• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11C
• /
• pp.75-84
• /
• 2001

In this paper, we propose an on-line FDD(Fault Detection and Diagnosis) system based on the three layer feed-forward neural network which is trained by the back-propagation teaming algorithm. We implement the on-line fault detection and diagnosis system by Visual C++ and Visual Basic. The proposed FDD system is applied to an air handling unit in operation. Experimental results show the high performance of our system in the task of fault detection and diagnosis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.615-618
• /
• 2019

Visual saliency detection is an important part in various vision-based applications. There are a myriad of techniques for saliency detection in color images. However, the number of methods for saliency detection in infrared images is inadequate. In this paper, we introduce a simple approach for pedestrian identification in infrared images using saliency. The input image is thresholded into several Boolean maps, an initial saliency map is then calculated as a weighted sum of created Boolean maps. The initial map is further refined by using thresholding, morphology operation, and Gaussian filter to produce the final, high-quality saliency map. The experiment showed that the proposed method produced high performance results when applied to real-life data.

• ETRI Journal
• /
• v.41 no.4
• /
• pp.483-493
• /
• 2019

Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand-crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel-level agreement to the model learned from the detection phase is achieved. Our two-phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1159-1181
• /
• 2016

This study introduces an image-based 2D-to-3D conversion system that provides significant stereoscopic visual effects for humans. The linear and atmospheric perspective cues that compensate each other are employed to estimate depth information. Rather than retrieving a precise depth value for pixels from the depth cues, a direction angle of the image is estimated and then the depth gradient, in accordance with the direction angle, is integrated with superpixels to obtain the depth map. However, stereoscopic effects of synthesized views obtained from this depth map are limited and dissatisfy viewers. To obtain impressive visual effects, the viewer's main focus is considered, and thus salient object detection is performed to explore the significance region for visual attention. Then, the depth map is refined by locally modifying the depth values within the significance region. The refinement process not only maintains global depth consistency by correcting non-uniform depth values but also enhances the visual stereoscopic effect. Experimental results show that in subjective evaluation, the subjectively evaluated degree of satisfaction with the proposed method is approximately 7% greater than both existing commercial conversion software and state-of-the-art approach.

• Journal of the Optical Society of Korea
• /
• v.16 no.2
• /
• pp.145-150
• /
• 2012

We present a display-based visual stimulator for psychophysical and electrophysiological visual sensitivity measurements. The stimulator offers various psychophysical visual stimuli and transfers the signals from external devices along with the stimulation signals to an electrophysiological recorder. As an experimental demonstration, we perform a visual sensitivity experiment in the mesopic vision range by using the display-based stimulator. The intensity of the steady-state visual evoked potential is observed to correlate with the luminance of the flickering visual stimulation. For the psychophysically determined detection thresholds, we determine the mesopic luminance, showing agreement with the perceived brightness within the uncertainty of the luminance measurement.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.137-151
• /
• 2014

This paper proposes a method of detecting object of interest(OOI) in general natural images. OOI is subjectively estimated by human in images. The vision of human, in general, might focus on OOI. As the first step for automatic detection of OOI, candidate regions of OOI are detected by using a saliency map based on the human visual perception. A saliency map locates an approximate OOI, but there is a problem that they are not accurately segmented. In order to address this problem, in the second step, an exact object region is automatically detected by combining graph-based image segmentation and skeletonization. In this paper, we calculate the precision, recall and accuracy to compare the performance of the proposed method to existing methods. In experimental results, the proposed method has achieved better performance than existing methods by reducing the problems such as under detection and over detection.

