• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.410-415
• /
• 2006

The SVDD(support vector data description) is one of the most important one-class support vector learning methods, which depends on the strategy of utilizing the balls defined on the feature space to discriminate the normal data from all other possible abnormal objects. This paper addresses on the extension of the SVDD method toward the problem of recovering the normal contents from the data contaminated with noises. The validity of the proposed de-noising method is shown via application to recovering the high-resolution images from the low-resolution images based on the high-resolution training data.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.420-438
• /
• 2004

Artificially or naturally contained texts in the natural images have significant and detailed information about the scenes. If we develop a method that can extract and recognize those texts in real-time, the method can be applied to many important applications. In this paper, we suggest a new method that extracts the text areas in the natural images using the low-level image features of color continuity. gray-level variation and color valiance and that verifies the extracted candidate regions by using the high-level text feature such as stroke. And the two level features are combined hierarchically. The color continuity is used since most of the characters in the same text lesion have the same color, and the gray-level variation is used since the text strokes are distinctive in their gray-values to the background. Also, the color variance is used since the text strokes are distinctive in their gray-values to the background, and this value is more sensitive than the gray-level variations. The text level stroke features are extracted using a multi-resolution wavelet transforms on the local image areas and the feature vectors are input to a SVM(Support Vector Machine) classifier for the verification. We have tested the proposed method using various kinds of the natural images and have confirmed that the extraction rates are very high even in complex background images.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.75-77
• /
• 2012

In this paper, We proposed that real-time pupil detection using local binarization at each region of eyes in image. In image obtained a single low-resolution web-camera, we detect a region of face using haar-like feature and then detect each region of eyes depending upon the rate of width and height of region of face respectively. In each region of eyes, we detect the pupil after local preprocessing and binarizing. This pupil detection can be variously used for HCI(Human-Computer Interface) systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.180-194
• /
• 2021

For small image registration, feature-based approaches are likely to fail as feature detectors cannot detect enough feature points from low-resolution images. The classic FFT approach's prediction accuracy is high, but the registration time can be relatively long, about several seconds to register one image pair. To achieve real-time and high-precision rigid registration for small images, we apply deep neural networks for supervised rigid transformation prediction, which directly predicts the transformation parameters. We train deep registration models with rigidly transformed CIFAR-10 images and STL-10 images, and evaluate the generalization ability of deep registration models with transformed CIFAR-10 images, STL-10 images, and randomly generated images. Experimental results show that the deep registration models we propose can achieve comparable accuracy to the classic FFT approach for small CIFAR-10 images (32×32) and our LSTM registration model takes less than 1ms to register one pair of images. For moderate size STL-10 images (96×96), FFT significantly outperforms deep registration models in terms of accuracy but is also considerably slower. Our results suggest that deep registration models have competitive advantages over conventional approaches, at least for small images.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.5
• /
• pp.197-206
• /
• 2014

Motor imagery based Brain-computer Interface(BCI), which has recently attracted attention, is the technique for decoding the user's voluntary motor intention using Electroencephalography(EEG). For classifying the motor imagery, event-related desynchronization(ERD), which is the phenomenon of EEG voltage drop at sensorimotor area in ${\mu}$-band(8-13Hz), has been generally used but this method are not free from the performance degradation of the BCI system because EEG has low spatial resolution and shows different ERD-appearing band according to users. Common spatial pattern(CSP) was proposed to solve the low spatial resolution problem but it has a disadvantage of being very sensitive to frequency-band selection. Discriminative filter bank common spatial pattern(DFBCSP) tried to solve the frequency-band selection problem by using the Fisher ratio of the averaged EEG signal power and establishing discriminative filter bank(DFB) which only includes the feature frequency-band. However, we found that DFB might not include the proper filters showing the spatial pattern of ERD. To solve this problem, we apply a band-selection process using CSP feature vectors and linear discriminant analysis to DFBCSP instead of the averaged EEG signal power. The filter selection results and the classification accuracies of the existing and the proposed methods show that the CSP feature is more effective than signal power feature.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2844-2851
• /
• 2015

