• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.5
• /
• pp.617-623
• /
• 2008

This paper presents a human motion recognition method using both centroid shift and local basis images. The centroid shift based on 1st moment balance technique is applied to get the robust motion images against position or size changes, the extraction of local basis images based on independent component analysis(ICA) is also applied to find a set of statistically independent motion features, which is included in each motions. Especially, ICA of fixed-point(FP) algorithm based on Newton method is used for being quick to extract a local basis images of motions. The proposed method has been applied to the problem for recognizing the 160(1 person * 10 animals * 16 motions) sign language motion images of 240*215 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed method has a superior recognition performances(speed, rate) than the method using local eigen images and the method using local basis images without centroid shift respectively.

• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.715-720
• /
• 2005

This paper presents a hybrid recognition method of first moment of face image and principal component analysis(PCA). First moment is applied to reduce the dimension by shifting to the centroid of image, which is to exclude the needless backgrounds in the face recognitions. PCA is implemented by single layer neural network which has a teaming rule of Foldiak algorithm. It has been used as an alternative method for numerical PCA. PCA is to derive an orthonormal basis which directly leads to dimensionality reduction and possibly to feature extraction of face image. The proposed method has been applied to the problems for recognizing the 48 face images(12 Persons $\ast$ 4 scenes) of 64$\ast$64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed method has a superior recognition performances(speed, rate). The negative angle has been relatively achieved more an accurate similarity than city-block or Euclidean.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.429-436
• /
• 2004

This paper proposes an independent component analyses(ICAs) of the fixed-point (FP) algorithm based on Newton and secant method by adding the kurtosis, respectively. The kurtosis is applied to cluster the analyzed components, and the FP algorithm is applied to get the fast analysis and superior performance irrelevant to learning parameters. The proposed ICAs have been applied to the problems for separating the 6-mixed signals of 500 samples and 10-mixed images of $512\times512$ pixels, respectively. The experimental results show that the proposed ICAs have always a fixed analysis sequence. The results can be solved the limit of conventional ICA without a kurtosis which has a variable sequence depending on the running of algorithm. Especially. the proposed ICA can be used for classifying and identifying the signals or the images. The results also show that the secant method has better the separation speed and performance than Newton method. And, the secant method gives relatively larger improvement degree as the problem size increases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.58-64
• /
• 2016

In this paper presents Robust k-means clustering-based high-speed bar code decoding method to blur and lighting. for fast operation speed and robust decoding to blur, proposed method uses adaptive local threshold binarization methods that calculate threshold value by dividing blur region and a non-blurred region. Also, in order to prevent decoding fail from the noise, decoder based on k-means clustering algorithm is implemented using area data summed pixel width line of the same number of element. Results of simulation using samples taken at various worst case environment, the average success rate of proposed method is 98.47%. it showed the highest decoding success rate among the three comparison programs.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1294-1302
• /
• 2015

A lot of image quality assessment metrics that can precisely reflect the human visual system (HVS) have previously been researched. The Structural SIMilarity (SSIM) index is a remarkable HVS-aware metric that utilizes structural information, since the HVS is sensitive to the overall structure of an image. However, SSIM fails to deal with color difference in terms of the HVS. In order to solve this problem, the Structural and Hue SIMilarity (SHSIM) index has been selected with the Hue, Saturation, Intensity (HSI) model as a color space, but it cannot reflect the HVS-aware color difference between two color images. In this paper, we propose a new image quality assessment method for a color image by using a CIE Lab color space. In addition, by using a support vector machine (SVM) classifier, we also propose an optimization system for applying optimal metric according to the types of distortion. To evaluate the proposed index, a LIVE database, which is the most well-known in the area of image quality assessment, is employed and four criteria are used. Experimental results show that the proposed index is more consistent with the other methods.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.355-361
• /
• 2014

The aim of the present study was to evaluate a relative emission of image plate (IP) in computed radiography (CR) system by using relative sensitivity in film/screen methods. The characteristic curve was obtained by using the uniform aluminum 11-step wedge penetrometer. X-ray exposure factors on radiographic digital image were 50 kVp, 10 mAs. We adjusted zero of all parameter of algorithms (MUSICA) so proximate to raw data and applied to 200 of exposure class. Modeling on relative emission of IP are used IP without fading time and IP after 4 hours, 8 hours, 12 hours, 24 hours in the respective storage after X-ray exposure. The results of this study showed that the sensitivity point density at the measuring of relative sensitivity in CR was suited pixel values of the 2000 easy to relatively measure the characteristic curve and when relative sensitivity is decreased, the amount of light emitted from the image signal for generating was also decreased. In conclusion, the proposed method of measurement of relative sensitivity can be utilized to evaluate the quantity of relative emission of IP in CR system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.336-341
• /
• 2004

This paper proposes an independent component analysis(ICA) of the fixed-point (FP) algorithm based on secant method and the kurtosis. The FP algorithm based on secant method is applied to improve the analysis speed and performance by simplifying the calculation process of the complex derivative in Newton method, the kurtosis is applied to cluster the components. The proposed ICA has been applied to the problems for separating the 6-mixed signals of 500 samples and 8-mixed images of $512{\times}512$ pixels, respectively. The experimental results show that the proposed ICA has always a fixed analysis sequence. The result can be solved the limit of conventional ICA based on secant method which has a variable sequence depending on the running of algorithm. Especially, the proposed ICA can be used for classifying and identifying the signals or the images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.337-343
• /
• 2012

The techniques of implementing 3D movie have been developed by stereoscopic representation methods of the scene based on human visual experience. Recently, though various novel approaches for stereo movies are proposed to produce realistic 3D image, more study have to be done for compensating keystone distortion which is generated by moving virtual camera. In this paper we propose a novel production technique which minimizes keystone distortion based on analyzing pixel distance, and is easily implemented on popular graphics environment. First, in graphics environment we categorize each objects as individual layers, and extract image data to produce 3D image. The comparison between each animation sequences from proposed and conventional production methods shows that our production technique well compensate the distortion.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.7-14
• /
• 2006

This paper presents an efficient face recognition method using both first moment of image and basis images. First moment which is a method for finding centroid of image, is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. Basis images which are the face features, are respectively extracted by principal component analysis(PCA) and fixed-point independent component analysis(FP-ICA). This is to improve the recognition performance by excluding the redundancy considering to second- and higher-order statistics of face image. The proposed methods has been applied to the problem for recognizing the 48 face images(12 persons*4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed methods has a superior recognition performances(speed, rate) than conventional PCA and FP-ICA without preprocessing, the proposed FP-ICA has also better performance than the proposed PCA. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.