• ETRI Journal
• /
• v.41 no.6
• /
• pp.797-810
• /
• 2019

Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high-contrast background, but they have no effect on the extraction of a salient object from images with complex low-contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics-like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low-contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low-contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state-of-the-art approaches, the proposed approach performs well.

• Bulletin of the Korean Chemical Society
• /
• v.28 no.10
• /
• pp.1746-1750
• /
• 2007

The second-order scattering (SOS) phenomenon of the interaction of Pd nanoparticles with protein was reported and a simple, sensitive, palladium nanoparticle-based assay for trace amount of protein with SOS technique was developed. The SOS intensities were significantly enhanced due to the interaction of Pd nanoparticles with bovine serum albumin (BSA) or human serum albumin (HSA) at pH 3.5 or 4.0, respectively. The maximum SOS peak appeared at 260/520 nm (λex/λem). The optimal experiment conditions, affecting factors and the influence of some coexisting substances were checked. The SOS intensity increased proportionally with the increase of Pd concentration below 3.0 × 10?5 mol·L?1, while declined gradually above 4.0 × 10?5 mol·L?1. BSA within the range of 0.01-2.6 μg·mL?1 and HSA of 0.01-1.7 μg·mL?1 can be detected with this method and the detection limits were 2.3 and 11.2 ng·mL?1, respectively. The method was successfully applied to the quantitative detection of total protein content in human serum samples with the maximum relative standard deviation (RSD) lower than 2.6% and the recoveries over the range of 99.5-100.5%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.199-204
• /
• 2008

Visual surveillance is an active topic recently in Computer Vision. Event detection and recognition is one important and useful application of visual surveillance system. In this paper, we propose a new method to recognize the entering and exiting events based on the human's movement feature and the door's state. Without sensors, the proposed approach is based on novel and simple vision method as a combination of edge detection, motion history image and geometrical characteristic of the human shape. The proposed method includes several applications such as access control in visual surveillance and computer vision fields.

• Journal of Korean Institute of Industrial Engineers
• /
• v.29 no.2
• /
• pp.165-171
• /
• 2003

Visual search in an unstructured search field is a fruitful research area for computational modeling. Search models that describe relationship between search time and probability of target detection have been used for prediction of human search performance and provision of ideal goals for search training. Until recently, however, most of models were focused on detecting a single target in a search field, although, in practice, a search field includes multiple targets and search models for multiple targets may differ from search models for a single target. This study proposed a random search model for multiple targets, generalizing a random search model for a single target which is the most typical search model. To test this model, human search data were collected and compared with the model. This model well predicted human performance in visual search for multiple targets. This paper also proposed how to determine optimal stopping time in multiple-target search.

• Journal of Microbiology and Biotechnology
• /
• v.33 no.8
• /
• pp.1101-1110
• /
• 2023

Streptococcus mutans is the primary causative agent of caries, which is one of the most common human diseases. Thus, rapid and early detection of cariogenic bacteria is critical for its prevention. This study investigated the combination of loop-mediated isothermal amplification (LAMP) and microfluid technology to quantitatively detect S. mutans. A low-cost, rapid microfluidic chip using LAMP technology was developed to amplify and detect bacteria at 2.2-2.2 × 10⁶ colony-forming units (CFU)/ml and its detection limits were compared to those of standard polymerase chain reaction. A visualization system was established to quantitatively determine the experimental results, and a functional relationship between the bacterial concentration and quantitative results was established. The detection limit of S. mutans using this microfluidic chip was 2.2 CFU/ml, which was lower than that of the standard approach. After quantification, the experimental results showed a good linear relationship with the concentration of S. mutans, thereby confirming the effectiveness and accuracy of the custom-made integrated LAMP microfluidic system for the detection of S. mutans. The microfluidic system described herein may represent a promising simple detection method for the specific and rapid testing of individuals at risk of caries.

• Mycobiology
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2017

Drosophila melanogaster is a useful model organism that offers essential insights into developmental and cellular processes shared with humans, which has been adapted for large scale analysis of medically important microbes and to test the toxicity of heavy metals, industrial solvents and other poisonous substances. We here give a brief review of the use of the Drosophila model in medical mycology, discuss the volatile organic compounds (VOCs) produced by the opportunistic human pathogen, Aspergillus fumigatus, and give a brief summary of what is known about the toxicity of some common fungal VOCs. Further, we discuss the use of VOC detection as an indirect indicator of fungal growth, including for early diagnosis of aspergillosis. Finally, we hypothesize that D. melanogaster has promise for investigating the role of VOCs synthesized by A. fumigatus as possible virulence factors.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.2
• /
• pp.271-279
• /
• 2012

