• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
  • DOI
  • UT
成果搜索
High Impact Results & Cited Count Trend for Year Keyword Cloud and Partner Relationship

Query:

学者姓名:周术诚

Refining:

Language

Submit

Clean All

Sort by:
Default
  • Default
  • Title
  • Year
  • WOS Cited Count
  • Impact factor
  • Ascending
  • Descending
< Page ,Total 3 >
基于图像融合和注意力机制的图像分类
期刊论文 | 2025 , 48 (03) , 120-128 | 南京师大学报(自然科学版)
Abstract&Keyword Cite

Abstract :

图像分类作为计算机视觉领域的一个关键任务,在多种应用场景中具有重要意义.针对图像分类中的准确性和鲁棒性问题,提出了一种基于图像融合和注意力机制的分类方法.首先,选用了ResNet-152作为图像分类的基础模型,并对公开数据集进行了预处理.在特征融合阶段,采用了三个并行支路,分别应用不同大小的卷积核进行特征提取.随后,在残差网络结构后引入了注意力机制,综合了构建的格拉姆矩阵、平均池化和最大池化,以突出模型对分类有益的区域.在实验阶段,在公共图像数据集上进行大量实验,结果表明所提出的方法在实际应用中表现出很好的效果,分类准确度从最初的96.68%提高到98.87%.同时,相较于传统方法具有更好的鲁棒性.因此,本研究为图像分类领域提供了一种有效的改进方法,具有广泛的应用前景.

Keyword :

卷积网络 卷积网络 图像分类 图像分类 图像融合 图像融合 注意力机制 注意力机制 深度学习 深度学习

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 黄文秀 , 周术诚 , 陈新元 et al. 基于图像融合和注意力机制的图像分类 [J]. | 南京师大学报(自然科学版) , 2025 , 48 (03) : 120-128 .
MLA 黄文秀 et al. "基于图像融合和注意力机制的图像分类" . | 南京师大学报(自然科学版) 48 . 03 (2025) : 120-128 .
APA 黄文秀 , 周术诚 , 陈新元 , 周忠眉 , 王榕国 . 基于图像融合和注意力机制的图像分类 . | 南京师大学报(自然科学版) , 2025 , 48 (03) , 120-128 .
Export to NoteExpress RIS BibTex

Version :

基于多注意力U-Net全卷积网络的视网膜图像视盘提取方法 incoPat ipsunlight
专利 | 2022-01-12 | CN202210029904.1
Abstract&Keyword Cite

Abstract :

本发明涉及一种基于多注意力U‑Net全卷积网络的视网膜图像视盘提取方法,包括以下步骤:步骤S1 : 获取原始彩色视网膜图像,并采用最亮点提取及区域模糊最亮区域的方法进行感兴趣区域提取;步骤S2 : 根据提取的感兴趣区域图像,采用RGB通道分离,并对分离后的红色通道图像进行直方图均衡化和标准化处理;步骤S3 : 将红色通道图像,直方图均衡化图图像和标准化图像进行通道融合产生新的三通道图像;步骤S4 : 基于多注意力U‑Net全卷积网络,构建并训练视网膜图像视盘分割模型;步骤S5将将通道融合后的图像数据输入视网膜视盘分割模型进行视网膜图像视盘提取分割。本发明实现了视网膜图像视盘的高精度提取分割。

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 魏丽芳 , 陈楠 , 李军 et al. 基于多注意力U-Net全卷积网络的视网膜图像视盘提取方法 : CN202210029904.1[P]. | 2022-01-12 .
MLA 魏丽芳 et al. "基于多注意力U-Net全卷积网络的视网膜图像视盘提取方法" : CN202210029904.1. | 2022-01-12 .
APA 魏丽芳 , 陈楠 , 李军 , 徐宏韬 , 杨长才 , 周术诚 et al. 基于多注意力U-Net全卷积网络的视网膜图像视盘提取方法 : CN202210029904.1. | 2022-01-12 .
Export to NoteExpress RIS BibTex

Version :

