• Korean Journal of Remote Sensing
• /
• v.34 no.1
• /
• pp.151-166
• /
• 2018

This paper compares the four selections of performance used in the application of genetic algorithms (GAs) to automatically optimize multispectral pixel cluster for unsupervised classification from KOMPSAT-3 data, since the selection among three main types of operators including crossover and mutation is the driving force to determine the overall operations in the clustering GAs. Experimental results demonstrate that the tournament selection obtains a better performance than the other selections, especially for both the number of generation and the convergence rate. However, it is computationally more expensive than the elitism selection with the slowest convergence rate in the comparison, which has less probability of getting optimum cluster centers than the other selections. Both the ranked-based selection and the proportional roulette wheel selection show similar performance in the average Euclidean distance using the pixel clustering, even the ranked-based is computationally much more expensive than the proportional roulette. With respect to finding global optimum, the tournament selection has higher potential to reach the global optimum prior to the ranked-based selection which spends a lot of computational time in fitness smoothing. The tournament selection-based clustering GA is used to successfully classify the KOMPSAT-3 multispectral data achieving the sufficient the matic accuracy assessment (namely, the achieved Kappa coefficient value of 0.923).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.6
• /
• pp.465-470
• /
• 2013

In this paper, we introduce a modulation code design problem where best selection of two-dimensional codewords are determined to reduce two-dimensional (2D) Intersymbol Interference (ISI) and Interpage Interference (IPI), while when these codewords are randomly arranged on the storage, isolated pixel cannot be formed. Codeword selection problem and isolated pixel detection problem are formulated as integer program models and we develop a cutting plane algorithm where a valid cut is generated to remove current feasible solution to avoid isolated pixel by solving the isolated pixel detection subproblem. Using the proposed method, $4{\times}2$ 6/8 codewords with non-isolated pixel are found.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.211-216
• /
• 2006

The Constrained Linear Spectral Unmixing(CLSU) is investigated for sub-pixel image processing, Its result is the abundance map which mean fractions of endmember existing in a mixed pixel. Compared to the Linear Spectral Unmixing using least square method, CLSU uses the NNLS (Non-Negative Least Square) algorithm to guarantee that the estimated fractions are constrained. But, CLSU gets Into difficulty in image processing due to select endmember at a user's disposition. In this study, endmember selection optimization method using entropy in the error-image analysis is proposed. In experiments which is used hyperion image, it is shown that our method can select endmember number than CLSU based on unsupervised endemeber selection.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.7
• /
• pp.291-296
• /
• 2015

In this paper, we propose a new confidence measure using pixel selection for eye detection and design a hybrid eye detector. For this, we produce sub-images by applying a pixel selection method to the eye patches and construct the BDA(Biased Discriminant Analysis) feature space for measuring the confidence of the eye detection results. For a hybrid eye detector, we select HFED(Haar-like Feature based Eye Detector) and MFED(MCT Feature based Eye Detector), which are complementary to each other, as basic detectors. For a given image, each basic detector conducts eye detection and the confidence of each result is estimated in the BDA feature space by calculating the distances between the produced eye patches and the mean of positive samples in the training set. Then, the result with higher confidence is adopted as the final eye detection result and is used to the face alignment process for face recognition. The experimental results for various face databases show that the proposed method performs more accurate eye detection and consequently results in better face recognition performance compared with other methods.

• Journal of Korea Multimedia Society
• /
• v.20 no.12
• /
• pp.2009-2015
• /
• 2017

A two-dimensional lens is required to reproduce both the horizontal and vertical parallax through an autostereoscopic 3D display. Among the two-dimensional lenses, a hexagonal micro lens array (MLA) having good optical efficiency is mainly used. However, the hexagonal MLA has complex geometric features. The first feature is that the lens cells are zigzagged in the vertical direction, which should be reflected in the view number calculation for each sub-pixel. The second feature is that the four sides of a hexagonal lens cell are tilted, requiring a more careful view index assignment to the lens cell. In this paper, we propose a sub-pixel multiplexing scheme suitable for the features of the hexagonal MLA. We also propose a view-overlay algorithm based on a two-dimensional lens and compare subjective image quality with existing view-selection through autostereoscopic 3D display implementation.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.9
• /
• pp.91-98
• /
• 1997