Objective: This study classified three different emotional states(boredom, pain, and surprise) using physiological signals. Background: Emotion recognition studies have tried to recognize human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 122 college students participated in this experiment. Three different emotional stimuli were presented to participants and physiological signals, i.e., EDA(Electrodermal Activity), SKT(Skin Temperature), PPG(Photoplethysmogram), and ECG (Electrocardiogram) were measured for 1 minute as baseline and for 1~1.5 minutes during emotional state. The obtained signals were analyzed for 30 seconds from the baseline and the emotional state and 27 features were extracted from these signals. Statistical analysis for emotion classification were done by DFA(discriminant function analysis) (SPSS 15.0) by using the difference values subtracting baseline values from the emotional state. Results: The result showed that physiological responses during emotional states were significantly differed as compared to during baseline. Also, an accuracy rate of emotion classification was 84.7%. Conclusion: Our study have identified that emotions were classified by various physiological signals. However, future study is needed to obtain additional signals from other modalities such as facial expression, face temperature, or voice to improve classification rate and to examine the stability and reliability of this result compare with accuracy of emotion classification using other algorithms. Application: This could help emotion recognition studies lead to better chance to recognize various human emotions by using physiological signals as well as is able to be applied on human-computer interaction system for emotion recognition. Also, it can be useful in developing an emotion theory, or profiling emotion-specific physiological responses as well as establishing the basis for emotion recognition system in human-computer interaction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.5112-5128
• /
• 2016

Tracking human body is an important problem in computer vision field. Tracking failures caused by occlusion can lead to wrong rectification of the target position. In this paper, a robust human tracking algorithm is proposed to address the problem of occlusion, rotation and improve the tracking accuracy. It is based on Tracking-Learning-Detection framework. The key auxiliary information is used in the framework which motivated by the fact that a tracking target is usually embedded in the context that provides useful information. First, face localization method is utilized to find key face location information. Second, the relative position relationship is established between the auxiliary information and the target location. With the relevant model, the key face information will get the current target position when a target has disappeared. Thus, the target can be stably tracked even when it is partially or fully occluded. Experiments are conducted in various challenging videos. In conjunction with online update, the results demonstrate that the proposed method outperforms the traditional TLD algorithm, and it has a relatively better tracking performance than other state-of-the-art methods.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.199-208
• /
• 2023

The emergence of COVID-19 virus has shaken almost every aspect of human life including but not limited to social, financial, and economic changes. One of the most significant impacts was obviously healthcare. Now though the pandemic has been over, its aftereffects are still there. Among them, a prominent one is people lifestyle. Work from home, enhanced screen time, limited mobility and walking habits, junk food, lack of sleep etc. are several factors that have still been affecting human health. Consequently, diseases like diabetes, high blood pressure, anxiety etc. have been emerging at a speed never witnessed before and it mainly includes the people at young age. The situation demands an early prediction, detection, and warning system to alert the people at risk. AI and Machine learning has been investigated tremendously for solving the problems in almost every aspect of human life, especially healthcare and results are promising. This study focuses on reviewing the machine learning based approaches conducted in detection and prediction of diabetes especially during and post pandemic era. That will help find a research gap and significance of the study especially for the researchers and scholars in the same field.

• Transactions on Electrical and Electronic Materials
• /
• v.8 no.6
• /
• pp.293-298
• /
• 2007

The aged are faced with increasing risk for falls. The aged have more fragile bones than others. When falls occur, it is important to detect this emergency state because such events often lead to more serious illness or even death. A implementation of PDA system, for detection of emergency situation, was developed using 3-axis accelerometer in this paper as follows. The signals were acquired from the 3-axis accelerometer, and then transmitted to the PDA through a Bluetooth module. This system can classify human activity, and also detect an emergency state like falls. When the fall occurs, the system generates the alarm on the PDA. If a subject does not respond to the alarm, the system determines whether the current situation is an emergency state or not, and then sends some information to the emergency center in the case of an urgent situation. Three different studies were conducted on 12 experimental subjects, with results indicating a good accuracy. The first study was performed to detect the posture change of human daily activity. The second study was performed to detect the correct direction of fall. The third study was conducted to check the classification of the daily physical activity. Each test lasted at least 1 min. in the third study. The output of the acceleration signal was compared and evaluated by changing various postures after attaching a 3-axis accelerometer module on the chest. The newly developed system has some important features such as portability, convenience and low cost. One of the main advantages of this system is that it is available at home healthcare environment. Another important feature lies in its low cost of manufacture. The implemented system can detect the fall accurately, so it will be widely used in emergency situations.