检索结果-内蒙古大学图书馆

Discrete-Time dynamic image segmentation Using Oscillators with Adaptive Coupling

International Journal of Modern Nonlinear Theory and Application 2016年第2期5卷 93-103页

作者： Mio Kobayashi Tetsuya Yoshinaga Department of Creative Technology Engineering National Institute of Technology Anan College Tokushima Japan Institute of Health Biosciences Tokushima University Tokushima Japan

In this study, we propose a novel discrete-time coupled model to generate oscillatory responses via periodic points with a high periodic order. Our coupled system comprises one-dimensional oscillators based on the Rulkov map and a single globally coupled oscillator. Because the waveform of a one-dimensional oscillator has sharply defined peaks, the coupled system can be applied to dynamic image segmentation. Our proposed system iteratively transforms the coupling of each oscillator based on an input value that corresponds to the pixel value of an input image. This approach enables our system to segment image regions in which pixel values gradually change with respect to a connected region. We conducted a bifurcation analysis of a single oscillator and a three-coupled model. Through simulations, we demonstrated that our system works well for gray-level images with three isolated image regions.

关键词： Discrete-Time Coupled Model dynamic image segmentation Oscillatory Responses One-Dimensional Oscillator

来源：评论

学校读者我要写书评

暂无评论

Damage detection method of automobile hub based on image texture feature

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2023年第4期23卷 1941-1953页

作者： Wang, Ying Wuxi Inst Technol Sch Automobile & Transportat Wuxi 214121 Jiangsu Peoples R China

With the rapid growth in the number of motor vehicles worldwide, the general public is beginning to attach importance to the quality inspection of wheels before they leave the factory. The current wheel defect detection systems are often cumbersome to operate and have low practical performance. Therefore, this research will use dynamic image segmentation, image texture feature extraction and Back Propagation neural network classification based on wheel image defect feature analysis algorithm to achieve automatic intelligent detection of automotive wheel defects. In this study, an intelligent detection system for automotive wheel defects is also designed, and finally the performance of the detection system is tested experimentally to illustrate its practicality. The experimental results show that the proposed intelligent detection system for automotive wheel defects based on image texture features identifies defects in wheel castings with a correct rate of 96% and a false positive rate of only 2%. This illustrates that the detection system proposed in this study has a high recognition rate and can provide a useful reference for the automotive industry inspection.

关键词： image texture features automotive wheels dynamic image segmentation defect detection

来源：评论

学校读者我要写书评

暂无评论

A segmentation method for left ventricular magnetic resonance images based on temporal feature enhancement 9

A segmentation method for left ventricular magnetic resonanc...

引用

9th International Symposium on Computer and Information Processing Technology, ISCIPT 2024

作者： Li, Yuanzhe Xu, Huahu Cao, Yongji Chen, Xingyuan Shanghai University College of Computer Engineering and Science Shanghai China Shanghai Forensic Service Platform Shanghai Key Laboratory of Forensic Medicine Shanghai China

ISBN: (纸本)9798350388404

Accurate segmentation of the left ventricle (LV) from dynamic cardiac magnetic resonance imaging (MRI) is a critical focus in computer-assisted cardiovascular diagnostics. Most current deep learning methods, which are primarily designed for static imaging, often overlook the temporal features inherent in the heart's continuous motion. This oversight can limit their effectiveness in clinical diagnostic applications. To address this, we introduce a novel segmentation model, ST TransUNet, which is specifically tailored to capture the dynamic MRI data's feature information along the time dimension. Our model integrates temporal and deformable global attention modules to enhance the accuracy of LV segmentation throughout the cardiac cycle. We conducted experimental validation using three publicly available cine-MRI datasets: ACDC, NDSB2, and SCD. Results demonstrate that ST TransUNet achieves the highest mean Dice Similarity Coefficient (DSC) across all frames within the cardiac cycle and particularly excels in segmenting the LV during the end-systolic phase, when morphological complexity is at its peak. The proposed model offers a promising approach for automatic LV segmentation in MRI imaging. © 2024 IEEE.

