• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.661-664
• /
• 1998

Since the region segmentation at high resolution contains most of viable semantic object contours in an image, the bottom-up approach for image segmentation is appropriate for the application such as MPEG-4 which needs to preserve semantic object contours. However, the conventioal region merging methods, that follow the region segmentation, have poor performance in keeping low-contrast semantic object contours. In this paper, we propose an image segmentation algorithm based on classified region merging. The algorithm pre-segments an image with a large number of small regions, and also classifies it into several classes having similar gradient characteristics. Then regions only in the same class are merged according to the boundary weakness or statisticsal similarity. The simulation result shows that the proposed image segmentation preserves semantic object contours very well even with a small number of regions.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.3
• /
• pp.25-33
• /
• 2007

In this paper, I propose a method which can enhance the visual quality of IRST images based on a loaded location in ship and an AOS. The IRST adjusts an AOS to detect targets with various altitudes because of its narrow vertical field of view and offers various functions to enhance images with its low contrast. In the proposed method, images are divided into two regions of sea and sky on the basis of the horizon after establishing relation between an AOS and a horizon location within an image. As a result, image enhancement of the proposed method is performed adaptively according to the divided region while that of conventional method is performed for entire image without the region division. Simulation results show that the proposed method represents higher visibility compared with conventional one.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.544-564
• /
• 2022

Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.3
• /
• pp.132-140
• /
• 2007

The quality of the camera image is worse than that of the scanner image because of lighting variation and inaccurate focus. This paper proposes a binarization method for camera-based document recognition, which is tolerant to low-quality camera images. Based on an existing method reported to be effective in previous evaluations, we enhanced the adaptability to the image with a low contrast due to low intensity and inaccurate focus. Furthermore, applying an additional small-size window in the binarization process, it is effective to extract the fine detail of character structure, which is often degraded by conventional methods. In experiments, we applied the proposed method as well as other methods to a document recognizer and compared the performance for many cm images. The result showed the proposed method is effective for recognition of document images captured by the camera.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.623-632
• /
• 2019

Many researches have been carried out for brightness and contrast enhancement, illumination reduction and so forth. Recently, the aforementioned hand-crafted approaches have been replaced by artificial neural networks. This paper proposes a convolutional neural network that can replace the method of generating a reflectance image where illumination component is attenuated. Experiments are carried out on 102 low-light images and we validate the feasibility of the replacement by producing satisfactory reflectance images.

• Journal of Magnetics
• /
• v.19 no.3
• /
• pp.248-254
• /
• 2014

The purpose of this study is to figure out how uptake counts of technetium ($^{99m}Tc$) among radioisotopes in the human body are affected if computed tomography (CT), magnetic resonance imaging (MRI) and isotope examination are performed consecutively. $^{99m}Tc$ isotope material, iodinated contrast media for CT and paramagnetic contrast media for magnetic resonance (MR) were used as experimental materials. First, $^{99m}Tc$ was added to 4 cc normal saline in a test tube. Then, 2 cc of CT contrast media such as $Iopamidol^{(R)}$ and $Dotarem^{(R)}$ were diluted with 2 cc normal saline, and 2cc of MRI contrast media such as $Primovist^{(R)}$ and $Gadovist^{(R)}$ were diluted with 2 cc normal saline. Each distributed contrast media was a total of 4 cc and included 10m Ci of $^{99m}Tc$. A gamma camera, a LEHR (Low energy high resolution) collimator and a pin-hole collimator were used for image acquisition. Image acquisition was repeated a total of 6 times and 120 frames were obtained and uptake counts of $^{99m}Tc$ were measured (from this procedure). In this study, as a result of measuring the uptake counts of $^{99m}Tc$ using the LEHR collimator, the uptake counts were less measured in all contrast media than normal saline as a reference. In particular, the lowest uptake counts were measured when $Gadovist^{(R)}$, contrast media for MRI, was used. However, the result of measuring the uptake counts of $^{99m}Tc$ using the pin-hole collimator showed higher uptake counts in all contrast media, except for $Iopamidol^{(R)}$, than normal saline as a reference. The highest uptake counts were measured particularly when $Primovist^{(R)}$, contrast media for MRI, was used. In performing the gamma camera examination using contrast media and $^{99m}Tc$, it is considered significant to check the changes in the uptake counts to improve various diagnosis values.

