• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.113-121
• /
• 2005

Face detection in real-time video constitutes one of the major trend in face recognition. In this paper, we propose a face detection algorithm using the skin color and Haar-like feature in real-time video. The proposed algorithm is followed by three sequences; First, moving objects are detected by difference-method in YCbCr coordinates, and then by using Haar-like features, face candidate regions of the moving objects is selected. Finally we extract the most possible face candidates by comparing the pixel values of face candidates with the skin color. In order to prevent a mistake. we use similar features or skin color to detect a face by selecting a adaptive ROI and improve the processing speed in real-time video. The computer simulation shows the validity of the proposed method that the processing speed is improved by 30% than previous works and the detection success rate is 96.8%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.1
• /
• pp.67-74
• /
• 2002

A study on image searching and management techniques is actively developed by user requirements for multimedia information that are existing as images, audios, texts data from various information processing devices. If we can automatically detect and segment changing scenes from real-time image sequences, we can improve an effectiveness of image searching systems. In this paper, we propose cut detection techniques based on image color distribution and we evaluated its performance on various real-time image sequences. Results of experiments show that the proposed method are robust on various image patterns than color histogram method using statistical informations of images. Also, these methods can be used for cut detection on real-time image sequences.

• Journal of Veterinary Clinics
• /
• v.22 no.4
• /
• pp.348-352
• /
• 2005

We described a rapid, sensitive and reproducible real-time PCR assay for detection and quantitation of canine parvovirus type 2 in the feces of dogs with parvovirus infection. The method was demonstrated to be highly specific and sensitive, allowing a precise canine parvovirus type-2 quantitation over range of eight orders of magnitude from $10^2\;to\;10^9$ copies of standard DNA. Then, fecal samples from parvovirus infected dogs were analyzed by conventional PCR and real-time PCR. Real-time PCR is more sensitive than conventional PCR, allowing to detect low viral titers of CPV-2 in infected dogs. By real-time PCR, a wide range of parvovirus particles was found in the samples from $1.45\times10^6\;to\;9.45\times10^8$ copies/0.01g of feces. However, when dogs are in infection of parvovirus, it is difficult to prove that the numbers of peripheral blood leukocytes are correlated with those of fecal shedding virus.

• Research in Plant Disease
• /
• v.14 no.3
• /
• pp.219-222
• /
• 2008

Real time PCR was used to discriminate Colletotrichum acutatum and C. gloeosporioides for analysis of population density. Two primers, caInt2 and cgint, used for conventional PCR to discriminate two species were modified with fluorescent dye to make probe for real time PCR. Fluorescence signals were successfully detected by fCaInt2 and vCgint probe coupled with primer pair Unicon and Unicor1 resulting in discrimination of C. acutatum and C. gloeosporioides by comparison of delta Rn value.

• Journal of Marine Bioscience and Biotechnology
• /
• v.2 no.4
• /
• pp.263-266
• /
• 2007

Vibrio vulnificusis a causative agent of serious diseases in humans resulting from the contact of wound with seawater or consumption of raw seafood. Several studies aimed at detecting V. vulnificus have targeted vvh as a representative virulence toxin gene belonging to the bacterium. In this study, we targeted the rpoS gene, a general stress regulator, to detect V. vulnificus. PCR specificity was identified by amplification of 8 V. vulnificus templates and by the loss of a PCR product with 36 non-V. vulnificus strains. The PCR assay had the 273-bp fragment and the sensitivity of 10 pg DNA from V. vulnificus. SYBR Green I-based real-time PCR assay targeting the rpoS gene showed a melting temperature of approximately $84^{\circ}C$ for V. vulnificus strains. The minimum level of detection by real-time PCR was 2 pg of purified genomic DNA, or $10^3$ V. vulnificus cells from pure cultured broth and $10^3$ cells in 1g of oyster tissue homogenates. These data indicate that real-time PCR is a sensitive, species-specific, and rapid method for detecting this bacterium using the rpoS gene in pure cultures and in infected oyster tissues.