关键词： Deep Learning dynamic image segmentation Left Ventricular MRI segmentation Temporal-feature Enhancement

来源：评论

学校读者我要写书评

暂无评论

Discrete-Time dynamic image segmentation Based on Oscillations by Destabilizing a Fixed Point

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2011年第5期6卷 468-473页

作者： Fujimoto, Ken'ichi Kobayashi, Mio Yoshinaga, Tetsuya Univ Tokushima Inst Hlth Biosci Tokushima 7708509 Japan Univ Tokushima Grad Sch Hlth Sci Tokushima 7708509 Japan

We have developed a discrete-time dynamical system consisting of a global inhibitor and chaotic neurons that can generate oscillatory responses. We have also found that our system can work as a dynamic image-segmentation system utilizing oscillatory responses of chaotic neurons. dynamic image segmentation is to severally extract isolated image regions from a static image and is to exhibit segmented images in time series according to oscillatory responses of chaotic neurons. At certain parameter values, chaotic neurons can generate adequate oscillatory responses for dynamic image segmentation. However, they generate non-oscillatory responses for certain initial values due to the coexistence of a stable fixed point corresponding to non-oscillatory responses. Their appearances indicate that our system does not work as a dynamic image-segmentation system. In this study, we designed a destabilizer for a stable fixed point to prevent its appearance. We also demonstrated that our system with a designed destabilizer worked well. (C) 2011 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

关键词： chaotic neuron oscillatory response dynamic image segmentation stable fixed point destabilizer

来源：评论

学校读者我要写书评

暂无评论

Human image Recognition through dynamic Mapping Generation 4

Human Image Recognition through Dynamic Mapping Generation

引用

4th International Conference on Green Technology and Sustainable Development (GTSD)

作者： Feng, Hsuan-Ming Chen, Hua-Ching Wong, Ching-Chang Natl Quemoy Univ Dept Comp Sci & Informat Engn 1 Univ Rd Kin Ning Vallage Kinmen 892 Taiwan Tamkang Univ Dept Elect Engn New Taipei Taiwan

ISBN: (纸本)9781538651261

This paper proposed an image preparing technology to remove completely the noise effects of unexpected conditions and actually extract primary feature of human pose in indoor environment. Color image conversation with YCbCr, enhanced image intelligibility with a median filter, one OPEN operation and one labeling algorithm, are applied to detect the object's boundary. A dynamic image segmentation matching algorithm generated human feature vectors, which are used to search the most similar pattern for approximating the correct human pose. Several experiments show that the proposed dynamic image segmentation matching algorithm actually detected the real characteristics of human pose and makes the great support to re-cover the various image feature problem in complex environment. Future work Or an intelligent human pose is used to virtually control home equipment in everywhere.

关键词： image Preparing Technology dynamic image segmentation Human Pose Recognition

来源：评论

学校读者我要写书评

暂无评论

Automated Coronary Tree segmentation for X-ray Angiography Sequences Using Fully-convolutional Neural Networks 33

Automated Coronary Tree Segmentation for X-ray Angiography S...

引用

33rd IEEE International Conference on Visual Communications and image Processing (IEEE VCIP)

作者： Zhao, Lei Li, Deyu Chen, Jianhui Wan, Tao Beihang Univ Sch BSME Beijing Peoples R China 91 Cent Hosp PLA Jiaozuo Henan Peoples R China Beihang Univ Beijing Adv Innovat Ctr Biomed Engn Beijing Peoples R China

ISBN: (纸本)9781538644584

Cardiovascular disease is the number one killer that threatens human health. Analysis of coronary vascular geometry plays an important role in the diagnosis of cardiovascular disease. In order to make reliable judgments for clinical usage, accurate and robust vascular segmentation methods are needed. We present an improved segmentation approach for dynamic coronary angiography sequences, which can obtain blood vessel trees in real time. We start with a pre-trained convolutional neural network (CNN) on imageNet as the base network for initialization. We then adapt this network to the structure of one-shot video object segmentation (OSVOS) to obtain the parent network, which is trained on 50 X-ray angiography sequences for extracting blood vessels. Finally, the model is further fine-tuned using 10 specific coronary angiography sequences to achieve real-time vascular segmentation. Our method achieved the Dice index of 0.88, suggesting that the presented method can be potentially useful in developing a real-time segmentation method for coronary angiography sequences.

关键词： coronary tree extraction dynamic image segmentation coronary angiography convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

dynamic image segmentation SYSTEM WITH MULTI-SCALING SYSTEM FOR GRAY SCALE image

DYNAMIC IMAGE SEGMENTATION SYSTEM WITH MULTI-SCALING SYSTEM ...

