• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.383-391
• /
• 2017

In image processing, image segmentation has been studied by various methods in a long time. Image segmentation is the process of partitioning a digital image into multiple objects and face detection is a typical image segmentation field being used in a variety of applications that identifies human faces in digital images. In this paper, we propose a method for extracting the contours of faces included in images. Using the Viola-Jones algorithm, to do this, we detect the approximate locations of faces from images. But, the Viola-Jones algorithm could detected the approximate location of face not the correct position. In order to extract a more accurate face region from image, we use skin color in this paper. In details, face region would be extracted using the analysis of horizontal and vertical histograms on the skin area. Finally, the face contour is extracted using snake algorithm for the extracted face area. In this paperr, a modified snake energy function is proposed for face contour extraction based snake algorithm proposed by Williams et al.[7]

• Journal of Food Hygiene and Safety
• /
• v.26 no.3
• /
• pp.273-282
• /
• 2011

This study established hazards which may cause risk to human at farm during cultivation stage of paprika. Samples of plants (paprika, leaf, stem), cultivation environments (water, soil), personal hygiene (hand, glove, clothes), work utensils (carpet, basket, box) and airborne bacteria were collected from three paprika farms (A, B, C) located in Western Gyeongnam, Korea. The collected samples were assessed for biological (sanitary indications and major foodborne pathogens), chemical (heavy metals, pesticide residues) and physical hazards. In biological hazards, total bacteria and coliform were detected at the levels of 1.9~6.6 and 0.0~4.610g CFU/g, leaf, mL, hand or 100 $cm^2$, while Escherichia coli was not detected in all samples. In major pathogens, only Bacillus cereus were detected at levels of ${\leq}$ 1.5 log CFU/g, mL, hand or 100 $cm^2$, while Staphylococuus aureus, Listeria monocytogenes, E. coli O157 and Salmonella spp. were not detected in all samples. Heavy metal and pesticide residue as chemical hazards were detected at levels below the regulation limit, physical hazard factors, such as insects, pieces of metal and glasses, were also found in paprika farms. Proper management is needed to prevent biological hazards due to cross-contamination while physical and chemical hazards were appropriate GAP criteria.

• Journal of Life Science
• /
• v.16 no.2 s.75
• /
• pp.323-327
• /
• 2006

The Formation of acrylamide was studied in Maillard model reaction systems based on asparagine-glucose. The mixture of asparagine and glucose in equal molar ratio, and then heated at 125, 150, 175 and $200^{\circ}C$ for 10, 20 and 30 minute, respectively. The reaction products were extracted with ethyl acetate and methanol, and then isolated and detected on FFAP capillary column and HP-5MS 5% phenyl methyl siloxane column by using GC/MS. Acrylamide was detected only from methanol extracts and on FFAP capillary column, at retention time 23.53 min., and the detection limit was 4.6 ng. Acrylamide content mainly increased with increasing temperature and processing time till $175^{\circ}C$, therefore, maximal acrylamide formation occurred at $175^{\circ}C$ for 10 minute ($116{\mu}g/g$), while, above $175^{\circ}C$, higher temperatures or prolonged processing times caused a decrease of acrylamide levels, finally disappeared at $200^{\circ}C$ for 30 minute. Three major compounds were identified as 1,3-dihydroxypropanone, 2,3-dihydro-3,5-dihydroxy-6-methyl-4H-pyrane-4-one and 5-hydroxymethylfurfural, and three minor compounds also as 5-methylfurfural, 2-acetylpyrrole and N,N-dimethylcyclohexamine, from ethyl acetate or methanol extracts on FFAP or HP-5MS capillary column.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.11
• /
• pp.305-313
• /
• 2019

Recently, spatial information is being constructed actively based on the images obtained by drones. Because occlusion areas occur due to buildings as well as many obstacles, such as trees, pedestrians, and banners in the urban areas, an efficient way to resolve the problem is necessary. Instead of the traditional way, which replaces the occlusion area with other images obtained at different positions, various models based on deep learning were examined and compared. A comparison of a type of feature descriptor, HOG, to the machine learning-based SVM, deep learning-based DNN, CNN, and RNN showed that the CNN is used broadly to detect and classify objects. Until now, many studies have focused on the development and application of models so that it is impossible to select an optimal model. On the other hand, the upgrade of a deep learning-based detection and classification technique is expected because many researchers have attempted to upgrade the accuracy of the model as well as reduce the computation time. In that case, the procedures for generating spatial information will be changed to detect the occlusion area and replace it with simulated images automatically, and the efficiency of time, cost, and workforce will also be improved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.4B
• /
• pp.566-575
• /
• 2010

In recent, artificial immune system has become an important research direction in the anomaly detection of networks. The conventional artificial immune systems are usually based on the negative selection that is one of the computational models of self/nonself discrimination. A main problem with self and non-self discrimination is the determination of the frontier between self and non-self. It causes false positive and false negative which are wrong detections. Therefore, additional functions are needed in order to detect potential anomaly while identifying abnormal behavior from analogous symptoms. In this paper, we design novel network attack detection and response schemes based on artificial immune system, and evaluate the performance of the proposed schemes. We firstly generate detector set and design detection and response modules through adopting the interaction between dendritic cells and T-cells. With the sequence of buffer occupancy, a set of detectors is generated by negative selection. The detection module detects the network anomaly with a set of detectors and generates alarm signal to the response module. In order to reduce wrong detections, we also utilize the fuzzy number theory that infers the degree of threat. The degree of threat is calculated by monitoring the number of alarm signals and the intensity of alarm occurrence. The response module sends the control signal to attackers to limit the attack traffic.

