The Experts below are selected from a list of 9950790 Experts worldwide ranked by ideXlab platform
Samuel W K Chan - One of the best experts on this subject based on the ideXlab platform.
-
multi attributes image analysis for the classification of web documents using unsupervised technique
Intelligent Data Engineering and Automated Learning, 2005Co-Authors: Samuel W K ChanAbstract:The aim of this research is to develop a system based on multi-attributes image analysis and a neural network self-organization feature map (SOFM) that will facilitate the automated classification of images or icons in Web documents. Four different image attribute sets are extracted. The system integrates different image attributes without demanding any particular primitive to be dominant. The system is implemented and the results generated show meaningful clusters. The performance of the system is compared with the Hierarchical Agglomerative Clustering (HAC) algorithm. Evaluation shows that similar images will fall onto the same region in our approach, in such a way that it is possible to retrieve images under family relationships.
-
IDEAL - Multi-attributes image analysis for the classification of web documents using unsupervised technique
Lecture Notes in Computer Science, 2005Co-Authors: Samuel W K ChanAbstract:The aim of this research is to develop a system based on multi-attributes image analysis and a neural network self-organization feature map (SOFM) that will facilitate the automated classification of images or icons in Web documents. Four different image attribute sets are extracted. The system integrates different image attributes without demanding any particular primitive to be dominant. The system is implemented and the results generated show meaningful clusters. The performance of the system is compared with the Hierarchical Agglomerative Clustering (HAC) algorithm. Evaluation shows that similar images will fall onto the same region in our approach, in such a way that it is possible to retrieve images under family relationships.
Thomas S. Huang - One of the best experts on this subject based on the ideXlab platform.
-
towards learning a self inverse network for bidirectional image to image translation
arXiv: Computer Vision and Pattern Recognition, 2019Co-Authors: Zengming Shen, Yifan Chen, Bogdan Georgescu, Shaohua Kevin Zhou, Thomas S. HuangAbstract:The one-to-one mapping is necessary for many bidirectional image-to-image translation applications, such as MRI image synthesis as MRI images are unique to the patient. State-of-the-art approaches for image synthesis from domain X to domain Y learn a convolutional neural network that meticulously maps between the domains. A different network is typically implemented to map along the opposite direction, from Y to X. In this paper, we explore the possibility of only wielding one network for bi-directional image synthesis. In other words, such an autonomous learning network implements a self-inverse function. A self-inverse network shares several distinct advantages: only one network instead of two, better generalization and more restricted parameter space. Most importantly, a self-inverse function guarantees a one-to-one mapping, a property that cannot be guaranteed by earlier approaches that are not self-inverse. The experiments on three datasets show that, compared with the baseline approaches that use two separate models for the image synthesis along two directions, our self-inverse network achieves better synthesis results in terms of standard metrics. Finally, our sensitivity analysis confirms the feasibility of learning a self-inverse function for the bidirectional image translation.
-
non local kernel regression for image and video restoration
European Conference on Computer Vision, 2010Co-Authors: Haichao Zhang, Jianchao Yang, Yanning Zhang, Thomas S. HuangAbstract:This paper presents a non-local kernel regression (NL-KR) method for image and video restoration tasks, which exploits both the non-local self-similarity and local structural regularity in natural images. The non-local self-similarity is based on the observation that image patches tend to repeat themselves in natural images and videos; and the local structural regularity reveals that image patches have regular structures where accurate estimation of pixel values via regression is possible. Explicitly unifying both properties, the proposed non-local kernel regression framework is robust and applicable to various image and video restoration tasks. In this work, we are specifically interested in applying the NL-KR model to image and video super-resolution (SR) reconstruction. Extensive experimental results on both single images and realistic video sequences demonstrate the superiority of the proposed framework for SR tasks over previous works both qualitatively and quantitatively.
Juan Yu - One of the best experts on this subject based on the ideXlab platform.
