequency of using features proposed in this paper, get a better recognition rate(70-90%) than previously reported papers, and this method give shape to get objectivity and fixed quantity in diagnosis of cells, The methods described in this paper be used immediately for discrimination of neoplastic cells.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.3
• /
• pp.383-391
• /
• 2016

Ballast water provides stability and manoeuvrability to a ship. Foreign harmful aquatic organisms, which were transferred by ballast water, cause disturbing ecosystem. In order to minimize transference of foreign harmful aquatic organisms, IMO(International Maritime Organization) adopted the International Convention for the Control and Management of Ship's Ballast Water and Sediments in 2004. If the convention take effect, a port authority might need to check that ballast water is properly disposed of. In this paper, we propose a method of counting harmful aquatic organisms in ballast water thorough image processing. We extracted three samples from the ballast water that had been collected at Busan port in Korea. Then we made three grey-scale images from each sample as experimental data. We made a comparison between the proposed method and CellProfiler which is a well known cell-counting program based on image processing. Setting of CellProfiler is empirically chosen from the result of cell count by an expert. After finding a proper threshold for each image at which the result is similar to that of CellProfiler, we used the average value as the final threshold. Our experimental results showed that the proposed method is simple but about ten times faster than CellProfiler without loss of the output quality.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.23 no.1
• /
• pp.1-7
• /
• 2010

Objective : Mercuric chloride is excreted in the urine and stool. Bangpungtongseong-san(BT) has been used commonly skin disease and has diuresis and excretion effect. This study is aimed to find out effects of Kami- bangpungtongseong-san(KBT) on the skin disease toxicated by mercury. Method : Experiment was conducted with No treated group(Normal group), Mercuric chloride subcutaneous injection group(Control group) and Kami-bangpungtongseong-san-treated group (Sample group). KBT Extracts were delivered orally in 7 days in sample group. We observed epithelial cell hyperplastic, angiogenesis, inflammatory cell infiltration of skin. For the charting the results, image analysis was taken. The result of image analysis was verified significance by Sigmaplot 2000(P<0.05). Result : This study shows an relieving epithelial cell hyperplastic, angiogenesis, inflammatory cell infiltration of exposure skin on mercuric chloride. Conclusion : According to the result of study, we can expect to the effect of KBT extracts' therapeutic action to tissue injuries of the mice' skin on acute mercurial toxication.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.9
• /
• pp.823-828
• /
• 2013

To reduce the cost per watt of photovoltaic power, it is important to reduce the cell thickness of crystalline silicon solar cells. As the thickness of the silicon layer is reduced, two distinctive thermal expansion rates between the silicon and the aluminum layer induce bowing in a solar cell. With a thinner silicon layer, the bowing distance grows exponentially. Excessive bowing could damage the silicon wafer. In this study, we tried to measure an irregularly curved silicon solar cell more accurately using a 3D image scanner. For the detailed analysis of the three-dimensional bowing shape, a least square fit was applied to the point data from the scanned image. It has been found that the bowing distance and shape distortion increase with a decrease in the thickness of the silicon layer. An Ag strip on top of the silicon layer can reduce the bowing distance.

• Journal of Korean Physical Therapy Science
• /
• v.10 no.1
• /
• pp.198-205
• /
• 2003

We evaluated the effect of low power GaAsAl laser on re-epithelization in full-thickness excisional wound of rat skin. Two full-thickness excisions were made on the back of the experimental animals. Low power laser applications with 10mW intensity were treated experimental animals twice a day for 7 days. On the seventh postoperative day the quantitative analysis of re-epithelization was performed using immunohistochemical staining for proliferating cell nuclear antigen (PCNA). The majority of PCNA immunoreactive cells was observed at epithelial cells in the margin of full thickness excisional wound. The low power laser treatments significantly increased the number of PCNA immunoreactive cell as compared to that of non treated animal group (p<0.01). The shape of PCNA immunoreactive cell appeared as small dark, round to ovoid structures. Most PCNA immunoreactive cells exhibited a high intensity of staining that contrasted sharply with the surrounding background. In conclusion, these findings suggest that GaAlAs laser treatments effectively enhance the epithelial wound healing by the stimulating cell proliferation. Furthermore, the majority of cell proliferation occurred in the margin of full thickness excisional wound.

• 대한생식의학회:학술대회논문집
• /
• 2004.06a
• /
• pp.76-76
• /
• 2004

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.357-362
• /
• 1996

A way of quantitatively describing the tissue architecture we have investigated when developing a computer program for malignancy grading of transitional cell bladder carcinoma. The minimum spanning trees, MST was created by connecting the center points of the nuclei in the tissue section image. These nuclei were found by thresholding the image at an automatically determined threshold followed by a connected component labeling and a watershed algorithm for separation of overlapping nuclei. Clusters were defined in the MST by thresholding the edge lengths. For these clusters geometric and densitometric features were measures. These features were compared by multivariate statistical methods to the subjective grading by the pathologists and the resulting correspondence was 85% on a material of 40 samples.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.11
• /
• pp.2493-2499
• /
• 2011

With growth of nano-bio industry, it is of significant importance to develop an automated system to exploit cell behaviors, including migration, mitosis, apoptosis, shape deformation of individual cells and their interactions among cells in the process of cell growth. In this paper, we proposed preprocessing techniques, a classification method which classifies clusters (overlapping multiple cells) from cells and an automated method which counts the number of cells and clusters in order to analyze 2D or 3D deformations of the cells in the real-time images from microscope in the cell culture. We conducted the 3T3 cell images taken from each thirty-minute interval. It showed the average 99.8% accuracy automatically for separating cells and clusters.