• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.171-187
• /
• 2023

When a person's face is recognized through a recording device such as a low-pixel surveillance camera, it is difficult to capture the face due to low image quality. In situations where it is difficult to recognize a person's face, problems such as not being able to identify a criminal suspect or a missing person may occur. Existing studies on face recognition used refined datasets, so the performance could not be measured in various environments. Therefore, to solve the problem of poor face recognition performance in low-quality images, this paper proposes a method to generate high-quality images by performing image quality improvement on low-quality facial images considering various environments, and then improve the performance of facial feature point detection. To confirm the practical applicability of the proposed architecture, an experiment was conducted by selecting a data set in which people appear relatively small in the entire image. In addition, by choosing a facial image dataset considering the mask-wearing situation, the possibility of expanding to real problems was explored. As a result of measuring the performance of the feature point detection model by improving the image quality of the face image, it was confirmed that the face detection after improvement was enhanced by an average of 3.47 times in the case of images without a mask and 9.92 times in the case of wearing a mask. It was confirmed that the RMSE for facial feature points decreased by an average of 8.49 times when wearing a mask and by an average of 2.02 times when not wearing a mask. Therefore, it was possible to verify the applicability of the proposed method by increasing the recognition rate for facial images captured in low quality through image quality improvement.

• Korean Journal of Remote Sensing
• /
• v.33 no.3
• /
• pp.257-266
• /
• 2017

In this study, the dust/smoke detection algorithm was developed with a multi-spectral satellite remote sensing method using Moderate resolution Imaging Spectroradiometer (MODIS) Level 1B (L1B) data and the results were validated as RGB composite images of red(R; band 1), green(G; band 4), blue(B; band 3) channels using MODIS L1B data and Cloud-Aerosol Lidar with Orthogonal Polarization Satellite Observations(CALIPSO) Vertical Feature Mask (VFM) product. In the daytime on March 30, 2007 and April 27, 2012, the consistencies between the dust/smoke detected by this algorithm and verification data were approximately 56.4 %, 72.0 %, respectively. During the nighttime, the similar consistency was 40.5 % on April 27, 2012. Although these results were analyzed for limited cases due to the spatiotemporal matching for the MODIS and CALIPSO satellites, they could be used to utilize the aerosol detection of geostationary satellites for the next generations in Korea through further research.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.2
• /
• pp.141-146
• /
• 2016

In this paper, we apply limited area mask operation and active contour model to accurately detect tongue area outline in tongue diagnosis system. To accurately analyze the properties of the tongue, first, the tongue area to be detected. Therefore an effective segmentation method for detecting the edge of tongue is very important. It experimented with tongue image DB consists of 20~30 students 30 people. Experiments on real tongue image show the good performance of this method. Experimental results show that the proposed method extracts object boundaries more accurately than existing methods without mask operation.

• Journal of information and communication convergence engineering
• /
• v.6 no.1
• /
• pp.80-85
• /
• 2008

Images are often corrupted by noises during signal acquisition and transmission. Among those noises, additive white Gaussian noise (AWGN) and impulse noise are most representative. For different types of noise have different characters, how to remove them separately from degraded image is one of the most fundamental problems. Thus, a modified image restoration algorithm is proposed in this paper, which can not only remove impulse noise of random values, but also remove the AWGN selectively. The noise detection step is by calculating the intensity difference and the spatial distance between pixels in a mask. To divide two different noises, the method is based on three weighted parameters. And the weighted parameters in the filtering mask depend on spatial distances, positions of impulse noise and standard deviation of AWGN. We also use the peak signal-to-noise ratio (PSNR) to evaluate restoration performance, and simulation results demonstrate that the proposed method performs better than conventional median-type filters, in preserving edge details.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.519-521
• /
• 2015

세라믹 소재 영상에서 결함 영역이 다른 영역보다 명암도가 밝게 나타나는 정보를 이용하여 ROI 영역을 추출한다. 추출된 ROI 영역에서 Blurring 기법을 적용하여 미세 잡음을 제거한다. 미세 잡음이 제거된 ROI 영역에서 Median Filter기법을 적용하여 임펄스 잡음을 제거한다. 임펄스 잡음이 제거된 영역에서 Prewit Mask을 적용하여 수평과 수직 에지를 검출하고 검출된 에지에 윤곽선 추적 기법을 적용하여 결함 영역의 경계를 보정한다. 보정된 영상에서 Blob Labeling 기법을 적용하여 최종적으로 결함 영역을 추출한다. 제안된 방법을 8mm와 10mm 세라믹 소재 영상을 대상으로 실험한 결과, 기존의 결함 검출 방법보다 제안된 검출 방법의 검출 성능이 개선된 것을 확인하였다.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.16 no.12
• /
• pp.1097-1102
• /
• 2003

In this paper, we used only PR as etching mask, while it used usually Cr/AU as etching mask, and in order to fabricate a photosensor has the increased sensitivity, we investigated on the sensitivity of general type and p-i-n type diode. we designed microchannel size width max 10um, min 5um depth max 10um, reservoir size max 100um, min 2mm. Fabrication of microfluidic devices in glass substrate by glass wet etching methods and glass to glass fusion bonding. The p-i-n diode has higher sensitivity than photodiode, Considering these results, we fabricated p-i-n diodes on the high resistive(4㏀$.$cm) wafer into rectangle and finger pattern and compared internal resistance of each pattern. The internal resistance of pin diode can be decreased by the application of finger pattern has parallel resistance structure from 571Ω to 393Ω.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2003.11a
• /
• pp.201-206
• /
• 2003

In clinical practice, CT Angiography is a powerful technique for the visualziation of blood flow in arterial vessels throughout the body. However CT Angiography images of blood vessels anywhere in the body may be fuzzy if the patient moves during the exam. In this paper, we propose a novel technique for removing global motion artifacts in the 3D space. The proposed methods are based on the two key ideas as follows. First, the method involves the extraction of a set of feature points by using a 3D edge detection technique based on image gradient of the mask volume where enhanced vessels cannot be expected to appear, Second, the corresponding set of feature points in the contrast volume are determined by correlation-based registration. The proposed method has been successfully applied to pre- and post-contrast CTA brain dataset. Since the registration for motion correction estimates correlation between feature points extracted from skull area in mask and contrast volume, it offers an accelerated technique to accurately visualize blood vessels of the brain.

• Journal of the Optical Society of Korea
• /
• v.17 no.1
• /
• pp.73-80
• /
• 2013

In the process of lithography using ultra violet light sources for semiconductor devices, most of defects are made by sub-micrometer pollutants generated at photochemical reactions. We proposed and developed a novel vibration-insensitive on-axis interferometer with a sub-micrometer lateral resolution by using the interference between two beams: one scattered from defects and the other reflected from a reference area without defects. The proposed system was successfully demonstrated to detect a small Al defect of 0.5 ${\mu}m$ diameter within the inspection time of less than 30 minutes over the area of the photo-mask which is 6 inch by 6 inch square.

• Journal of Multimedia Information System
• /
• v.7 no.4
• /
• pp.257-262
• /
• 2020

In this paper, a method of detecting the emergency situations such as body fall is proposed by using color images. We detect body areas and key parts of a body through a pre-learned Mask R-CNN in the images captured by a camera. Then we find the centerline of the body through the joint points of both shoulders and feet. Also, we calculate an angle to the center line and then calculate the amount of change in the angle per hour. If the angle change is more than a certain value, then it is decided as a suspected fall. Also, if the suspected fall state persists for more than a certain frame, then it is determined as a fall situation. Simulation results show that the proposed method can detect body fall situation accurately.