In this paper, a new pixel decimation algorithm for the estimation of motion vector is proposed. In traditional methods, the computational cost can be reduced since only part of the pixels are used for motion vector calculation. But these methods limits the accuracy ofmotion vector because of the same reason. We derive a selection criteria of subsampled pixels that can reduce the probablity of false motion vector detection based on stochastic point of view. By using this criteria, a new pixel decimation algorithm that can reduce the prediction error with similar computational cost is presented. The simulation results applied to standard images haveshown that the proposed algorithm has less mean absolute prediction error than conventional pixel decimation algorithm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.149-154
• /
• 2021

Unlike or common images, Hyperspectral images were taken by continuous electromagnetic spectral into numerous bands according to wavelengths and are high-capacity high-resolution images. It has more information than ordinary images, so it is used to explore objects and materials. To reduce the amount of information in hyper-spectral images to be processed, band selection is utilized. Existing band selection techniques are heuristic techniques based on statistics, which take a long time and often lack generality and universality. To compensate for this, this paper utilizes quantization concept to draw representative bands through Discrete Range, we use them for band selection algorithm. Experimental results showed that the proposed technique performed much faster than conventional band selection methods, and that the performance accuracy was similar to that of the original even though the number of bands was reduced by one-seventh to one-tenth.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.141-147
• /
• 2021

In this paper, in order to improve the utilization of hyperspectral large-capacity data feature information by reducing complex computations by dimension reduction of neural network inputs in embedded systems, the band selection algorithm is applied in each subset. Among feature extraction and feature selection techniques, the feature selection aim to improve the optimal number of bands suitable for datasets, regardless of wavelength range, and the time and performance, more than others algorithms. Through this experiment, although the time required was reduced by 1/3 to 1/9 times compared to the others band selection technique, meaningful results were improved by more than 4% in terms of performance through the K-neighbor classifier. Although it is difficult to utilize real-time hyperspectral data analysis now, it has confirmed the possibility of improvement.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.1
• /
• pp.41-53
• /
• 1988

Line drawing images are the most proper information to represent the characteristics and shapes of digital images and used for recognition and communication. For the coding of line drawing images, common eight-direction chain code is used mostly. In the paper, the new mode selection chain code method is proposed which can compress the eight-direction chain code about twenty percents and be used for the reversible coding method of line drawing images. In this coding techniques, we set a reference mode for each quadrant around an abject pixel, and assign 3-directional code for these reference modes. Therefore a line pixel is coded with 3 bits. Also, a new corner finding method of line drawing images using this mode selection chain code is proposed in this paper.

• Korean Journal of Remote Sensing
• /
• v.25 no.1
• /
• pp.21-30
• /
• 2009

The purposes of this paper are to present a selection method of neighboring pixels whose local statistics are similar to the center pixel and combine the selection result with mean curvature diffusion filter to reduce noises in remote sensed imagery. The order of selection of neighboring pixels is critical, especially for finding a pixel belonging to the homogeneous region, since the statistics of the homogeneous region vary according to the selection order. An effective strategy for selecting neighboring pixels, which uses rank-order differences vector obtained by computing the intensity differences between the center pixel and neighboring pixels and arranging them in ascending order, is proposed in this paper. By using region growing method, we divide the elements of the rank-ordered differences vector into two groups, homogeneous rank-ordered differences vector and outlier rank-ordered differences vector. The mean curvature diffusion filter is combined with a line process, which chooses selectively diffusion coefficient of the neighboring pixels belonging into homogeneous rank-ordered differences vector. Experimental results using an aerial image and a TerraSAR-X satellite image showed that the proposed method reduced more efficiently noises than some conventional adaptive filters using all neighboring pixels in updating the center pixel.