The U-NET Via Batch Norm Model for Optic Disc Extraction and Segmentation in Retinal Image EI
期刊论文 | 2022 , 511-514 | ACM International Conference Proceeding Series
Abstract&Keyword Cite

Abstract :

The segmentation and location of the optic disc in retinal images is of great significance for early diagnosis of glaucoma. To solve the issue, a novel optic disc segmentation and location algorithm is proposed by U-NET network combing the BatchNorm structure. And the morphological opening and reconstruction are used to highlight the position of optic disc and the improved U-NET is utilized to train the segmentation model. The public database IDRiD is used to evaluate the performance of the proposed algorithm. Experimental results indicate that the U-NET can obtain better optic disc structure, especially for the extraction of optic disc edge. The average accuracy is 0.9972, sensitivity is 0.9835, specificity is 0.9975, and Area Under Curve is up to 0.9458, Dice is 0.9435, mIoU is 0.8932. The performances are more competitive than state-of-the-art methods. © 2022 ACM.

Keyword :

Diagnosis Diagnosis Extraction Extraction Image segmentation Image segmentation Ophthalmology Ophthalmology

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Chen, Nan , Zhao, Yi , Li, Jun et al. The U-NET Via Batch Norm Model for Optic Disc Extraction and Segmentation in Retinal Image [J]. | ACM International Conference Proceeding Series , 2022 : 511-514 .
MLA Chen, Nan et al. "The U-NET Via Batch Norm Model for Optic Disc Extraction and Segmentation in Retinal Image" . | ACM International Conference Proceeding Series (2022) : 511-514 .
APA Chen, Nan , Zhao, Yi , Li, Jun , Yang, Danni , Zhou, Shucheng , Xue, Lanyan . The U-NET Via Batch Norm Model for Optic Disc Extraction and Segmentation in Retinal Image . | ACM International Conference Proceeding Series , 2022 , 511-514 .
Export to NoteExpress RIS BibTex

Version :

改进的k最邻近算法在海量数据挖掘中的应用
期刊论文 | 2021 , 35 (01) , 24-28 | 济南大学学报(自然科学版)
Abstract&Keyword Cite

Abstract :

为了提高数据挖掘的效率与准确性,将k最邻近算法与样本均衡策略相结合,在海量数据挖掘中进行应用;首先对样本集文本进行分析,找出样本领域的密集分布区域,对样本密集区域进行有效裁剪优化,实现样本分布均衡,然后对经过样本均衡处理的数据样本执行传统k最邻近算法,根据权重获得分类结果,最后对不同k值的k最邻近算法进行实例仿真。结果表明,在相同的数据样本环境中,相比于其他分类算法,采用改进的k最邻近算法的分类准确度和分类效率更高。

Keyword :

k最邻近算法 k最邻近算法 数据挖掘 数据挖掘 样本优化 样本优化 样本均衡 样本均衡 邻域密集区域 邻域密集区域

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 黄文秀 , 唐超尘 , 神显豪 et al. 改进的k最邻近算法在海量数据挖掘中的应用 [J]. | 济南大学学报(自然科学版) , 2021 , 35 (01) : 24-28 .
MLA 黄文秀 et al. "改进的k最邻近算法在海量数据挖掘中的应用" . | 济南大学学报(自然科学版) 35 . 01 (2021) : 24-28 .
APA 黄文秀 , 唐超尘 , 神显豪 , 周术诚 . 改进的k最邻近算法在海量数据挖掘中的应用 . | 济南大学学报(自然科学版) , 2021 , 35 (01) , 24-28 .
Export to NoteExpress RIS BibTex

Version :

基于均衡采样拼接的多通道U型全卷积神经网络的视网膜血管图像分割方法 incoPat ipsunlight
专利 | 2020-09-07 | CN202010931829.9
Abstract&Keyword Cite

Abstract :

