• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.134-137
• /
• 2005

Unsupervised spectral angle classification (USAC) is the algorithm that can extract ground object information with the minimum 'Spectral Angle' operation on behalf of 'Spectral Euclidian Distance' in the clustering process. In this study, our algorithm uses the unit vector instead of the spectral distance to compute the mean of cluster in the unsupervised classification. The proposed algorithm (MUSAC) is applied to the Hyperion and ETM+ data and the results are compared with K-Meails and former USAC algorithm (FUSAC). USAC is capable of clearly classifying water and dark forest area and produces more accurate results than K-Means. Atmospheric correction for more accurate results was adapted on the Hyperion data (Hyperion-FLAASH) but the results did not have any effect on the accuracy. Thus we anticipate that the 'Spectral Angle' can be one of the most accurate classifiers of not only multispectral images but also hyperspectral images. Furthermore the cluster unit vector can be an efficient technique for determination of each cluster mean in the USAC.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.547-553
• /
• 2008

We propose a two-stage document layout segmentation method. At the first stage, as top-down segmentation, morphological distance map algorithm extracts a collection of rectangular regions from a given input image. This preliminary result from the first stage is employed as input parameters for the process of next stage. At the second stage, a machine-learning algorithm is adopted RBF network, one of neural networks based on statistical model, is selected. In order for constructing the hidden layer of RBF network, a data clustering technique bared on the self-organizing property of Kohonen network is utilized. We present a result showing that the supervised neural network, trained by 300 number of sample data, improves the preliminary results of the first stage.

• Journal of Biomedical Engineering Research
• /
• v.12 no.2
• /
• pp.99-106
• /
• 1991

For the automatic detection of pulmonary blood vessels, a new algorithm is proposed using the fact that human recognizes a pattern orderly according to their size. This method simulates the human recognition process by the pyramid images. For the detection of vessels using multilevel image, large and wtde ones are detected from the most compressed level, followed by the detection of small and narrow ones from the less compressed images with FCM(fuzzy c means) clustering algorithm which classifies similar data into a group. As the proposed algorithm detects blood vessels orderly according to their size, there is no need to consider the variation of parameters and the branch points which should be considered in other detection algirithms. In the detection of patterns whose size changes successively like pulmonary blood vessels, this proposed algorithm can be properly applied

• Journal of Korea Multimedia Society
• /
• v.23 no.11
• /
• pp.1349-1360
• /
• 2020

In recent years, Convolutional Neural Networks (CNNs) have been successfully implemented in different tasks of computer vision. Since CNN models are the representatives of supervised learning algorithms, they demand large amount of data in order to train the classifiers. Thus, obtaining data with correct labels is imperative to attain the state-of-the-art performance of the CNN models. However, labelling datasets is quite tedious and expensive process, therefore real-life datasets often exhibit incorrect labels. Although the issue of poorly labelled datasets has been studied before, we have noticed that the methods are very complex and hard to reproduce. Therefore, in this research work, we propose Deep CleanNet - a considerably simple system that achieves competitive results when compared to the existing methods. We use K-means clustering algorithm for selecting data with correct labels and train the new dataset using a deep CNN model. The technique achieves competitive results in both training and validation stages. We conducted experiments using MNIST database of handwritten digits with 50% corrupted labels and achieved up to 10 and 20% increase in training and validation sets accuracy scores, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7302-7308
• /
• 2014

Detecting target objects robustly in natural environments is a difficult problem in the computer vision and image processing areas. This paper suggests a method of robustly detecting target objects in the environments where reflection exists. The suggested algorithm first captures scenes with a stereo camera and extracts the line and corner features representing the target objects. This method then eliminates the reflected features among the extracted ones using a homographic transform. Subsequently, the method robustly detects the target objects by clustering only real features. The experimental results showed that the suggested algorithm effectively detects the target objects in reflection environments rather than existing algorithms.

