期刊文献+
共找到645篇文章
< 1 2 33 >
每页显示 20 50 100
A VIDEO SPECTRUM SPLITTING ENCODING SCHEME BASED ON HUMAN VISION AND ITS COMPUTER SIMULATION
1
作者 赵宇 李华 +1 位作者 俞斯乐 滕建辅 《Transactions of Tianjin University》 EI CAS 1995年第1期79+76-79,共5页
In this paper, a 3-D video encoding scheme suitable for digital TV/HDTV (high definition television) is studied through computer simulation. The encoding scheme is designed to provide a good match to human vision. Bas... In this paper, a 3-D video encoding scheme suitable for digital TV/HDTV (high definition television) is studied through computer simulation. The encoding scheme is designed to provide a good match to human vision. Basically, this involves transmission of low frequency luminance information at full frame rate for good motion rendition and transmission of high frequency luminance signal at reduced frame rate for good detail in static images. 展开更多
关键词 D video encoding discrete wavelet transform human vision computer simulation
在线阅读 下载PDF
Interpolation of Images Using Discrete Wavelet Transform to Simulate Image Resizing as in Human Vision 被引量:5
2
作者 Rohini S. Asamwar Kishor M. Bhurchandi Abhay S. Gandhi 《International Journal of Automation and computing》 EI 2010年第1期9-16,共8页
This paper presents discrete wavelet transform (DWT) and its inverse (IDWT) with Haar wavelets as tools to compute the variable size interpolated versions of an image at optimum computational load. As a human obse... This paper presents discrete wavelet transform (DWT) and its inverse (IDWT) with Haar wavelets as tools to compute the variable size interpolated versions of an image at optimum computational load. As a human observer moves closer to or farther from a scene, the retinal image of the scene zooms in or out, respectively. This zooming in or out can be modeled using variable scale interpolation. The paper proposes a novel way of applying DWT and IDWT in a piecewise manner by non-uniform down- or up-sampling of the images to achieve partially sampled versions of the images. The partially sampled versions are then aggregated to achieve the final variable scale interpolated images. The non-uniform down- or up-sampling here is a function of the required scale of interpolation. Appropriate zero padding is used to make the images suitable for the required non-uniform sampling and the subsequent interpolation to the required scale. The concept of zeroeth level DWT is introduced here, which works as the basis for interpolating the images to achieve bigger size than the original one. The main emphasis here is on the computation of variable size images at less computational load, without compromise of quality of images. The interpolated images to different sizes and the reconstructed images are benchmarked using the statistical parameters and visual comparison. It has been found that the proposed approach performs better as compared to bilinear and bicubic interpolation techniques. 展开更多
关键词 Discrete wavelet transform nomuniform sampling zeroeth level discrete wavelet transform (DWT) INTERPOLATION human vision.
在线阅读 下载PDF
Shadow detection combining characters of human vision
3
作者 李建锋 邹北骥 +1 位作者 李玲芝 高焕芝 《Journal of Central South University》 SCIE EI CAS 2014年第2期659-667,共9页
A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined tog... A shadow detection method using pulse couple neural network inspired by the characters of human visual system is proposed.More precisely,lateral inhibition of human vision and coefficient of variation are combined together to improve the pulse couple neural network.Shadow detection is considered to be a shadow region segmentation problem.Experiment shows that the presented method is consistent with human vision compared to shadow detection methods based on HSV and pulse couple neural network(PCNN) by both subjective and objective assessments. 展开更多
关键词 pulse couple neural network lateral inhibition shadow detection coefficient of variation weight matrix human vision system
在线阅读 下载PDF
Rendering algorithms for aberrated human vision simulation
4
作者 István Csoba Roland Kunkli 《Visual Computing for Industry,Biomedicine,and Art》 EI 2023年第1期51-75,共25页
Vision-simulated imagery―the process of generating images that mimic the human visual system―is a valuable tool with a wide spectrum of possible applications, including visual acuity measurements, personalized plann... Vision-simulated imagery―the process of generating images that mimic the human visual system―is a valuable tool with a wide spectrum of possible applications, including visual acuity measurements, personalized planning of corrective lenses and surgeries, vision-correcting displays, vision-related hardware development, and extended reality discomfort reduction. A critical property of human vision is that it is imperfect because of the highly influential wavefront aberrations that vary from person to person. This study provides an overview of the existing computational image generation techniques that properly simulate human vision in the presence of wavefront aberrations. These algorithms typically apply ray tracing with a detailed description of the simulated eye or utilize the point-spread func-tion of the eye to perform convolution on the input image. Based on the description of the vision simulation tech-niques, several of their characteristic features have been evaluated and some potential application areas and research directions have been outlined. 展开更多