本发明提出一种基于均衡采样拼接的多通道U型全卷积神经网络的视网膜血管图像分割方法,包括以下步骤:步骤S1:对原始彩色视网膜图像采用三通道直方图均衡化并结合特性值伽马矫正进行预处理;步骤S2:构建多尺度均衡化划分采样点后进行图像块随机拼接扩充数据样本;步骤S3:将图像数据归一化;步骤S4:将归一化后的图像数据输入视网膜血管分割模型进行视网膜血管网络分割;所述视网膜血管分割模型由训练集产生的归一化后的图像数据通过对色彩敏感的三通道U‑Net全卷积网络进行训练获得。其在精度,灵敏度,以及特异性以及AUC上有较大优势。

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 魏丽芳 , 张天一 , 张婷 et al. 基于均衡采样拼接的多通道U型全卷积神经网络的视网膜血管图像分割方法 : CN202010931829.9[P]. | 2020-09-07 .
MLA 魏丽芳 et al. "基于均衡采样拼接的多通道U型全卷积神经网络的视网膜血管图像分割方法" : CN202010931829.9. | 2020-09-07 .
APA 魏丽芳 , 张天一 , 张婷 , 杨长才 , 周术诚 , 陈日清 . 基于均衡采样拼接的多通道U型全卷积神经网络的视网膜血管图像分割方法 : CN202010931829.9. | 2020-09-07 .
Export to NoteExpress RIS BibTex

Version :

Robust Correspondence Detection by L2E Estimator for Retinal Image Registration CPCI-S
期刊论文 | 2017 , 318-324 | 2017 14TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS AND NETWORKS & 2017 11TH INTERNATIONAL CONFERENCE ON FRONTIER OF COMPUTER SCIENCE AND TECHNOLOGY & 2017 THIRD INTERNATIONAL SYMPOSIUM OF CREATIVE COMPUTING (ISPAN-FCST-ISCC)
Abstract&Keyword Cite

Abstract :

Establishing reliable correspondences is often challenging for retinal image registration with poor quality and low overlap. The conventional local search methods usually find many incorrect correspondences by feature descriptor, which would degrade the accuracy of image registration. In this paper, we propose a robust correspondence detection framework for low overlap and poor quality retinal image registration. Specifically, coherent spatial criterion is utilized to remove the false correspondences based on the initial matches in the first hierarchical. And the L-2-minimizing estimator is used for further hierarchical discarding significant fraction of outliers and estimating the transformation parameters to align the retinal images by affine model and quadratic model. Since such fitting inliers can be used to preserve the significant correspondences between the fixed image and to-be-aligned image with low overlap, it becomes more efficient to obtain accurate transformation. Through quantitative measurements and visual inspect, our proposed method shows the superior robustness and accuracy to the state-of-the-art methods.

Keyword :

correspondence detection correspondence detection image registration image registration L-2-minimizing estimate L-2-minimizing estimate retinal image retinal image

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Wei, Lifang , Yang, Changcai , Zhou, Shucheng et al. Robust Correspondence Detection by L2E Estimator for Retinal Image Registration [J]. | 2017 14TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS AND NETWORKS & 2017 11TH INTERNATIONAL CONFERENCE ON FRONTIER OF COMPUTER SCIENCE AND TECHNOLOGY & 2017 THIRD INTERNATIONAL SYMPOSIUM OF CREATIVE COMPUTING (ISPAN-FCST-ISCC) , 2017 : 318-324 .
MLA Wei, Lifang et al. "Robust Correspondence Detection by L2E Estimator for Retinal Image Registration" . | 2017 14TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS AND NETWORKS & 2017 11TH INTERNATIONAL CONFERENCE ON FRONTIER OF COMPUTER SCIENCE AND TECHNOLOGY & 2017 THIRD INTERNATIONAL SYMPOSIUM OF CREATIVE COMPUTING (ISPAN-FCST-ISCC) (2017) : 318-324 .
APA Wei, Lifang , Yang, Changcai , Zhou, Shucheng , Chen, Riqing , Pan, Lin . Robust Correspondence Detection by L2E Estimator for Retinal Image Registration . | 2017 14TH INTERNATIONAL SYMPOSIUM ON PERVASIVE SYSTEMS, ALGORITHMS AND NETWORKS & 2017 11TH INTERNATIONAL CONFERENCE ON FRONTIER OF COMPUTER SCIENCE AND TECHNOLOGY & 2017 THIRD INTERNATIONAL SYMPOSIUM OF CREATIVE COMPUTING (ISPAN-FCST-ISCC) , 2017 , 318-324 .
Export to NoteExpress RIS BibTex