• Journal of radiological science and technology
• /
• v.15 no.1
• /
• pp.65-78
• /
• 1992

Routine chest radiography is generally imaged by high voltage technique but some radiological technologists use low voltage for imaging. High voltage is usually said between $120\;kV{\sim}140\;kV$. Some RTs like using heavy filtration but others seldom like using it. However which is better for use calcium tungustate film screen system or ortho system and high contrast film or wide latitude c-type film for the exculusive use of chest radiography. We could not make a decision which is ideal method for use. In my opinion any method is not always exellent for chest radiography. In my experiments that I had at Kaken hospital in Japan last year I expect to keep the balance between image quality and diagnostic range and to reduce radiation dose for patients. My experiments are as follows. 1. We have looked into system characteristics(speed and contrast) in accordance with kVp($80{\sim}140$) and added filter($no{\sim}1/16\;VL$) in three screen film systems(BX3+CRONEX4, SRO750+MGH, SRO750+MGL). 2. We have looked into skin dose and film dose with same D=1.8 lung field density in accordance with kVp($80{\sim}140$) and added filter($no{\sim}1/16\;VL$) in three screen film systems. 3. We have compared with the evaluation between correlation of physical image quality(MTF) and optical diagnostic capability. Result are follows. 1. Speed of BX3+CRONEX4 became higher in accodance with kVp and thickness of filter but speed of ortho system was not as like regular system. Thicker filter diminished the speed over 100 kV range in SRO750+MGL. In case of SRO750+MGH speed of 1/16VL filter was looked into lower than speed of 1/4VL filter. Sensitivity of ortho system depends on tube voltage and added filter. 2. Skin dose has been detected $225\;{\mu}Gy{\sim}66\;{\mu}Gy$ in BX3+CRONEX4 from 80 kV, no filter to 140 kV, 1/16VL filter. SRO750+MGH could reduce the patient dose $1/2{\sim}1/3$ level in comparison to that of BX3+CRONEX4. 3. The higher kV was the worse MTF became the thicker filter was the worse MTF became too. MTF of BX3+CRONEX4 was detected better than MTF of SRO750+MGH but SRO750+MGH's optical detectability of small lesion in lung field came out better than that of BX3+CRONEX4. Conclusion Recently routine chest radiography is generally imaged by high voltage but it seems to be there are some questions in using of film screen combination. In high voltage chest radiography the subject contrast will come down that means latitude become wider. In this case if we select the low contrast film screen system(C or L type) the film contrast will fall down extremly and detectability of small lesion will be deteriorated. Wide latitude C, L type film has a merit of high detectability on mediastinum. Furthermore high contrast film screen system has the advantage to keep the high contrast in low density region as like mediastinum and heart shadow. Therefore in low subject contrast high voltage chest radiography we would rather choose the high contrast film screen system(H type) I think. From a view point of patient dose detectability of mediastinum and lung field. The optimum technical facter was found out 120 kV, 1/16VL filter : BX3+CRONEX4, 140 kV, 1/4VL filter : SRO750+MGH, 100 kV, 1/4VL filter : SRO750+MGL.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1649-1657
• /
• 2008

In this paper, to overcome the failure of binarization for the characters suffered from low contrast and non-uniform illumination in license plate character recognition system, we improved the binarization method by combining local thresholding with global thresholding and edge detection. Firstly, apply the local thresholding method to locate the characters in the license plate image and then get the threshold value for the character based on edge detector. This method solves the problem of local low contrast and non-uniform illumination. Finally, back-propagation Neural Network is selected as a powerful tool to perform the recognition process. The results of the experiments i1lustrate that the proposed binarization method works well and the selected classifier saves the processing time. Besides, the character recognition system performed better recognition accuracy 95.7%, and the recognition speed is controlled within 0.3 seconds.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.5
• /
• pp.126-131
• /
• 2004

As a noninvasive imaging method, optical coherence tomography system has been extensively studied because it has some advantages such as imaging of high resolution, low cost, and compact size configuration. In order to improve the SNR of OCT system, two types of interferometers were configured and then, we compared simulation with measurement of reference sample. In the OCT system is configured with Michelson interferometer, the contrast of cross-sectional image is reduced with low SNR detection which is due to loss of feedback interference signal from light source part. Also, in order to image measured data with real time, image processing program is constructed. From results of simulation, it is confirmed that improved Michelson interferometer is improved about 10[dB] with a 50 : 50 fiber coupler. And from the measurement of reference sample, about 5[dB] is improved with a 50 : 50 fiber coupler. It is confirmed that the OCT system is configured with the improved Michelson interferometer which has a good distinctive cross-sectional image due to higher contrast.

• Journal of the Korean Society of Radiology
• /
• v.2 no.1
• /
• pp.23-29
• /
• 2008

The present study proposed a method that dissolves ultrasonographic images into multiple resolutions using wavelet conversion and a boundary detection filter and improves the quality of ultrasonographic images through boundary detection filtering. In order to reduce noises and strengthen edges, the proposed method adjusted selectivity coefficient by area step by step from a low resolution image obtained from wavelet converted images to a high resolution image and performed edge filtering in consideration of direction. Through this method, we generated a selective low pass filtering effect in areas except edges by decreasing the wavelet coefficient for pixels in spot areas, improved continuity by smoothing edges in the tangential direction, and enhanced contrast by thinning in the normal direction. Through an experiment, we compared the filtering method using a non linear anisotropic expansion model and the filtering method using wavelet contraction structure in single resolution.