• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.13-20
• /
• 2004

In the real-time automatic face recognition technique, accurate face detection is essential and very important part because it has the effect to face recognition performance. In this paper, we use color information, edge information, and binary information to detect candidate regions of eyes from Input image, and then detect face candidate region using the center point of the detected eyes. We verify both eye candidate region and face candidate region using Support Vector Machines(SVM). It is possible to perform fast and reliable face detection because we can protect false detection through these verification process. From the experimental results, we confirmed the Proposed algorithm in this paper shows excellent face detection rate over 99%.

• Journal of the Korean Society of Combustion
• /
• v.6 no.2
• /
• pp.65-70
• /
• 2001

To investigate statistics of flamelet in a turbulent premixed flame and to obtain components of their burning velocities in a vertical plane above a pipe-flow burner, the local motion of flamelets with respect to gas are measured by specially arranged diagnostics, composed of an electrostatic probe with four identical sensors and a two-color four-beam LDV system. With this technique, the three-dimensional local flame-front-velocity vector is measured by the electrostatic probe for the first time, and simultaneously the axial and radial components of the local gas-velocity vector in a vertical plane above the vertically oriented burner are measured by the LDV system. Two components of burning velocities of planar flamelets can be obtained from these results and are found to be distributed over different directions and to range in magnitude from nearly zero to a few times the planar, unstrained adiabatic laminar burning velocity measured in the unburnt gas. It may be concluded from these results that turbulence exerts measurable influences on flamelets and causes at least some of them to exhibit increased burning velocity.

• Journal of the Korean Society of Combustion
• /
• v.7 no.2
• /
• pp.62-68
• /
• 2002

To investigate statistics of flamelet in a turbulent premixed flame and to obtain components of their burning velocities in a vertical plane above a pipe-flow burner, the local motion of flamelets with respect to gas are measured by specially arranged diagnostics, composed of an electrostatic probe with four identical sensors and a two-color four-beam LDV system. With this technique, the three-dimensional local flame- front-velocity vector is measured by the electrostatic probe for the first time, and simultaneously the axial and radial components of the local gas-velocity vector in a vertical plane above the vertically oriented burner are measured by the LDV system. Two components of burning velocities of planar flamelets can be obtained from these results and are found to be distributed over different directions and to range in magnitude from nearly zero to a few times the planar, un strained adiabatic laminar burning velocity measured in the unburnt gas. It may be concluded from these results that turbulence exerts measurable influences on flamelets and causes at least some of them to exhibit increased burning velocity.

• Journal of Satellite, Information and Communications
• /
• v.8 no.1
• /
• pp.77-82
• /
• 2013

The object tracking method using particle filtering has been proved successful since it is based on the Monte Carlo simulation to estimate the posterior distribution of the state vector that is nonlinear and non-Gaussian in the real-world situation. In this paper, we present two nobel methods that can improve the performance of the object tracking algorithm based on the particle filtering. First one is the feedback method that replace the low-weighted tracking sample by the estimated state vector in the previous frame. The second one is an tracking box correction method to find an confidence interval of back projection probability on the estimated candidate object area. An sample propagation equation is also presented, which is obtained by experiments. We designed well-organized test data set which reflects various challenging circumstances, and, by using it, experimental results proved that the proposed methods improves the traditional particle filter based object tracking method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.490-498
• /
• 2011

In this paper, we present a two-stage vision-based approach to detect multi views of pedestrian in road scene images. The first stage is HG (Hypothesis Generation), in which potential pedestrian are hypothesized. During the hypothesis generation step, we use a vertical, horizontal edge map, and different colors between road background and pedestrian's clothes to determine the leg position of pedestrian, then a novel symmetry peaks processing is performed to define how many pedestrians is covered in one potential candidate region. Finally, the real candidate region where pedestrian exists will be constructed. The second stage is HV (Hypothesis Verification). In this stage, all hypotheses are verified by Support Vector Machine for classification, which is robust for multi views of pedestrian detection and recognition problems.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1223-1232
• /
• 2019

