• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.640-647
• /
• 2001

In this paper, a noise-tolerant generalized symmetry transform(NTGST) is proposed as an effective attention operator for the spot detection in BLU inspection, in which various spots with variable sizes, shapes, gray levels, and low contrast, should be detected from the complex, noisy background with lattice shaped shading. The proposed NTGST takes into account the polarity of convergence and divergence of the radial orientation of the intensity gradient as well as it's magnitude and symmetry, and thereby can detect only the BLU spots from the noisy and lattice shaped shadows of background. Experiments are conducted on the BLU inspection image obtained by CCD camera, and the proposed NTGST is Proved to be effectively used in BLU inspection.

• Journal of Construction Engineering and Project Management
• /
• v.3 no.2
• /
• pp.1-12
• /
• 2013

Research indicates that good front-end planning (FEP) results in the achievement of higher levels of project performance. By facilitating collaboration among stakeholders in diverse locations with the use of workflow-enabled processes, such pressures can be reduced, and the overall process and results of FEP can be improved. With these goals, a front-end planning tool (FEPT) has been developed as support for owners and major contractors who are engaged in front-end planning. This paper presents the new FEPT and describes how it has been used for construction megaprojects in the nuclear power, oil and gas, and mining industries. The paper begins with the definitions related to and an explanation of the general process for implementing and applying the FEPT and then describes and analyzes how the FEPT was applied in case study projects in order to test its validity. The results indicate that the FEPT increases the efficiency and effectiveness of front-end planning for the megaprojects studied and that it has the potential to produce similar results for other megaprojects.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.127-134
• /
• 2003

This paper is intended to develop an algorithm for automatic detection of traffic accidents using image sequences. This algorithm is designed for detecting stopped vehicles traffic accidents, break down, illegal stop in the road shoulder - on the range of camera view. Virtual traps are set on accident-prone spots. We analyze the changes in gray levels of pixels on the virtual traps which represent the motion of vehicles on the corresponding spots. We verify the proposed algorithm by simulating some situations and checking if it detect them correctly.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.570-595
• /
• 2017

Robust and perceptually-adaptive image watermarking algorithms have mainly targeted gray-scale images either at the modeling or embedding levels despite the widespread availability of color images. Only few of the existing algorithms are specifically designed for color images where color correlation and perception are constructively exploited. In this paper, a new perceptual and high-capacity color image watermarking solution is proposed based on the extension of Tsui et al. algorithm. The $CIEL^*a^*b^*$ space and the spatio-chromatic Fourier transform (SCFT) are combined along with a perceptual model to hide watermarks in color images where the embedding process reconciles between the conflicting requirements of digital watermarking. The perceptual model, based on an emerging color image model, exploits the non-uniform just-noticeable color difference (NUJNCD) thresholds of the $CIEL^*a^*b^*$ space. Also, spread-spectrum techniques and semi-random low-density parity check codes (SR-LDPC) are used to boost the watermark robustness and capacity. Unlike, existing color-based models, the data hiding capacity of our scheme relies on a game-theoretic model where upper bounds for watermark embedding are derived. Finally, the proposed watermarking solution outperforms existing color-based watermarking schemes in terms of robustness to standard image/color attacks, hiding capacity and imperceptibility.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.29 no.1
• /
• pp.283-297
• /
• 1999

Purpose: To compare radiographic images of Digora/sup (R)/ system and Ektaspeed Plus film obtained from normal adults. Materials and methods: Storage phosphor plate(SPP) was placed in a film holder behind Ektaspeed Plus film package without lead foil. The effect of film on SPP was studied in a separate in vitro experiment. Forty-seven sets of images were prepared for the evaluaton. The regions of interest(ROI) for evaluation were designated at seven sites including normal anatomical structures. The image quality for each ROI was evaluated on enhanced and unenhanced storage phosphor(SP) images and Ektaspeed Plus film. Results: Two film-SPP configurations showed significantly different gray levels at each step of the aluminum step wedge(p<0.05). The contrasts were comparable. Enhanced SP images were significantly superior to unenhaned images and film in all anatomical sturctures(p<0.01). The differences between unenhanced SP images and film were significant(p<0.05) except root canal and cortical bone on alveolar crest. For anatomical items. there were statistically significant difference among five observers(p<0.05). Conclusions: The image quality of enhanced SP images were superior to Ektaspeed Plus film. and Digora system is potentially applicable to clinical diagnosis.

