• Journal of Korea Multimedia Society
• /
• v.19 no.3
• /
• pp.626-632
• /
• 2016

In this paper, we propose the defect emphasis in TFT-LCD panel image. The defect emphasis image consist of S(Shape) map and B(Brightness) map. S map based on DoG(difference of gaussian) is made with the mura defect shape characteristic. And B map use defect intensity property that defect intensity is higher than background. The experiments were conducted to evaluate the performance of the proposed defect emphasis method. The results of experiments show the validity of the defect emphasis using the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.71.1-71
• /
• 2001

In this paper, an improved method of environment map building and a region search algorithm for mobile robot are presented. For the environment map building of mobile robot, measurement data of ultrasonic sensors and certainty grid representation is usually used. In this case, inaccuracies due to the uncertainty of ultrasonic data are included in the map. In order to solve this problem, an environment map building method using a Bayesian model was proposed previously[5]. In this study, we present an improved method of probability map building that uses infrared sensors and shift division Gaussian probability distribution with the existing Bayesian update method using ultrasonic sensors. Also, a region search algorithm for ...

• Korean Journal of Remote Sensing
• /
• v.30 no.6
• /
• pp.817-827
• /
• 2014

In the satellite remote sensing, the operational environment of the satellite sensor causes image degradation during the image acquisition. The degradation results in noise and blurring which badly affect identification and extraction of useful information in image data. This study proposes a maximum a posteriori (MAP) estimation using Point-Jacobian iteration to restore a degraded image. The proposed method assumes a Gaussian additive noise and Markov random field of spatial continuity. The proposed method employs a neighbor window of spoke type which is composed of 8 line windows at the 8 directions, and a boundary adjacency measure of Mahalanobis square distance between center and neighbor pixels. For the evaluation of the proposed method, a pixel-wise classification was used for simulation data using various patterns similar to the structure exhibited in high resolution imagery and an unsupervised segmentation for the remotely-sensed image data of 1 mspatial resolution observed over the north area of Anyang in Korean peninsula. The experimental results imply that it can improve analytical accuracy in the application of remote sensing high resolution imagery.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1183-1195
• /
• 2020

Visual saliency detection is an essential task because it is an important part of various vision-based applications. There are many techniques for saliency detection in color images. However, the number of methods for saliency detection in infrared images is limited. In this paper, we introduce a simple approach for saliency detection in infrared images based on the thresholding technique. The input image is thresholded into several Boolean maps, and an initial saliency map is calculated as a weighted sum of the created Boolean maps. The initial map is further refined by using thresholding, morphology operation, and a Gaussian filter to produce the final, high-quality saliency map. The experiment showed that the proposed method has high performance when applied to real-life data.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.697-698
• /
• 2006

In this paper, we propose a new scheme to generate multi-view images using a depth-image-based rendering (DIBR) technique. In order to improve the quality of multi-view images at newly exposed areas during mesh-based rendering, we preprocess the depth map using a Gaussian smoothing filter. Previous algorithms apply a smoothing filter to the whole depth map even if the depth map is collapsed. After extracting objects from the depth map, we apply the smoothing filter to their boundaries. Finally, we cannot only maintain the depth quality, but also generate high quality multi-view images. Experimental results show that our proposed algorithm outperforms previous works and supports an efficient depth keying technique.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.3
• /
• pp.67-71
• /
• 2016

This paper addresses a problem of defocus map recovery from single image. We describe a simple effective approach to estimate the spatial value of defocus blur at the edge location of the image. At first, we perform a re-blurring process using Gaussian function with input image, and calculate a gradient magnitude ratio with blurring amount between input image and re-blurred image. Then we get a full defocus map by propagating the blur amount at the edge location. Experimental result reveals that our method outperforms a reliable estimation of depth map, and shows that our algorithm is robust to noise, inaccurate edge location and interferences of neighboring edges within input image.

• Journal of Broadcast Engineering
• /
• v.22 no.5
• /
• pp.608-617
• /
• 2017

Methods of contrast enhancement have problem such as side effect of over-enhancement with non-gaussian histogram distribution, tradeoff enhancement efficiency against brightness preserving. In order to enhance contrast at various histogram distribution, segmentation to region with gaussian distribution and then enhance contrast each region. First, we segment an image into several regions using GMM(Gaussian Mixture Model)fitting by that k-mean clustering and EM(Expectation-Maximization) in $L^*a^*b^*$ color space. As a result region segmentation, we get the region map and probability map. Then we apply local contrast enhancement algorithm that mean shift to minimum overlapping of each region and preserve brightness histogram equalization. Experiment result show that proposed region based contrast enhancement method compare to the conventional method as AMBE(AbsoluteMean Brightness Error) and AE(Average Entropy), brightness is maintained and represented detail information.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.803-814
• /
• 2016

Recent times have seen an exponential increase in the amount of spatial data, which is in many cases associated with temporal data. Recent advances in computer technology and computation of hierarchical Bayesian models have enabled to analyze complex spatio-temporal data. Our work aims at modeling data of daily average nitrogen dioxide (NO2) levels obtained from 25 air monitoring sites in Seoul between 2003 and 2010. We considered an independent Gaussian process model and an auto-regressive model and carried out estimation within a hierarchical Bayesian framework with Markov chain Monte Carlo techniques. A Gaussian predictive process approximation has shown the better prediction performance rather than a Hierarchical auto-regressive model for the illustrative NO2 concentration levels at any unmonitored location.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.5
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.