• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.385-394
• /
• 2009

Face tracking and recognition are difficult problems because the face is a non-rigid object. The main reasons for the failure to track and recognize the faces are the changes of a face pose and environmental illumination. To solve these problems, we propose a nonlinear manifold framework for the face pose and the face illumination normalization processing. Specifically, to track and recognize a face on the video that has various pose variations, we approximate a face pose density to single Gaussian density by PCA(Principle Component Analysis) using images sampled from training video sequences and then construct the GMM(Gaussian Mixture Model) for each person. To solve the illumination problem for the face tracking and recognition, we decompose the face images into the reflectance and the illuminance using the SSR(Single Scale Retinex) model. To obtain the normalized reflectance, the reflectance is rescaled by histogram equalization on the defined range. We newly approximate the illuminance by the trained manifold since the illuminance has almost variations by illumination. By combining these two features into our manifold framework, we derived the efficient face tracking and recognition results on indoor and outdoor video. To improve the video based tracking results, we update the weights of each face pose density at each frame by the tracking result at the previous frame using EM algorithm. Our experimental results show that our method is more efficient than other methods.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.1
• /
• pp.1-10
• /
• 2000

In this paper, a new digital watermarking algorithm using wavelet transform is proposed. Wavelet transform is widely used for image processing, because of its multiresolution characteristic which conforms to the principles of the human visual system(HVS). It is also very efficient for localizing images in the spatial and frequency domain. Since wavelet coefficients can be characterized by the gaussian distribution, the proposed algorithm uses a gaussian distributed random vector as the watermark in order to achieve invisibility and robustness. After the original image is transformed using DWT(Discrete Wavelet Transform), the coefficients of all subbands including LL subband are utilized to equally embed the watermark to the whole image. To select perceptually significant coefficients for each subband, we use level-adaptive thresholding. The watermark is embedded to the selected coeffocoents, using different scale factors according to the wavelet characteristics. In the process of watermark detection, the similarity between the original watermark and the extracted watermark is calculated by using vector projection method. We analyze the performance of the proposed algorithm, compared with other transform-domain watermarking methods. The experimental results tested on various images show that the proposed watermark is less visible to human eyes and more robust to image compressions, image processings, geometric transformations and various noises, than the existing methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.267-274
• /
• 2023

In this paper, a method for estimating the illuminant chromaticity of a scene for an input image is proposed. The illuminant chromaticity is estimated using the illuminant reference region. The conventional method uses a certain number of reference lighting information. By comparing the chromaticity distribution of pixels from the input image with the chromaticity set prepared in advance for the reference illuminant, the reference illuminant with the largest overlapping area is regarded as the scene illuminant for the corresponding input image. In the process of calculating the overlapping area, the weights for each reference light were applied in the form of a Gaussian distribution, but a clear standard for the variance value could not be presented. The proposed method extracts an independent reference chromaticity region from a given reference illuminant, calculates the characteristic values in the r-g chromaticity plane of the RGB color coordinate system for all pixels of the input image, and then calculates the independent chromaticity region and features from the input image. The similarity is evaluated and the illuminant with the highest similarity was estimated as the illuminant chromaticity component of the image. The performance of the proposed method was evaluated using the database image and showed an average of about 60% improvement compared to the conventional basic method and showed an improvement performance of around 53% compared to the conventional Gaussian weight of 0.1.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.1
• /
• pp.121-128
• /
• 2017

In this paper, we propose a dual-channel acoustic event detection (AED) method using nonnegative tensor factorization (NTF) and hidden Markov model (HMM) in order to improve detection accuracy of AED in multisource environments. The proposed method first detects multiple acoustic events by utilizing channel gains obtained from the NTF technique applied to dual-channel input signals. After that, an HMM-based likelihood ratio test is carried out to verify the detected events by using channel gains. The detection accuracy of the proposed method is measured by F-measures under 9 different multisource conditions. Then, it is also compared with those of conventional AED methods such as Gaussian mixture model and nonnegative matrix factorization. It is shown from the experiments that the proposed method outperforms the convectional methods under all the multisource conditions.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.3
• /
• pp.317-325
• /
• 2016

This paper describes the technique for Radar Particle filter for TBD(Track Before Detect) processing. TBD technique is applied when target is difficult to detect due to low signal-to-noise ratio caused by strong clutter environments, small RCS targets and stealth targets. Particle filter is suitable for a recursive TBD algorithm and has improved estimation accuracy than Kalman filter. In this paper, we will present a new method of calculating particle weight, when observation values(including strong clutter) are received at the same time. Estimation error performance of the particle filter algorithm is analyzed by using the virtual radar observation scenario.

• Journal of Advanced Navigation Technology
• /
• v.15 no.6
• /
• pp.1132-1137
• /
• 2011

In this paper, we propose Modified Multi CAMShift Algorithm(Modified Multi Continuously Adaptive Mean Shift Algorithm) that extracts skin color area and tracks several human body parts for real-time human tracking system. Skin color area is extracted by filtering input image in predefined RGB value range. These areas are initial search windows of hands and face for tracking. Gaussian background model prevents search window expending because it restricts skin color area. Also when occluding between these areas, we give more weights in occlusion area and move mass center of target area in color probability distribution image. As result, the proposed algorithm performs better than the original CAMShift approach in multiple object tracking and even when occluding of objects with similar colors.

• Journal of Advanced Navigation Technology
• /
• v.16 no.3
• /
• pp.545-552
• /
• 2012

In this paper, we propose Modified Multi CAMShift Algorithm based on Kalman filter and Weighted Search Windows(KWMCAMShift) that extracts skin color area and tracks several human body parts for real-time human tracking system. We propose modified CAMShift algorithm that generates background model, extracts skin area of hands and head, and tracks the body parts. Kalman filter stabilizes tracking search window of skin area due to changing skin area in consecutive frames. Each occlusion areas is avoided by using weighted window of non-search areas and main-search area. And shadows are eliminated from background model and intensity of shadow. The proposed KWMCAMShift algorithm can estimate human pose in real-time and achieves 96.82% accuracy even in the case of occlusions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.3
• /
• pp.149-154
• /
• 2014

The cross-correntropy concept can be expressed with inner products of two different probability density functions constructed by Gaussian-kernel density estimation methods. Blind algorithms based on the maximization of the cross-correntropy (MCC) and a symbol set of randomly generated N samples yield superior learning performance, but have a huge computational complexity in the update process at the aim of weight adjustment based on the MCC. In this paper, a method of reducing the computational complexity of the MCC algorithm that calculates recursively the gradient of the cross-correntropy is proposed. The proposed method has only O(N) operations per iteration while the conventional MCC algorithms that calculate its gradients by a block processing method has $O(N^2)$. In the simulation results, the proposed method shows the same learning performance while reducing its heavy calculation burden significantly.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.867-873
• /
• 2018

Recently, interests in the field of image processing have increased with the increased demand for digital imaging devices. However, digital images are damaged by the noise generated by various causes during image processing. Generally in digital imaging devices, noise such as AWGN, etc. is generated and performance and reliability are deteriorated, and various researches are in progress to remove it. Accordingly in the present paper, an algorithm to protect the high frequency components of the images and to efficiently remove AWGN is proposed. The proposed algorithm calculates the final output by adjusting estimate values applied with Gaussian mask and weight values applied according to the local mask distribution. And for performance evaluation of the proposed algorithm, simulations were performed with the existing methods, and the characteristics were compared through PSNR and the processed, enlarged images.