-
Image fusion of fault detection in power system based on deep learning
Cluster Computing, 2019Co-Authors: Yu Li, Renzhuo Wan, Meiyu Qian, Pengfeng Liu, Qian Cai, Fengyuan Yu, Xiaoying Li, Kun Yuan, Junwen Guo, Juan YuAbstract:Aiming at the three main problems of power system—leakage, high temperature and physical damage, a new image fusion of fault detection method in power system based on deep learning is proposed in this paper. The core of deep learning is achieved by capsule network model. The model is trained and tested by self-built image dataset of power system. There are three types of dataset: visible images,infrared images and ultraviolet images. After being preprocessed and feature-extracted, the visible image is used as the fusion image background, the infrared image provides the thermal information of power equipment, and the ultraviolet image provides the electric field information on the exterior of power equipment. The collected images are decomposed into corresponding high frequency component image and low frequency component image respectively, which reconstructed into fused images by the capsule network model. With the registration of the three types of images, the faults in the power system can be detected and displayed accurately in the fused image.
Jong-kyun Hong - One of the best experts on this subject based on the ideXlab platform.
-
Extraneous self-imaging phenomenon with weak-guiding condition
Optics letters, 2007Co-Authors: Jong-kyun Hong, Sang-sun Lee, Seung-dae LeeAbstract:We discuss a self-imaging phenomenon in a multimode interference (MMI) coupler. From experiment, different Self-Images, which are undefined in MMI theory, are observed. These undefined Self-Images are named "extraneous Self-Images" (Ex_SIs) for convenience. To estimate the applicability of the Ex_SIs, the characteristics of both the single Self-Image (0 dB Self-Image, 0 dB SI), which is defined in MMI theory, and the Ex_SI are compared and analyzed through simulation and experiment. The results show that the Ex_SI has an imaging period that is the same as the 0 dB SI and that the excess loss and the extinction ratio of the Ex_SI improve more than that of the 0 dB SI as the imaging period increases.
-
A Pseudo-Self-Imaging Phenomenon in Multimode Waveguides
Journal of the Optical Society of Korea, 2006Co-Authors: Jong-kyun Hong, Sang-sun Lee, Seok Ho SongAbstract:This study introduces an undefined self-imaging phenomenon, called here the pseudo-self-imaging phenomenon. The relative phases of the guided modes were used to discover how the pseudo-Self-Images are formed. The pseudo-Self-Image was found and measured experimentally. The experimental results showed that both the pseudo-Self-Image and the 0-dB Self-Image have similar intensity values and have opposite positions in the lateral direction.
-
Pseudo-self-imaging phenomenon in multimode waveguide and its application
Proceedings of SPIE, 2006Co-Authors: Jong-kyun Hong, Sang-sun LeeAbstract:The Self-Image profiles in a multimode waveguide can be estimated from the phase relations of the guided-modes. However, in MMI theory, the propagation constants of each guided-mode are defined as a perfectly confined condition. Because of the effect of the Goos-Haenchen shift, there are large phase differences for each guided-mode between the predictions of MMI theory and the actual phenomena. Because the relative phases of the guided-modes are not the same as the theoretical ones in a multimode waveguide, it is possible that an undefined Self-Image can be produced. In this paper, such a phenomenon is called the 'pseudo-self-imaging phenomenon'. This phenomenon can be observed in both the simulation and the experimental results. The excess loss has been measured, and the results are the same as -0.5dB for both the 1st 0-dB Self-Image and the 1st pseudo-Self-Image. These results may have been occurred by the phase mismatch of the guided-modes. The extinction ratios are also measured, and the results are 15.5dB for the 0-dB self image and 16.2dB for the pseudo-Self-Image. From the result, it is shown that the pseudo-Self-Image is formed after the 0-dB Self-Image and the pseudo-Self-Images' intensity can be higher then the 0-dB Self-Images.
-
Experimental study of the self-imaging phenomenon with weak-guiding condition
Microwave and Optical Technology Letters, 2006Co-Authors: Jong-kyun Hong, Sang-sun LeeAbstract:This paper investigates a self-imaging phenomenon in a multimode interference (MMI) coupler. In the experiment, different Self-Images which are undefined in MMI theory are observed. This undefined Self-Image is named the “pseudo-Self-Image ” (PSI) as a matter of convenience. The characteristics of both the single Self-Image (0-dB Self-Image: 0-dB SI), which is defined in MMI theory, and the PSI are compared and analyzed through simulation and experimentation to estimate the applicability of the PSI. Results show that the PSI has an imaging period the same as the 0-dB SI, and the excess loss and the extinction ratio of the PSI improve more than those of the 0-dB SI as the imaging period increases. © 2006 Wiley Periodicals, Inc. Microwave Opt Technol Lett 48:2354–2357, 2006;Published online in Wiley InterScience (www.interscience.wiley.com).DOI 10.1002/mop.21942
Sang-sun Lee - One of the best experts on this subject based on the ideXlab platform.