How to recover from the multiple 2D images into 3D object has been widely studied in the field of computer vision. In order to improve the accuracy of the recovered 3D shape, it is more important that noise must be minimized and the number of image frames must be guaranteed. However, potential noise is implied when tracking feature points. And the number of image frames which is consisted of an observation matrix usually decrease because of tracking failure, occlusions, or low image resolution, and so on. Therefore, it is obviously essential that the number of image frames must be secured by recovering the missing feature points under noise. Thus, we propose the analytic approach which can control directly the error distance and orientation of missing feature point by the geometrical properties under noise distribution. The superiority of proposed method is demonstrated through experimental results for synthetic and real object.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.6C
• /
• pp.349-354
• /
• 2011

Passive millimeter wave imaging has the capability of detecting concealed objects under clothing. Also, passive millimeter imaging can obtain interpretable images under low visibility conditions like rain, fog, smoke, and dust. However, the image quality is often degraded due to low spatial resolution, low signal level, and low temperature resolution. This paper addresses image registration and fusion between passive millimeter images and visual images. The goal of this study is to combine and visualize two different types of information together: human subject's identity and concealed objects. The image registration process is composed of body boundary detection and an affine transform maximizing cross-correlation coefficients of two edge images. The image fusion process comprises three stages: discrete wavelet transform for image decomposition, a fusion rule for merging the coefficients, and the inverse transform for image synthesis. In the experiments, various types of metallic and non-metallic objects such as a knife, gel or liquid type beauty aids and a phone are detected by passive millimeter wave imaging. The registration and fusion process can visualize the meaningful information from two different types of sensors.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.3
• /
• pp.15-20
• /
• 2008

High-spatial resolution remote sensing satellites (IKONOS-2, QuickBird and KOMPSAT-2) have provided low-spatial resolution multispectral images and high-spatial resolution panchromatic images. Image fusion or Pan-sharpening is a very important in that it aims at using a satellite image with various applications such as visualization and feature extraction through combining images that have a different spectral and spatial resolution. Many image fusion algorithms are proposed, most methods could not preserve the spectral information of original multispectral image after image fusion. In order to solve this problem, modified induction technique which reduce the spectral distortion of fused image is developed. The spectral distortion is adjusted by the comparison between the spatially degraded pan-sharpened image and original multispectral image and our algorithm is evaluated by QuickBird satellite imagery. In the experiment, pan-sharpened image by various methods can reduce spectral distortion when our algorithm is applied to the fused images.

• Smart Structures and Systems
• /
• v.1 no.1
• /
• pp.63-82
• /
• 2005

This paper introduces a technology for robust and low maintenance cost sensor network capable to detect accelerations below a micro-g in a wide frequency bandwidth (above 1,000 Hz). Sensor networks with such performance are critical for navigation, seismology, acoustic sensing, and for the health monitoring of civil structures. The approach is based on the fabrication of an array of high sensitivity accelerometers, each utilizing Fabry-Perot cavity with wavelength-dependent reflectivity to allow embedded optical detection and serialization. The unique feature of the approach is that no local power source is required for each individual sensor. Instead one global light source is used, providing an input optical signal which propagates through an optical fiber network from sensor-to-sensor. The information from each sensor is embedded onto the transmitted light as an intrinsic wavelength division multiplexed signal. This optical "rainbow" of data is then assessed providing real-time sensing information from each sensor node in the network. This paper introduces the Fabry-Perot based accelerometer and examines its critical features, including the effects of imperfections and resolution estimates. It then presents serialization techniques for the creation of systems of arrayed sensors and examines the effects of serialization on sensor response. Finally, a fabrication process is proposed to create test structures for the critical components of the device, which are dynamically characterized.