• Food Science of Animal Resources
• /
• v.41 no.1
• /
• pp.85-94
• /
• 2021

A pig-specific real-time PCR assay based on the mitochondrial ND5 gene was developed to detect porcine material in food and other products. To optimize the performance of assay, seven commercial TaqMan master mixes and two real-time PCR platforms (Applied Biosystems StepOnePlus and Bio-rad CFX Connect) were used to evaluate the limit of detection (LOD) as well as the PCR efficiency and specificity. The LODs and PCR efficiencies for the seven master mixes on two platforms were 0.5-5 pg/reaction and 84.96%-108.80%, respectively. Additionally, non-specific amplifications of DNA from other animal samples (human, dog, cow, and chicken) were observed for four master mixes. These results imply that the sensitivity and specificity of a real-time PCR assay may vary depending on master mix and platform used. The best combination of master mix and real-time PCR platform can accurately detect 0.5 pg porcine DNA, with a PCR efficiency of 100.49%.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.2
• /
• pp.150-161
• /
• 2012

Eye detection is widely used in applications, such as face recognition, driver behavior analysis, and human-computer interaction. However, it is difficult to achieve real-time performance with software-based eye detection in an embedded environment. In this paper, we propose a parallel hardware architecture for real-time eye detection. We use the AdaBoost algorithm with modified census transform(MCT) to detect eyes on a face image. We parallelize part of the algorithm to speed up processing. Several downscaled pyramid images of the eye candidate region are generated in parallel using the input face image. We can detect the left and the right eye simultaneously using these downscaled images. The sequential data processing bottleneck caused by repetitive operation is removed by employing a pipelined parallel architecture. The proposed architecture is designed using Verilog HDL and implemented on a Virtex-5 FPGA for prototyping and evaluation. The proposed system can detect eyes within 0.15 ms in a VGA image.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.3
• /
• pp.185-192
• /
• 2015

Since real-time monitoring systems, such as early fault detection, have been very important, an infrared thermography technique was proposed as a new diagnosis method. This study focused on damage detection and temperature characteristic analysis of ball bearings using the non-destructive, infrared thermography method. In this paper, for the reliability assessment, infrared experimental data were compared with finite element analysis (FEA) results from ANSYS. In this investigation, the temperature characteristics of ball bearing were analyzed under various loading conditions. Finally, it was confirmed that the infrared thermography technique was useful for the real-time detection of damage to bearings.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.25 no.1
• /
• pp.76-83
• /
• 2012

In a real-time indoor place recognition system using image features detection, specific markers included in input image should be detected exactly and quickly. However because the same markers in image are shown up differently depending to movement, direction and angle of camera, it is required a method to solve such problems. This paper proposes a technique to extract the features of object without regard to change of the object scale. To support real-time operation, it adopts SURF(Speeded up Robust Features) which enables fast feature detection. Another feature of this system is the user mark designation which makes possible for user to designate marks from input image for location detection in advance. Unlike to use hardware marks, the feature above has an advantage that the designated marks can be used without any manipulation to recognize location in input image.

• Journal of information and communication convergence engineering
• /
• v.13 no.1
• /
• pp.42-49
• /
• 2015

In laser pointer interaction systems, laser spot detection is one of the most important technologies, and most of the challenges in this area are related to the varying backgrounds, and the real-time performance of the interaction system. In this paper, we present a robust dictionary construction and update algorithm based on a sparse model of background subtraction. In order to control dynamic backgrounds, first, we determine whether there is a change in the backgrounds; if this is true, the new background can be directly added to the dictionary configurations; otherwise, we run an online cumulative average on the backgrounds to update the dictionary. The proposed dictionary construction and update algorithm for laser spot detection, is robust to the varying backgrounds and noises, and can be implemented in real time. A large number of experimental results have confirmed the superior performance of the proposed method in terms of the detection error and real-time implementation.