• Journal of Microbiology and Biotechnology
• /
• v.31 no.5
• /
• pp.705-709
• /
• 2021

Porphyromonas gingivalis (P. gingivalis) is a major bacterial pathogen that causes periodontitis, a chronic inflammatory disease of tissues around the teeth. Periodontitis is known to be related to other diseases, such as oral cancer, Alzheimer's disease, and rheumatism. Thus, a precise and sensitive test to detect P. gingivalis is necessary for the early diagnosis of periodontitis. The objective of this study was to optimize a rapid visual detection system for P. gingivalis. First, we performed a visual membrane immunoassay using 3,3',5,5'-tetramethylbenzidine (TMB; blue) and coating and detection antibodies that could bind to the host laboratory strain, ATCC 33277. Antibodies against the P. gingivalis surface adhesion molecules RgpB (arginine proteinase) and Kgp (lysine proteinase) were determined to be the most specific coating and detection antibodies, respectively. Using these two selected antibodies, the streptavidin-horseradish peroxidase (HRP) reaction was performed using a nitrocellulose membrane and visualized with a detection range of 10³-10⁵ bacterial cells/ml following incubation for 15 min. These selected conditions were applied to test other oral bacteria, and the results showed that P. gingivalis could be detected without cross-reactivity to other bacteria, including Streptococcus mutans and Escherichia fergusonii. Furthermore, three clinical strains of P. gingivalis, KCOM 2880, KCOM 2803, and KCOM 3190, were also recognized using this optimized enzyme immunoassay (EIA) system. To conclude, we established optimized conditions for P. gingivalis detection with specificity, accuracy, and sensitivity. These results could be utilized to manufacture economical and rapid detection kits for P. gingivalis.

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.3
• /
• pp.255-265
• /
• 2017

Objective: This study aims to survey visual search performance models to assess and predict individual's visual tasks in everyday life and industrial sites. Background: Visual search is one of the most frequently performed and critical activities in everyday life and works. Visual search performance models are needed when designing or assessing the visual tasks. Method: This study was mainly based on survey of literatures related to ergonomics relevant journals and web surfing. In the survey, the keywords of visual search, visual search performance, visual search model, etc. were used. Results: On the basis of the purposes, developing methods and results of the models, this study categorized visual search performance models into six groups: probability-based models, SATO models, visual lobe-based models, computer vision models, neutral network-based models and detection time models. Major models by the categories were presented with their advantages and disadvantages. More models adopted the accuracy among two factors of accuracy and speed characterizing visual tasks as dependent variables. Conclusion: This study reviewed and summarized various visual search performance models. Application: The results would be used as a reference or tool when assessing the visual tasks.

• The Journal of the Korean dental association
• /
• v.49 no.8
• /
• pp.461-471
• /
• 2011

The detection of carious lesions is a key point to apply appropriate preventive measures or operative treatment of dental caries. A laser fluorescence device DIAGNOdent$^{(R)}$ (KaVo, Biberach, Germany) has also been shown to be of additional clinical value in the detection of initial caries. This report focus on the DIAGNOdent$^{(R)}$ for caries detection. DIAGNOdent$^{(R)}$ irradiate visible red light at a wavelength of 655 nm to elicit near-infrared fluorescence from caries lesion. This device is known as a reproducible method for caries detection, with good sensitivity and specificity especially for caries detection on occlusal and accessible smooth surfaces. DIAGNOdent$^{(R)}$ tended to be more sensitive method of detecting occlusal dentinal caries, however, showed more false-positive diagnoses than the visual inspection. So Clinician should not use the device as a clinician's primary diagnostic method and it is recommended that the device should be used in the decision-making process in relation to the diagnosis of caries as a second opinion in cases of doubt after visual inspection. The trend of modern dentistry would be a preventive approach rather than invasive treatment of the disease. This is possible only with early detection and respective preventive measures, DIAGNOdent$^{(R)}$ can help the changes.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.132-142
• /
• 2014

In this paper, we propose a traffic lights detection method using visual attention and spot-lights detection. To detect traffic lights in city streets at day and night time, the proposed method is used the structural form of a traffic lights such as colors, intensity, shape, textures. In general, traffic lights are installed at a position to increase the visibility of the drivers. The proposed method detects the candidate traffic lights regions using the top-down visual saliency model and spot-lights detect models. The visual saliency and spot-lights regions are positions of its difference from the neighboring locations in multiple features and multiple scales. For detecting traffic lights, by not using a color thresholding method, the proposed method can be applied to urban environments of variety changes in illumination and night times.