• International journal of advanced smart convergence
• /
• v.9 no.3
• /
• pp.232-238
• /
• 2020

In this paper, we study on aerial objects detection and position estimation algorithm for the safety of UAV that flight in BVLOS. We use the vision sensor and LiDAR to detect objects. We use YOLOv2 architecture based on CNN to detect objects on a 2D image. Additionally we use a clustering method to detect objects on point cloud data acquired from LiDAR. When a single sensor used, detection rate can be degraded in a specific situation depending on the characteristics of sensor. If the result of the detection algorithm using a single sensor is absent or false, we need to complement the detection accuracy. In order to complement the accuracy of detection algorithm based on a single sensor, we use the Kalman filter. And we fused the results of a single sensor to improve detection accuracy. We estimate the 3D position of the object using the pixel position of the object and distance measured to LiDAR. We verified the performance of proposed fusion algorithm by performing the simulation using the Gazebo simulator.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.6
• /
• pp.711-720
• /
• 2015

Recently many studies of Radar systems mounted on ground vehicles for autonomous driving, SLAM (Simultaneous localization and mapping) and collision avoidance have been reported. Since several pixels per an object may be generated in a close-range radar application, a width of an object can be estimated automatically by various signal processing techniques. In this paper, we tried to attempt to develop an algorithm to estimate obstacle width using Radar images. The proposed method consists of 5 steps - 1) background clutter reduction, 2) local peak pixel detection, 3) region growing, 4) contour extraction and 5)width calculation. For the performance validation of our method, we performed the test width estimation using a real data of two cars acquired by commercial radar system - I200 manufactured by Navtech. As a result, we verified that the proposed method can estimate the widths of targets.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.54.3-55
• /
• 2017

The Deep Lens Survey (DLS), a precursor to the Large Synoptic Survey Telescope (LSST), is a 20 deg2 survey carried out with NOAO's Blanco and Mayalltelescopes. DLS is unique in its depth reaching down to ~27th mags in BVRz bands. This enables a broad redshift baseline and is optimal for investigating cosmological evolution of the large scale structure. Galaxy-galaxylensing is a powerful tool to estimate averaged matter distribution around lensgalaxies by measuring shape distortions of background galaxies. The signal from galaxy-galaxy lensing is sensitive not only to galaxy halo properties, but also to cosmological environment at large scales. In this study, we measure galaxy-galaxy lensing and galaxy clustering, which together put strong constraints on the cosmological parameters. We obtain significant galaxy-galaxy lensing signals out to ~20 Mpc while tightly controlling systematics. The B-mode signals are consistent with zero. Our lens-source flip test indicates that minimal systematic errors are present in DLS photometric redshifts. Shear calibration is performed using high-fidelity galaxy image simulations. We demonstrate that the overall shape of the galaxy-galaxy lensing signal is well described by the halo model comprised of central and non-central halo contributions. Finally, we present our preliminary constraints on the matter density and the normalization parameters.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.107-116
• /
• 2004

The advent of microarray technologies gives an opportunity to moni tor the expression of ten thousands of genes, simultaneously. Such microarray data can be deteriorated by experimental errors and image artifacts, which generate non-negligible outliers that are estimated by 15% of typical microarray data. Thus, it is an important issue to detect and correct the se faulty probes prior to high-level data analysis such as classification or clustering. In this paper, we propose a systematic procedure for the detection of faulty probes and its proper correction in Genechip array based on multivariate statistical approaches. Principal component analysis (PCA), one of the most widely used multivariate statistical approaches, has been applied to construct a statistical correlation model with 20 pairs of probes for each gene. And, the faulty probes are identified by inspecting the squared prediction error (SPE) of each probe from the PCA model. Then, the outlying probes are reconstructed by the iterative optimization approach minimizing SPE. We used the public data presented from the gene chip project of human fibroblast cell. Through the application study, the proposed approach showed good performance for probe correction without removing faulty probes, which may be desirable in the viewpoint of the maximum use of data information.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.1060-1069
• /
• 2016

In this paper, we introduce the fingerprint recognition system based on Radial Basis Function Neural Network(RBFNN). Fingerprints are classified as four types(Whole, Arch, Right roof, Left roof). The preprocessing methods such as fast fourier transform, normalization, calculation of ridge's direction, filtering with gabor filter, binarization and rotation algorithm, are used in order to extract the features on fingerprint images and then those features are considered as the inputs of the network. RBFNN uses Fuzzy C-Means(FCM) clustering in the hidden layer and polynomial functions such as linear, quadratic, and modified quadratic are defined as connection weights of the network. Particle Swarm Optimization (PSO) algorithm optimizes a number of essential parameters needed to improve the accuracy of RBFNN. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. The performance evaluation of the proposed fingerprint recognition system is illustrated with the use of fingerprint data sets that are collected through Anguli program.