Version :

基于马尔可夫随机场的运动物体检测方法 CSCD PKU
期刊论文 | 2016 , 45 (01) , 116-120 | 福建农林大学学报(自然科学版)
Abstract&Keyword Cite

Abstract :

智能监控的实现是避免和防范变电站内各种潜在危险的一种有效途径.为了更准确判定变电站工作人员的运动状态,提出一种基于高斯混合模型结合马尔可夫随机场的运动物体检测方法.在图像的HSV颜色空间通过混合高斯背景建模实现对运动物体的初步检测,采用区域性马尔可夫随机场与运动物体模板匹配实现运动物体的精确检测,并根据模板去除存在的阴影.结果表明,该方法可在变电站不同背景条件下有效检测出运动物体,为运动物体的行为分析及运动场景拼接奠定了良好的基础.

Keyword :

视频图像 视频图像 运动检测 运动检测 马尔可夫随机场 马尔可夫随机场 高斯混合模型 高斯混合模型

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 魏丽芳 , 林甲祥 , 杨长才 et al. 基于马尔可夫随机场的运动物体检测方法 [J]. | 福建农林大学学报(自然科学版) , 2016 , 45 (01) : 116-120 .
MLA 魏丽芳 et al. "基于马尔可夫随机场的运动物体检测方法" . | 福建农林大学学报(自然科学版) 45 . 01 (2016) : 116-120 .
APA 魏丽芳 , 林甲祥 , 杨长才 , 董恒 , 周术诚 . 基于马尔可夫随机场的运动物体检测方法 . | 福建农林大学学报(自然科学版) , 2016 , 45 (01) , 116-120 .
Export to NoteExpress RIS BibTex

Version :

The plant virus microscope image registration method based on mismatches removing SCIE
期刊论文 | 2016 , 80 , 90-95 | MICRON
WoS CC Cited Count: 6
Abstract&Keyword Cite

Abstract :

The electron microscopy is one of the major means to observe the virus. The view of virus microscope images is limited by making specimen and the size of the camera's view field. To solve this problem, the virus sample is produced into multi-slice for information fusion and image registration techniques are applied to obtain large field and whole sections. Image registration techniques have been developed in the past decades for increasing the camera's field of view. Nevertheless, these approaches typically work in batch mode and rely on motorized microscopes. Alternatively, the methods are conceived just to provide visually pleasant registration for high overlap ratio image sequence. This work presents a method for virus microscope image registration acquired with detailed visual information and subpixel accuracy, even when overlap ratio of image sequence is 10% or less. The method proposed focus on the correspondence set and interimage transformation. A mismatch removal strategy is proposed by the spatial consistency and the components of keypoint to enrich the correspondence set. And the translation model parameter as well as tonal inhomogeneities is corrected by the hierarchical estimation and model select. In the experiments performed, we tested different registration approaches and virus images, confirming that the translation model is not always stationary, despite the fact that the images of the sample come from the same sequence. The mismatch removal strategy makes building registration of virus microscope images at subpixel accuracy easier and optional parameters for building registration according to the hierarchical estimation and model select strategies make the proposed method high precision and reliable for low overlap ratio image sequence. (C) 2015 Elsevier Ltd. All rights reserved.

