• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.272-287
• /
• 2016

Recently, various and effective contrast based salient object detection models to focus on a single target have been proposed. However, there is a lack of research on detection of multiple objects, and also it is a more challenging task than single target process. In the multiple target problem, we are confronted by new difficulties caused by distinct difference between properties of objects. The characteristic of existing models depending on the global maximum distribution of data point would become a drawback for detection of multiple objects. In this paper, by analyzing limitations of the existing methods, we have devised three main processes to detect multiple salient objects. In the first stage, regional features are extracted from over-segmented regions. In the second stage, the regional features are categorized into homogeneous cluster using the mean-shift algorithm with the kernel function having various sizes. In the final stage, we compute saliency scores of the categorized regions using only spatial features without the contrast features, and then all scores are integrated for the final salient regions. In the experimental results, the scheme achieved superior detection accuracy for the SED2 and MSRA-ASD benchmarks with both a higher precision and better recall than state-of-the-art approaches. Especially, given multiple objects having different properties, our model significantly outperforms all existing models.

• Proceedings of the Korean Nutrition Society Conference
• /
• 2001.05a
• /
• pp.202.2-202
• /
• 2001

• Interaction and multiscale mechanics
• /
• v.2 no.2
• /
• pp.153-175
• /
• 2009

Damage detection methods using structural dynamic responses have received much attention in the past decades. For bridge and offshore structures, these methods are usually based on beam models. To ensure the successful application of these methods, it is necessary to examine the sensitivity of modal properties to structural damages. To this end, an analytic solution is presented of the modal properties of simply-supported Euler-Bernoulli beams that contain a general damage with no additional assumptions. The damage can be a reduction in the bending stiffness or a loss of mass within a beam segment. This solution enables us to thoroughly discuss the sensitivities of different modal properties to various damages. It is observed that the lower natural frequencies and mode shapes do not change so much when a section of the beam is damaged, while the mode of rotation angle and curvature modes show abrupt change near the damaged region. Although similar observations have been reported previously, the analytical solution presented herein for clarifying the mechanism involved is considered a contribution to the literature. It is helpful for developing new damage detection methods for structures of the beam type.

• Journal of the Korean Wood Science and Technology
• /
• v.36 no.5
• /
• pp.24-32
• /
• 2008

Artificial brown-rot decay was induced to two wood species, Pinus densiflora and Pinus radiata. A modified direct inoculation method was used and the decay indicators of mass loss and two compressive mechanical properties, maximum compressive strength (MCS) and compressive stiffness, were estimated over the period of 8 weeks of fungal exposure. Measurable mass loss occurred 2 weeks after the fungal attack, with 15% to 22% of the loss occurring 8 weeks after fungal exposure with Fornitopsis palustris and Gloeophyllurn trabeurn. Mechanical properties proved to be far more sensitive than mass loss detection: approximately five to six times by quantity. Of the two mechanical properties, MCS was more sensitive to and consistent with progressive brown-rot decay. An ultrasonic test was performed to determine the feasibility and accuracy of this method for nondestructive detection of brown-rot decay. The ultrasonic test is highly sensitive at qualitative detection of the early stages of brown-rot decay.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.1
• /
• pp.54-58
• /
• 2023

In this study, we compared the detection accuracy of the parameters of the scaffold failure detection model. A detection algorithm based on convolutional neural network was used to construct a failure detection model for scaffold. The parameter properties of the model were changed and the results were quantitatively verified. The detection accuracy of the model for each parameter was compared and the parameter with the highest accuracy was identified. We found that the activation function has a significant impact on the detection accuracy, which is 98% for softmax.

