• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.529-535
• /
• 2000

In this paper, we propose a new method of designing the vector quantizer which is robustness to coding results and independent of statistical characteristics of an input image in wavelet transformed image coding processes. The most critical drawback of a conventional vector quantizer is the degradation of coding capability resulted from the discordance between quantizer objective image and statistical characteristics of training sequence which is for generating representing vector. In order to resolve the problem of conventional methods, we use independent random-variables and pseudo image to which image correlation and edge component were added, as a training sequence for generating representing vector. We have done a computer simulation in order to compare coding capability between a vector quantizer designed by the proposed method and one with the conventional method using real image as same as that is objective to coding of training sequence used in codebook generation. The results show the superiority of the proposed vector quantizer method at the aspect of coding capability compared to conventional one. They also clarify the problems of conventional methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1244-1248
• /
• 2005

In this paper, we propose fuzzy c-means (FCM) to solve recognition errors in invariant range image, multi-pose face recognition. Scale, center and pose error problems were solved using geometric transformation. Range image face data was digitized into range image data by using the laser range finder that does not depend on the ambient light source. Then, the digitized range image face data is used as a model to generate multi-pose data. Each pose data size was reduced by linear reduction into the database. The reduced range image face data was transformed to the gradient face model for facial feature image extraction and also for matching using the fuzzy membership adjusted by fuzzy c-means. The proposed method was tested using facial range images from 40 people with normal facial expressions. The output of the detection and recognition system has to be accurate to about 93 percent. Simultaneously, the system must be robust enough to overcome typical image-acquisition problems such as noise, vertical rotated face and range resolution.

• Journal of Information Processing Systems
• /
• v.13 no.3
• /
• pp.464-475
• /
• 2017

In this paper, we present a new texture image retrieval method which combines color and texture features extracted from images by a set of multi-resolution multi-direction (MRMD) filters. The MRMD filter set chosen is simple and can be separable to low and high frequency information, and provides efficient multi-resolution and multi-direction analysis. The color space used is HSV color space separable to hue, saturation, and value components, which are easily analyzed as showing characteristics similar to the human visual system. This experiment is conducted by comparing precision vs. recall of retrieval and feature vector dimensions. Images for experiments include Corel DB and VisTex DB; Corel_MR DB and VisTex_MR DB, which are transformed from the aforementioned two DBs to have multi-resolution images; and Corel_MD DB and VisTex_MD DB, transformed from the two DBs to have multi-direction images. According to the experimental results, the proposed method improves upon the existing methods in aspects of precision and recall of retrieval, and also reduces feature vector dimensions.

• 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 Institute of Control, Robotics and Systems
• /
• v.15 no.10
• /
• pp.1021-1028
• /
• 2009

In this paper, a location identification for a cleaning robot using a camera shooting forward a room ceiling which kas three point landmarks is introduced. These three points are made from a laser source which is placed on an auto charger. A fisheye lens covering almost 150 degrees is utilized and the image is transformed to a camera image grabber. The widly shot image has an inevitable distortion even if wide range is coverd. This distortion is flatten using an image warping scheme. Several vision processing techniques such as an intersection extraction erosion, and curve fitting are employed. Next, three point marks are identified and their correspondence is investigated. Through this image processing and image distortion adjustment, a robot location in a wide geometrical coverage is identified.

• Journal of information and communication convergence engineering
• /
• v.7 no.2
• /
• pp.231-234
• /
• 2009

Speckle noise reduction for power Doppler ventricle coherent image for restoration and enhancement using Fast Wavelet Transform with multi-thresholding and multi-filtering on the each subbands is presented. Fast Wavelet Transform divides into low frequency component image to high frequency component image to be multi-resolved. Speckle noise is located on high frequency component in multi-resolution image mainly. A Doppler ventricle image is transformed and inversed with separated threshold function and filtering from low to high resolved images for restoration to utilize visualization for ventricle diagnosis. The experimental result shows that the proposed method has better performance in comparison with the conventional method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.16-23
• /
• 2007

Changeable biometrics has been developed as a solution to problem of enhancing security and privacy. The idea is to transform a biometric signal or feature into a new one for the purposes of enrollment and matching. In this paper, we propose a changeable biometric system that can be applied to appearance based face recognition system. In the first step when using feature extraction, ICA(Independent Component Analysis) coefficient vectors extracted from an input face image are replaced randomly using their mean and variation. The transformed vectors by replacement are scrambled randomly and a new transformed face coefficient vector (transformed template) is generated by combination of the two transformed vectors. When this transformed template is compromised, it is replaced with new random numbers and a new scrambling rule. Because e transformed template is generated by e addition of two vectors, e original ICA coefficients could not be easily recovered from the transformed coefficients.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.3
• /
• pp.353-359
• /
• 2010

In this paper, we propose the automatic image-to-image registration of high resolution satellite images using local properties of tie points to improve the registration accuracy. A spatial distance between interest points of reference and sensed images extracted by Scale Invariant Feature Transform(SIFT) is additionally used to extract tie points. Coefficients of affine transform between images are extracted by invariant descriptor based matching, and interest points of sensed image are transformed to the reference coordinate system using these coefficients. The spatial distance between interest points of sensed image which have been transformed to the reference coordinates and interest points of reference image is calculated for secondary matching. The piecewise linear function is applied to the matched tie points for automatic registration of high resolution images. The proposed method can extract spatially well-distributed tie points compared with SIFT based method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1098-1110
• /
• 2003

In this paper, we propose a homomorphic wavelet-based MMSE filter with edge detection to restore images degraded by speckle noise. In the proposed method, a noisy image is first transformed into logarithmic domain. Each pixel in the transformed image is then classified into flat and edge regions by applying DIP operator to the image restored by homomorphic directional MMSE filter. Each pixel in flat region is restored by homomorphic wavelet-based MMSE filter. Each pixel in edge region is restored by the weighted sum of the output of homomorphic wavelet-based MMSE filtering and that of homomorphic directional MMSE filtering. The restored image in spatial domain is finally obtained by applying the exponential function to the restored image in logarithmic domain. Experimental results show that the restored images by the proposed method have ISNR improvement of 3.3-4.0 ㏈ and ${\beta}$, a measurement parameter on edge preservation, improvement of 0.0103-0.0126 and superior subjective image quality over those by conventional methods.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.631-635
• /
• 2004

The rapid development of digital media and communication network urgently brings about the need of data certification technology to protect IPR (Intellectual property right). This paper proposed a new watermarking method for embedding contents owner's audio signal in order to protect color image IPR. Since this method evolves the existing static model and embeds audio signal of big data, it has the advantage of restoring signal transformed due to attacks. Three basic stages of watermarking include: 1) Encode analogue ID owner's audio signal using PCM and create new 3D audio watermark; 2) Interleave 3D audio watermark by linear bit expansion and 3) Transform Y signal of color image into wavelet and embed interleaved audio watermark in the low frequency band on the transform domain. The results demonstrated that the audio signal embedding in color image proposed in this paper enhanced robustness against lossy JPEG compression, standard image compression and image cropping and rotation which remove a part of image.