Keyword :

Image registration Image registration Mismatching removal Mismatching removal Transformation models Transformation models Virus microscope image Virus microscope image

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 Wei, Lifang , Zhou, Shucheng , Dong, Heng et al. The plant virus microscope image registration method based on mismatches removing [J]. | MICRON , 2016 , 80 : 90-95 .
MLA Wei, Lifang et al. "The plant virus microscope image registration method based on mismatches removing" . | MICRON 80 (2016) : 90-95 .
APA Wei, Lifang , Zhou, Shucheng , Dong, Heng , Mao, Qianzhuo , Lin, Jiaxiang , Chen, Riqing . The plant virus microscope image registration method based on mismatches removing . | MICRON , 2016 , 80 , 90-95 .
Export to NoteExpress RIS BibTex

Version :

带反方向视角和二项交叉的布谷鸟搜索算法 CSCD PKU
期刊论文 | 2015 , 9 (08) , 1010-1017 | 计算机科学与探索
Abstract&Keyword Cite

Abstract :

布谷鸟搜索算法是一种新兴的自然仿生优化技术,其借用Lévy Flights随机走动和Biased随机走动搜索新的解。在Lévy Flights随机走动中,所有个体以当前种群获得的最优解为导向进行搜索,这容易导致种群趋同于该最优解。针对此问题,引入反方向视角使种群基于一定概率反向搜索,以避免趋同于当前最优解,并提出带反方向视角和二项式交叉的布谷鸟搜索算法。在提出的算法中,借用二项交叉操作以提高Biased随机走动的搜索能力。与标准的布谷鸟搜索算法对比,实验结果说明提出的策略能够有效地改善布谷鸟搜索算法求解连续函数优化问题的收敛速度和解的质量。与其他改进的布谷鸟搜索算法以及其他进化算法对比,实验结果说明提出的算法在求解连续函数优化问题上具有一定的竞争力。

Keyword :

二项交叉 二项交叉 函数优化问题 函数优化问题 反方向视角 反方向视角 布谷鸟搜索算法 布谷鸟搜索算法

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 梁忠 , 林要华 , 周术诚 . 带反方向视角和二项交叉的布谷鸟搜索算法 [J]. | 计算机科学与探索 , 2015 , 9 (08) : 1010-1017 .
MLA 梁忠 et al. "带反方向视角和二项交叉的布谷鸟搜索算法" . | 计算机科学与探索 9 . 08 (2015) : 1010-1017 .
APA 梁忠 , 林要华 , 周术诚 . 带反方向视角和二项交叉的布谷鸟搜索算法 . | 计算机科学与探索 , 2015 , 9 (08) , 1010-1017 .
Export to NoteExpress RIS BibTex

Version :

基于信誉权值策略的多重第三方远程证明机制 CSCD PKU
期刊论文 | 2015 , 50 (11) , 47-51,59 | 山东大学学报(理学版)
Abstract&Keyword Cite

Abstract :

针对单一第三方失效而影响云计算环境证明有效性问题,提出一种基于多重第三方远程证明机制。将单一第三方扩展为第三方验证者集群,保证了在部分验证者受到安全威胁情况下,仍然能够为证明请求者提供可靠的证明结果。同时提出第三方筛选算法和基于信誉权值策略应对多个第三方合谋攻击,避免由于恶意指控清白验证者而导致最终断言失效情形。实验结果表明,该机制相对于单一验证者更为安全可靠,在实际应用中能有效防御合谋攻击。

Keyword :

信誉权值策略 信誉权值策略 多重第三方 多重第三方 远程证明 远程证明

Cite:

Copy from the list or Export to your reference management。

GB/T 7714 纪祥敏 , 苏航 , 向騻 et al. 基于信誉权值策略的多重第三方远程证明机制 [J]. | 山东大学学报(理学版) , 2015 , 50 (11) : 47-51,59 .
MLA 纪祥敏 et al. "基于信誉权值策略的多重第三方远程证明机制" . | 山东大学学报(理学版) 50 . 11 (2015) : 47-51,59 .
APA 纪祥敏 , 苏航 , 向騻 , 周术诚 . 基于信誉权值策略的多重第三方远程证明机制 . | 山东大学学报(理学版) , 2015 , 50 (11) , 47-51,59 .
Export to NoteExpress RIS BibTex

Version :

10| 20| 50 per page
< Page ,Total 3 >

Export

Results:

Selected

to

Format:
Online/Total:122/15010
Address:FAFU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350002)
Copyright:FAFU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备10012082号