• Journal of Food Hygiene and Safety
• /
• v.11 no.2
• /
• pp.129-132
• /
• 1996

Recently, as concern about the residual antibiotics in milk increase, the detection methods of residual antibiotics used extensevely at the present time were investigated and compared to their properties and the detection limits of variable antibiotics. At first, comparactive tests of the detectable sensitivity of 4 test organisms, B. cereus, B. subtilis, M.luteus, B.stearothermophilus C-953, were performed by disc assay. As a result, B.stearothermophilus was the most sensitive strain of all other strains and showe the detect limit of 5-50 ppb for penlicillins (PCs). And also, B.subitilis was showed the more effective detection limit, 200-400 ppb, for aminoglycosides (AGs) and M.luteus was showed predominant sensitivity , 50-500 ppb for macrolides(MLs) and B.cereus was the most sensitive strain for tetracyclines (TCs) and showed the detection limit of 100-400 ppb. Therefore, each test strains were showed a different sensitivity in the detection of the different antibiotic families. When the detection limit of disc assay and other methods were compared, TTCmethod was less sensitive than other methods showing 5-50 ppb detectable lebel for PCs. Also, for the detection of other antibiotic families TTC method was showed the worst sensitivity and Delvo and Charm Farm tests were similar to the detectable properties of AGs and MLs. Although disc assay was showed the similar detection limit for PCs with Delvo and Charm Farm, it was more widely effective for the detection of kanamycin, erythromycin, chlortetracycline, doxycycline, verginiamycin and so on than Delvo or Charm Farm. CharmII test was showed the best sensitivity for the most of antibiotics except neomycin and gentamycin. But it was necessary that different tests must be performed to each antibiotic family and so it was regarded that the effectiveness of that method was low.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5643-5656
• /
• 2016

The detection accuracy of steganalysis depends on many factors, including the embedding algorithm, the payload size, the steganalysis feature space and the properties of the cover source. In practice, the cover source mismatch (CSM) problem has been recognized as the single most important factor negatively affecting the performance. To address this problem, we propose a new framework for blind, universal steganalysis which uses traditional steganalyst features. Firstly, cover images with the same statistical properties are searched from a reference image database as aided samples. The test image and its aided samples form a whole test set. Then, by assuming that most of the aided samples are innocent, we conduct outlier detection on the test set to judge the test image as cover or stego. In this way, the framework has removed the need for training. Hence, it does not suffer from cover source mismatch. Because it performs anomaly detection rather than classification, this method is totally unsupervised. The results in our study show that this framework works superior than one-class support vector machine and the outlier detector without considering the image retrieval process.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1311-1317
• /
• 2021

In this study, an airborne alpha detection system, which consists of a passivated implanted planar silicon (PIPS) detector and an air filter, was developed. A collimator applied to the alpha detection system showed an enhancement in resolution and a degradation in detection efficiency. The resolution and detection efficiency were compared and analyzed to evaluate the performance of the collimator. Thus, the resolution was found to be more important than the efficiency as a determining factor of the detection system performance, from the viewpoint of radionuclide identification. The performance was evaluated on three properties of the collimator: hole shape, hole length, and the ratio between the hole and frame pitches. From the hole shape performance evaluation, a hexagonal collimator showed the highest resolution. Further, the collimator with a hole pitch of 14 mm was found to have the highest resolution while that with a frame pitch of 4-6 mm (i.e., 1.2-1.4 times longer than the hole pitch) showed the highest resolution.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.2
• /
• pp.359-363
• /
• 2019

As commercial drones have been widely used, concerns for collision accidents with people and invading secured properties are emerging. The detection of drone is a challenging problem. The deep learning based object detection techniques for detecting drones have been applied, but limited to the specific cases such as detection of drones from bird and/or background. We have tried not only detection of drones, but classification of different drones with an end-to-end model. YOLOv2 is used as an object detection model. In order to supplement insufficient data by shooting drones, data augmentation from collected images is executed. Also transfer learning from ImageNet for YOLOv2 darknet framework is performed. The experimental results for drone detection with average IoU and recall are compared and analysed.

• Preventive Nutrition and Food Science
• /
• v.5 no.3
• /
• pp.136-141
• /
• 2000

The properties of pulsed photostimulated luminescence (PPSL) were measured to use as basis data for the detection of irradiated foodstuffs (34 different foods). Samples were packed in polyethylene bags and irradiated at 1, 5, and 10 kGy with a dose rate of 10 kGy/h. The samples irradiated were introduced in the sample chamber without other preparation and measured PPSL photon counts for 60 and 120 s. The PPSL photo counts of the irradiated samples were higher than the unirradiated, increased with increasing irradiation dose, and showed a good relationship between irradiation doses and photon counts in a multinomial expression. These results suggest that the detection of irradiated foodstuffs was possible by PPSL. Therefore, PPSL can be proposed as the method for the detection of irradiated foodstuffs.