-
Extraneous self-imaging phenomenon with weak-guiding condition
Optics letters, 2007Co-Authors: Jong-kyun Hong, Sang-sun Lee, Seung-dae LeeAbstract:We discuss a self-imaging phenomenon in a multimode interference (MMI) coupler. From experiment, different Self-Images, which are undefined in MMI theory, are observed. These undefined Self-Images are named "extraneous Self-Images" (Ex_SIs) for convenience. To estimate the applicability of the Ex_SIs, the characteristics of both the single Self-Image (0 dB Self-Image, 0 dB SI), which is defined in MMI theory, and the Ex_SI are compared and analyzed through simulation and experiment. The results show that the Ex_SI has an imaging period that is the same as the 0 dB SI and that the excess loss and the extinction ratio of the Ex_SI improve more than that of the 0 dB SI as the imaging period increases.
-
A Pseudo-Self-Imaging Phenomenon in Multimode Waveguides
Journal of the Optical Society of Korea, 2006Co-Authors: Jong-kyun Hong, Sang-sun Lee, Seok Ho SongAbstract:This study introduces an undefined self-imaging phenomenon, called here the pseudo-self-imaging phenomenon. The relative phases of the guided modes were used to discover how the pseudo-Self-Images are formed. The pseudo-Self-Image was found and measured experimentally. The experimental results showed that both the pseudo-Self-Image and the 0-dB Self-Image have similar intensity values and have opposite positions in the lateral direction.
-
Pseudo-self-imaging phenomenon in multimode waveguide and its application
Proceedings of SPIE, 2006Co-Authors: Jong-kyun Hong, Sang-sun LeeAbstract:The Self-Image profiles in a multimode waveguide can be estimated from the phase relations of the guided-modes. However, in MMI theory, the propagation constants of each guided-mode are defined as a perfectly confined condition. Because of the effect of the Goos-Haenchen shift, there are large phase differences for each guided-mode between the predictions of MMI theory and the actual phenomena. Because the relative phases of the guided-modes are not the same as the theoretical ones in a multimode waveguide, it is possible that an undefined Self-Image can be produced. In this paper, such a phenomenon is called the 'pseudo-self-imaging phenomenon'. This phenomenon can be observed in both the simulation and the experimental results. The excess loss has been measured, and the results are the same as -0.5dB for both the 1st 0-dB Self-Image and the 1st pseudo-Self-Image. These results may have been occurred by the phase mismatch of the guided-modes. The extinction ratios are also measured, and the results are 15.5dB for the 0-dB self image and 16.2dB for the pseudo-Self-Image. From the result, it is shown that the pseudo-Self-Image is formed after the 0-dB Self-Image and the pseudo-Self-Images' intensity can be higher then the 0-dB Self-Images.
-
Experimental study of the self-imaging phenomenon with weak-guiding condition
Microwave and Optical Technology Letters, 2006Co-Authors: Jong-kyun Hong, Sang-sun LeeAbstract:This paper investigates a self-imaging phenomenon in a multimode interference (MMI) coupler. In the experiment, different Self-Images which are undefined in MMI theory are observed. This undefined Self-Image is named the “pseudo-Self-Image ” (PSI) as a matter of convenience. The characteristics of both the single Self-Image (0-dB Self-Image: 0-dB SI), which is defined in MMI theory, and the PSI are compared and analyzed through simulation and experimentation to estimate the applicability of the PSI. Results show that the PSI has an imaging period the same as the 0-dB SI, and the excess loss and the extinction ratio of the PSI improve more than those of the 0-dB SI as the imaging period increases. © 2006 Wiley Periodicals, Inc. Microwave Opt Technol Lett 48:2354–2357, 2006;Published online in Wiley InterScience (www.interscience.wiley.com).DOI 10.1002/mop.21942