• Korean Journal of Food Science and Technology
• /
• v.36 no.6
• /
• pp.1032-1040
• /
• 2004

Biological, physical, and chemical hazards in raw manufacturing processes of Saengshik, powdered raw grains and vegetables, were analyzed to identify critical control points (CCPs). In raw materials, total plate and coliform counts ranged 2.82-8.23 and $1.40-6.57\;{\log}_{10}\;CFU/g$, respectively. In final products, total plate counts, except for Lactobacillus spp., were $1.51-7.40\;{\log}_{10}\;CFU/g$. During processing steps, both total plate and coliform counts decreased after washing, whereas no changes were observed after freeze-drying. Physical hazards, such as contents of metal and other contaminants, and chemical hazards, such as moisture content, were assessed. Suggested CCPs for Saengshik were: washing process for controlling microbial contamination, freeze-drying process for controlling moisture content to prevent deterioration and growth of microorganisms, and pulverization process for controlling contamination of foreign substances such as metals. These results will provide guideline to apply HACCP system standards to this product.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.282-294
• /
• 2017

In this paper, we propose a novel intelligent headlight control (IHC) system which is durable to various road lights and camera movement caused by vehicle driving. For detecting candidate light blobs, the region of interest (ROI) is decided as front ROI (FROI) and back ROI (BROI) by considering the camera geometry based on perspective range estimation model. Then, light blobs such as headlights, taillights of vehicles, reflection light as well as the surrounding road lighting are segmented using two different adaptive thresholding. From the number of segmented blobs, taillights are first detected using the redness checking and random forest classifier based on Haar-like feature. For the headlight and taillight classification, we use the random forest instead of popular support vector machine or convolutional neural networks for supporting fast learning and testing in real-life applications. Pairing is performed by using the predefined geometric rules, such as vertical coordinate similarity and association check between blobs. The proposed algorithm was successfully applied to various driving sequences in night-time, and the results show that the performance of the proposed algorithms is better than that of recent related works.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.6
• /
• pp.786-792
• /
• 2010

This paper presents a real-time lane detection method which can accurately find the lane-mark boundaries in complex road environment. Unlike many existing methods that pay much attention on the post-processing stage to fit lane-mark position among a great deal of outliers, the proposed method aims at removing those outliers as much as possible at feature extraction stage, so that the searching space at post-processing stage can be greatly reduced. To achieve this goal, a grid-based morphology operation is firstly used to generate the regions of interest (ROI) dynamically, in which a directional edge-linking algorithm with directional edge-gap closing is proposed to link edge-pixels into edge-links which lie in the valid directions, these directional edge-links are then grouped into pairs by checking the valid lane-mark width at certain height of the image. Finally, lane-mark colors are checked inside edge-link pairs in the YUV color space, and lane-mark types are estimated employing a Bayesian probability model. Experimental results show that the proposed method is effective in identifying lane-mark edges among heavy clutter edges in complex road environment, and the whole algorithm can achieve an accuracy rate around 92% at an average speed of 10ms/frame at the image size of $320{\times}240$.

• Korean Journal of Food Science and Technology
• /
• v.29 no.6
• /
• pp.1166-1174
• /
• 1997

This study was designed to investigate the changes in physicochemical and sensory characteristics of traditional kochujang during aging, which was prepared with a different meju fermented for various periods of time. The non-volatile organic acid contents in all samples gradually increased up to 90 days of fermentation. Kochujang prepared with a 40-day-fermented meju had $1.14{\sim}2.54$ times highter organic acid content after 90 days of aging as compared to other kochujang preparations. The most abundant free sugars were found to be glucose and fructose representing $82.27{\sim}100%$ of total free sugar contents in kochujang. 17 kinds of free amino acid including Glu, Asp and Met were found in traditional kochujang aged for 90 days. Glu was noted as the most contributing amino acid to the brothy taste of kochujang in the light of increasing ratio and content of Glu among free amino acids during aging. The total free amino acid contents of kochujang increased with an Increase in fermentation time of meju. Results of sensory evaluation revealed that kochujang prepared with a 40-day-fermented meju was best in terms of flavor and taste. These results suggest that kochujang prepared with a 40-day-fermented meju had the highest quality in terms of physicochemical and sensory characteristics of kochujang.

• Journal of Sensor Science and Technology
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2001

Conventional microgyroscopes of vibrating type require resonant frequency tuning of the driving and sensing modes to achieve high sensitivity. These tuning conditions depend on each fabricated microgyroscopes, even though the microgyroscopes are identically designed. A new micromachined resonator, which is applicable to microgyroscopes with self-toning characteristics, is presented. Since the laterally driven two degrees of freedom (2DOF) resonator was designed as a symmetric structure with identical stiffness in two orthogonal axes, the resonator is applicable to vibrating microgyroscopes, which do not need mode tuning. A dynamic model of the resonator was derived considering gyroscopic application. The dynamic model was evaluated by experimental comparison with fabricated resonators. The microgyroscopes were fabricated using a simple 2-mask-process of a single polysilicon layer deposited on an insulator layer. The feasibility of the resonator as a vibrating microgyroscopes with self-tuning capability is discussed. The fabricated resonators of a particular design have process-induced non-uniformities that cause different resonant frequencies. For several resonators, the standard deviations of the driving and sensing frequencies were as high as 1232Hz and 1214Hz, whereas the experimental average detuning frequency was 91.75Hz. The minimum detuned frequency was 68Hz with $0.034mVsec/^{\circ}$ sensitivity. The sensitivity of the microgyroscopes was low due to process-induced non-uniformity; the angular rate bandwidth, however, was wide. This resonator could be successfully applicable to a vibrating microgyroscopes with high sensitivity, if improvements in uniformity of the fabrication process are achieved. Further developments in improved integrated circuits are expected to lower the noise level even more.