• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.106-109
• /
• 2009

Recently, image matching becomes important in Computer Aided Diagnosis (CAD) due to the huge amount of medical images. Specially, texture feature is useful in medical image matching. However, texture features such as co-occurrence matrices can't describe well the spatial distribution of gray levels of the neighborhood pixels. In this paper we propose a frequency domain-based texture feature extractor that describes the local spatial distribution for medical image retrieval. This method is based on 2D Local Discrete Fourier transform of local images. The features are extracted from local Fourier histograms that generated by four Fourier images. Experimental results using 40 classes Brodatz textures and 1 class of Emphysema CT images show that the average accuracy of retrieval is about 93%.

• Economic and Environmental Geology
• /
• v.28 no.5
• /
• pp.527-533
• /
• 1995

A disadvantage of Fourier analysis is that frequency information can only be extracted for the complete duration of a signal f(t). Since the Fourier transform integral extends over all time, from $-{\infty}$ to $+{\infty}$), the information it provides arises from an average over the whole length of the signal. If there is a local oscillation representing a particular feature, this will contribute to the calculated Fourier transform $F({\omega})$, but its location on the time axis will be lost There is no way of knowing whether the value of $F({\omega})$ at a particular ${\omega}$ derives from frequencies present throughout the life of f(t) or during just one or a few selected periods. This disadvantage is overcome in wavelet analysis which provides an alternative way of breaking a signal down into its constituent parts. The main advantage of the wavelet transform over the conventional Fourier transform is that it can not only provide the combined temporal and spectral features of the signal, but can also localize the target information in the time-frequency domain simultaneously. The wavelet transform distinguishes itself from Short Time Fourier Transform for time-frequency analysis in that it has a zoom-in and zoom-out capability.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.3 s.96
• /
• pp.266-271
• /
• 2005

Although time-frequency analysis is useful for dispersive wave analysis, conventional methods such as the short-time Fourier transform do not take the dispersion phenomenon into consideration in the tiling of the time-frequency domain. The objective of this paper is to develop an adaptive time-frequency analysis method whose time-frequency tiling is determined with the consideration of signal dispersion characteristics. To achieve the adaptive time-frequency tiling, each of time-frequency atoms is rotated in the time-frequency plane depending on the local wave dispersion. To carry out this adaptive time-frequency transform, dispersion characteristics hidden in a signal are first estimated by an iterative scheme. To examine the effectiveness of the present method, the flexural wave signals measured in a plate were analyzed.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.606-610
• /
• 2004

Although time-frequency analysis is useful for dispersive wave analysis, conventional methods such as the short-time Fourier transform do not take the dispersion phenomenon into consideration in the tiling of the time-frequency domain. The objective of this paper is to develop an adaptive time-frequency analysis method whose time-frequency tiling is determined with the consideration of signal dispersion characteristics. To achieve the adaptive time-frequency tiling, each of time-frequency atoms is rotated in the time-frequency plane depending on the local wave dispersion. To carry out this adaptive time-frequency transform, dispersion characteristics hidden in a signal are first estimated by an iterative scheme. To examine the effectiveness of the proposed method, the flexural wave signals measured in a plate were analyzed.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.363.1-363
• /
• 2002

This paper presents that the Wavelet Transform can be used to detect the various local defects in a gearbox. Two types of defects which are broken tooth and localized wear, are experimented and the signals are collected by accerometer and acoustic sensors and analyized. Because of the complecity of the signals acquired form sensors, it is needed to identify the interesting signal. (omitted)

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.617-622
• /
• 2002

This paper presents that the Wavelet Transform can be used to detect the various local defects in a gearbos. Two types of defects which are broken tooth and localized wear, are experimented and the signals are collected by accerometer and analyzed. Because of the complecity of the signals acquired from sensor, it is needed to identify the interesting signal. The natural frequencies of shafts and the gear mesh frequency(GMF) is calculated theretically. DWT, CWT and the aplication are used to extract a gear-localized defect feature from the vibration signal of the gearbox with the defective gear. The results shows the transform is more effective to detect the failures than the Fourier Transform.

• Journal of Information Processing Systems
• /
• v.12 no.4
• /
• pp.555-576
• /
• 2016

In the conventional clustering algorithms, an object could be assigned to only one group. However, this is sometimes not the case in reality, there are cases where the data do not belong to one group. As against, the fuzzy clustering takes into consideration the degree of fuzzy membership of each pixel relative to different classes. In order to overcome some shortcoming with traditional clustering methods, such as slow convergence and their sensitivity to initialization values, we have used the Harmony Search algorithm. It is based on the population metaheuristic algorithm, imitating the musical improvisation process. The major thrust of this algorithm lies in its ability to integrate the key components of population-based methods and local search-based methods in a simple optimization model. We propose in this paper a new unsupervised clustering method called the Fuzzy Harmony Search-Fourier Transform (FHS-FT). It is based on hybridization fuzzy clustering and the harmony search algorithm to increase its exploitation process and to further improve the generated solution, while the Fourier transform to increase the size of the image's data. The results show that the proposed method is able to provide viable solutions as compared to previous work.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.5
• /
• pp.298-311
• /
• 2003

Iterative Fourier transform algorithm, (IFTA) is tile iterative numerical algorithm for the design of the diffractive optical elements (DOE), by which the phase distribution of a DOE converges on a local optimal solution. The convergence of IFTA depends on several factors 3s initial phase distribution, the structure of the degree of freedom on the observation plane, and the values of internal parameters. In this paper, we analyze tile dependence of the convergence of IFTA on an internal parameter of IFTA, the relaxation parameter, and propose a new hybrid scheme of genetic algorithm and IFTA to obtain more accurate solution.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.10-16
• /
• 2007

In this paper, we propose a technique for retrieving images using spatial color correlation and texture characteristics based on local fourier transform. In order to retrieve images, two new descriptors are proposed. One is a color descriptor which represents spatial color correlation. The other is a descriptor combining the proposed color descriptor with texture descriptor. Since most of existing color descriptors including color correlogram which represent spatial color correlation considered just color distribution between neighborhood pixels, the structural information of neighborhood pixels is not considered. Therefore, a novel color descriptor which simultaneously represents spatial color distribution and structural information is proposed. The proposed color descriptor represents color distribution of Min-Max color pairs calculating color distance between center pixel and neighborhood pixels in a block with 3x3 size. Also, the structural information which indicates directional difference between minimum color and maximum color is simultaneously considered. Then new color descriptor(min-max color correlation descriptor, MMCCD) containing mean and variance values of each directional difference is generated. While the proposed color descriptor includes by far smaller feature vector over color correlogram, the proposed color descriptor improves 2.5 % ${\sim}$ 13.21% precision rate, compared with color correlogram. In addition, we propose a another descriptor which combines the proposed color descriptor and texture characteristics based on local fourier transform. The combined method reduces size of feature vector as well as shows improved results over existing methods.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.225-232
• /
• 2017

Understanding actions in videos is an important task. It helps in finding the anomalies present in videos such as fights. Detection of fights becomes more crucial when it comes to sports. This paper focuses on finding fight scenes in Hockey sport videos using blur & radon transform and convolutional neural networks (CNNs). First, the local motion within the video frames has been extracted using blur information. Next, fast fourier and radon transform have been applied on the local motion. The video frames with fight scene have been identified using transfer learning with the help of pre-trained deep learning model VGG-Net. Finally, a comparison of the methodology has been performed using feed forward neural networks. Accuracies of 56.00% and 75.00% have been achieved using feed forward neural network and VGG16-Net, respectively.