引用

3rd International Conference on Bio-Inspired Systems and Signal Processing (BIOSIGNALS 2010)

作者： Fujimoto, Ken'ichi Musashi, Mio Yoshinaga, Tetsuya Univ Tokushima Inst Hlth Biosci 3-18-15 Kuramoto Tokushima 7708509 Japan Univ Tokushima Grad Sch Hlth Sci Tokushima 7708509 Japan

ISBN: (纸本)9789896740184

In this paper, we describe an image segmentation technique for a gray scale image by utilizing the nonlinear dynamics of two respective discrete-time dynamical systems. The authors have proposed a discrete-time dynamical system that consists of a global inhibitor and chaotic neurons that can generate oscillatory responses. By utilizing oscillatory responses, our system can perform dynamic image segmentation, which denotes segmenting image regions in an image and concurrently exhibiting segmented images in time series, for a binary image. In order that our system can work for a gray scale image, we introduce a multi-scaling system as a pre-processing unit of our system. It is also made of a discrete-time dynamical system and can find an image region composed of pixels with different gray levels by multi-scaling gray levels of pixels. In addition, it can compute the proximity between pixels based on their multi-scaled gray levels. Computed proximity becomes significant information for designing parameters in our system. We demonstrated that our dynamic image segmentation system with the multi-scaling system works well for a gray scale image.

关键词： dynamic image segmentation Coupled system Chaotic neurons Gray scale image Multi-scaling of gray levels

来源：评论

学校读者我要写书评

暂无评论

Reduced Model of Discrete-Time dynamic image segmentation System and Its Bifurcation Analysis

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2009年第4期19卷 283-289页

作者： Fujimoto, Ken'ichi Musashi, Mio Yoshinaga, Tetsuya Univ Tokushima Inst Hlth Biosci Tokushima 7708509 Japan Univ Tokushima Grad Sch Hlth Sci Tokushima 7708509 Japan

We have developed a discrete-time dynamic image segmentation system consisting of chaotic neurons and a global inhibitor. Our system receives an image with isolated regions and can output segmented images in time series based on oscillatory responses of chaotic neurons. In this article, we derive a reduced model to find intrinsic properties of the system of dynamic image segmentation. Using numerical method for analyzing dynamical systems, we investigated bifurcation phenomena of a fixed point observed in the reduced model. As the results, in a model of two coupled chaotic neurons, we found that a set of Neimark-Sacker bifurcations causes the generation of an in-phase oscillatory response, which is unsuitable for the purpose of dynamic image segmentation. The bifurcation analysis gives appropriate parameter values to exclude the generation of in-phase oscillatory responses, i.e., our dynamic image segmentation system can work well. (C) 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 283-289, 2009;Published online in Wiley InterScience (***). DOI 10.1002/ima.20204

关键词： dynamic image segmentation discrete-time dynamical system oscillatory response bifurcation

来源：评论

学校读者我要写书评

暂无评论

IDENTIFICATION OF TARGET image REGIONS BASED ON BIFURCATIONS OF A FIXED POINT IN A DISCRETE-TIME OSCILLATOR NETWORK

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2013年第1期9卷 355-363页

作者： Fujimoto, Ken'ichi Kobayashi, Mio Yoshinaga, Tetsuya Aihara, Kazuyuki Univ Tokushima Inst Hlth Biosci 3-18-15 Kuramoto Tokushima 7708509 Japan Anan Natl Coll Technol Dept Syst & Control Engn Anan 7740017 Japan Univ Tokyo Inst Ind Sci Meguro Ku Tokyo 1538505 Japan

image segmentation is a fundamental technique in image processing. We call the function that extracts blobs (image regions) in a given image and exhibits them in a time series "dynamic image segmentation". It is known that a locally excitatory globally inhibitory oscillator network (LEGION) described by ordinary differential equations is an interesting dynamic image-segmentation system using synchronization of coupled oscillators. On the other hand, we developed a discrete-time oscillator network that can perform dynamic image segmentation by synchronizing the oscillatory responses that are formed by periodic points in dynamics of discrete-time oscillators. Compared with LEGION, the proposed system can significantly reduce a computational cost because it does not need unnecessary numerical integration;moreover, we can design the suitable values of the system parameters for dynamic image segmentation on the basis of analyzed results on bifurcations of fixed and periodic points. In this paper, we describe how the topological property of a fixed point corresponding to non-oscillatory responses that are unsuitable for dynamic image segmentation in the proposed system gives significant information on the structure of regions in a given binary (black and white) image. We also suggest a novel way to identify the number of image regions without performing a segmentation process.

关键词： Discrete-time oscillator Fixed point Neimark-Sacker bifurcation dynamic image segmentation The number of image regions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：