• Journal of the Korea Convergence Society
• /
• v.5 no.3
• /
• pp.41-44
• /
• 2014

Sequential object analysis are playing vital role in real time application in computer vision and object detections.Measuring the similarity in two images are very important issue any authentication activities with how best to compare two independent images. Identification of similarities of two or more sequential images is also the important in respect to moving of neighborhoods pixels. In our study we introduce the morphological and shared near neighborhoods concept which produces a sufficient results of comparing the two images with objects. Considering the each pixel compare with 8-connectivity pixels of second image. For consider the pixels we expect the noise removed images are to be considered, so we apply the morphological transformations such as opening, closing with erosion and dilations. RGB of pixel values are compared for the two sequential images if it is similar we include the pixels in the resultant image otherwise ignore the pixels. All un-similar pixels are identified and ignored which produces the similarity of two independent images. The results are produced from the images with objects and gray levels. It produces the expected results from our process.

• Imaging Science in Dentistry
• /
• v.39 no.4
• /
• pp.195-198
• /
• 2009

Purpose : To establish reference doses of periapical radiography in Chonnam Province, Korea. Materials and Methods : The target-skin distances were measured for dental patient's 1235 exposures including 345 mandibular molar areas. Each periapical radiation exposure was simulated with exactly the same patients exposure parameters and the simulated radiation doses were measured utilizing Mult-O-Meter (Unfors Instruments, Billadal, Sweden). The measurements were done in 44 dental clinics with 49 dental x-ray sets in Chonnam Province for one or two weeks at each dental clinic during year 2006. Results : The third quartile patient surface doses were 2.8 mGy for overall periapical exposures and 3.2 mGy for periapical mandibular molar exposures. Conclusion : The third quartile patient surface doses in Chonnam Province can be used as a guide to accepted clinical practice to reduce patient radiation exposure for the surveyed reference doses were below the recommended dental periapical radiography dose of 7 mGy by IAEA.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.11
• /
• pp.103-111
• /
• 2016

Traditionally, in the hospital the doctors saw the TRUS images by their eyes and manually segmented the boundary between the prostate and nonprostate. But the manually segmenting process not only needed too much time but also had different boundaries according to the doctor. To cope the problems, some automatic segmentations of the prostate have been studied to generate the constant segmentation results and get the belief from patients. Besides, on detecting the boundary, the ones in the middle of all images are easy to find the boundary but the base and apex of the images are hard to do it since there are lots of uncertain boundary. Accurate detection of prostate boundaries is a challenging and difficult task due to weak prostate boundaries, speckle noises and the short range of gray levels. In this paper, we propose the method that extracts a prostate boundary using features of its directions on prostate image. As a result of our experiments, it shows that the boundary never falls short of the existing methods or human expert's segmentation. And also, its searching speed is too fast because the method searches a smaller area that other methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.10
• /
• pp.934-940
• /
• 1991

A modified quantizing method is introduced to teach single layer learning algorithm, which is implemented optically. The proposed optical system consists of input masks, holographic diffraction grating. LCD and CCD camera. The 2 dimensional interconnections between input neurons and output neurons are realized using holographic phase grating, which is fabricated for equal intensity distribution of diffraction orders. The two gray levels of LCD act as binary weights for each interconnection. The weights are compensated according to the learning algorithm in which the amount of weights to be compensated is determined by comparing the output patterns with target patterns. The learning process is iterated until the predetermined conditions are satisfied. Optical experiments are performed for two learning rates, 0.5 and 0.9 and the experimental results show that the proposed system is useful for optical neural networks.

• Journal of Information Display
• /
• v.12 no.1
• /
• pp.5-10
• /
• 2011

A novel architecture and proprietary electronic inks were developed to provide disruptive digital-media solutions based on an electrokinetic technology platform. The flexible reflective electronic media (eMedia) was fabricated by imprinting three-dimensional microscale structures with a roll-to-roll manufacturing platform. The HP technologies enable the required attributes for eMedia, such as low power, transparency, print-quality color, continuous levels of gray, and lowcost scalability. Pixelation was also demonstrated by integrating with the prototype oxide thin-film transistor backplane, and the system architecture was further developed by stacking primary-colorant layers for color reflective-display application. The innovations described in this paper are currently being developed further for the eSkins, eSignage, and ePaper applications.