The injection is the input method of the image feature vector from the encoder to the decoder. Since the image feature vector contains object details such as color and texture, it is essential to generate image captions. However, the bidirectional decoder model using the existing injection method only inputs the image feature vector in the first step, so image feature vectors of the backward sequence are vanishing. This problem makes it difficult to describe the context in detail. Therefore, in this paper, we propose the parallel injection method to improve the description performance of image captions. The proposed Injection method fuses all embeddings and image vectors to preserve the context. Also, We optimize our image caption model with Bidirectional Gated Recurrent Unit (Bi-GRU) to reduce the amount of computation of the decoder. To validate the proposed model, experiments were conducted with a certified image caption dataset, demonstrating excellence in comparison with the latest models using BLEU and METEOR scores. The proposed model improved the BLEU score up to 20.2 points and the METEOR score up to 3.65 points compared to the existing caption model.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.4
• /
• pp.87-94
• /
• 2007

Imbalances in focus, luminance and color between stereo Pairs could cause disparity vector estimation error and increment of transmission data. If the distribution of errors in residual image is large, it may influence to lowering of compression performance. Therefore, in this paper, we propose an efficient balancing method between stereo pairs to reduce the effect. For this, we registrated stereo images using a FFT based method to consider the pixels in the occluded region, we eliminated the pixels of blocks which has large error of disparity vector estimation in balancing function estimation. The balancing function has estimated using histogram specification, local information of target image and residual image between stereo images. Experiments show that the proposed method is effective in error distribution, PSNR and disparity vector estimation. We expect that our method can be improving compression efficiency in stereo coding system.

• Journal of Korea Multimedia Society
• /
• v.5 no.4
• /
• pp.415-425
• /
• 2002

In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome the drawbacks of the feature vector making up methods which use the global wavelet coefficients in subbands, we utilize the energy value of wavelet coefficients, and the shape-based retrieval of objects is processed by moment which is invariant in translation, scaling, rotation of the objects The proposed methods reduce feature vector size, and make progress performance of classification retrieval which provides fast retrievals times. To offer the abilities of region-based image retrieval, we discussed the image segmentation method which can reduce the effect of an irregular light sources. The image segmentation method uses a region-merging, and candidate regions which are merged were selected by the energy values of high frequency bands in discrete wavelet transform. The region-based image retrieval is executed by using the segmented region information, and the images are retrieved by a color, texture, shape feature vector.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.6
• /
• pp.21-28
• /
• 2013

This paper proposes an effective fire detection approach that includes the following multiple heterogeneous algorithms: moving region detection using grey level histograms, color segmentation using fuzzy c-means clustering (FCM), feature extraction using a grey level co-occurrence matrix (GLCM), and fire classification using support vector machine (SVM). The proposed approach determines the optimal threshold values based on grey level histograms in order to detect moving regions, and then performs color segmentation in the CIE LAB color space by applying the FCM. These steps help to specify candidate regions of fire. We then extract features of fire using the GLCM and these features are used as inputs of SVM to classify fire or non-fire. We evaluate the proposed approach by comparing it with two state-of-the-art fire detection algorithms in terms of the fire detection rate (or percentages of true positive, PTP) and the false fire detection rate (or percentages of true negative, PTN). Experimental results indicated that the proposed approach outperformed conventional fire detection algorithms by yielding 97.94% for PTP and 4.63% for PTN, respectively.

• Journal of Photoscience
• /
• v.7 no.2
• /
• pp.73-78
• /
• 2000

To analyze molecular traits determining pigmentation between Pharbitis nill violet and white, Amplified Fragment Length Polymorphism(AFLP) and Differential Display Reverse Transcription(DDRT) experiments were carried out with either genomic DNAs or total RNAs isolated from both plants. Results of AFLP experiment in combination of 8 EcoRⅠ primers with 6 MseⅠ primers showed 41 violet-and 60 white-specific DNA bands. In the subsequent experiment, 22 violet-and 22 white-specific DNA fragments were amplified by PCR with DNAs eluted. The sizes of the fragments range from 200 to 600bp. DDRT using total RNA produced 19 violet-and 17 white-specific cDNA fragments, ranging from 200 to 600bp. The fragments obtained by both AFLP and DDRT had been cloned into pGEM T-easy vector, amplified and subjected to the nucleotide sequence analyses. As a result of Blast sequence analysis, most of them sequenced up to date showed no similarity to any Known gene, while few has similarity to known animal or plant genes. An AFLP clone V6, for example, has a strong sequence similarity to the human transcription factor LZIP-alpha mRNA and a DDRT clone W19 to Solanum tuberosum 3-hydroxy-3-methylglutaryl coenzyme A reductase mRNA.