关键词 human vision human visual system vision simulation Wavefront aberrations Visual aberrations vision-realistic rendering
在线阅读 下载PDF
Reconstruction algorithm of super-resolution infrared image based on human vision processing mechanism 被引量:1
5
作者 Shaosheng DAI Zhihui DU Haiyan XIANG Jinsong LIU 《Frontiers of Optoelectronics》 CSCD 2015年第2期195-202,共8页
Aiming at solving the problem of low resolu- tion and visual blur in infrared imaging, a super-resolution infrared image reconstruction method using human vision processing mechanism (HVPM) was proposed. This method... Aiming at solving the problem of low resolu- tion and visual blur in infrared imaging, a super-resolution infrared image reconstruction method using human vision processing mechanism (HVPM) was proposed. This method combined a mechanism of vision lateral inhibition with an algorithm projection onto convex sets (POCS) reconstruction, the improved vision lateral inhibition network was utilized to enhance the contrast between object and background of low-resolution image sequences, then POCS algorithm was adopted to reconstruct super- resolution image. Experimental results showed that the proposed method can significantly improve the visual effect of image, whose contrast and information entropy of reconstructed infrared images were improved by approxi- mately 5 times and 1.6 times compared with traditional POCS reconstruction algorithm, respectively. 展开更多
关键词 human vision processing mechanism(HVPM) projection onto convex sets (POCS) SUPER-RESOLUTION infrared image reconstruction algorithm
原文传递
Human and Machine Vision Based Indian Race Classification Using Modified-Convolutional Neural Network
6
作者 Vani A.Hiremani Kishore Kumar Senapati 《Computer Systems Science & Engineering》 SCIE EI 2023年第3期2603-2618,共16页
The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographica... The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community. 展开更多
关键词 Data collection and preparation human vision analysis machine vision canny edge approximation method color local binary patterns convolutional neural network
在线阅读 下载PDF
Theoretical and practical exploration of vision building in human influenza pandemic prevention & control
7
作者 Peng Kong Yan Kong +1 位作者 Xu Jiang Xiaohua Wang 《Asian Pacific Journal of Tropical Medicine》 SCIE CAS 2010年第11期913-916,共4页
This article introduced the vision building concept about human influenza pandemic prevention and control.Different visions were built by creating different shapes of building blocks which also represented different o... This article introduced the vision building concept about human influenza pandemic prevention and control.Different visions were built by creating different shapes of building blocks which also represented different organizations and physical facilities,respectively.The around-view reflection is required to be developed in the process of building so as to search for the ideal pattern.The correlation of all sectors and systems are established to combine different kinds of things,from one family to another,from communities,towns,counties,cities,rural areas, provinces to the state to handle trivial problems.These training objectives have been successfully accomplished,which has not only enriched the knowledge about prevention and control of influenza pandemic between different departments but also clarified the roles and responsibility. It lays the firm foundation for next cooperation between different departments,and make a bridge for the objective and choice of channel over human influenza pandemic prevention and control. 展开更多
关键词 vision BUILDING human INFLUENZA PANDEMIC PREVENTION and CONTROL
暂未订购
The Declaration on the Right to Development as a First Step towards a Comprehensive Southern Vision on Human Rights 被引量:1
8
作者 Tom ZWART 《The Journal of Human Rights》 2017年第1期50-61,共12页
Having proper sanitation and hygiene, access to affordable health care and enough food on the table are the basic conditions for a dignified life. This link between human dignity and the right to development was made ... Having proper sanitation and hygiene, access to affordable health care and enough food on the table are the basic conditions for a dignified life. This link between human dignity and the right to development was made very persuasively already in the White Paper on human rights, issued by the State Council of P.R.C. in 1991. The Declaration on the right to development can be considered the first successful joint action undertaken by Southern states in the area of human rights. The Declaration was based on Southern scholarship, such as the pioneering research conducted by the Senegalese jurist Kéba M’baye. And its adoption was the result of joint stage management performed by diplomats from different continents. Therefore the Declaration serves as a source of inspiration for the work of drafting a Comprehensive Southern Vision on human rights. The Vision document will lay out a common Southern outlook on human rights issues as an elaboration of the Universal Declaration. 展开更多
关键词 Declaration on the right to development Comprehensive Southern vision Universal Declaration of human Rights Global South
原文传递
人体动作姿态识别方法研究综述
9
作者 梁本来 《信息记录材料》 2026年第1期18-20,26,共4页
人体动作识别技术是计算机视觉领域的重要研究方向。本文综述了当前主流的人体动作姿态识别方法,包括基于图像的姿态估计、基于视频的时序分析、三维空间姿态重建及基于骨架的动作识别等方法,通过对比分析各类方法在计算复杂度、场景适... 人体动作识别技术是计算机视觉领域的重要研究方向。本文综述了当前主流的人体动作姿态识别方法,包括基于图像的姿态估计、基于视频的时序分析、三维空间姿态重建及基于骨架的动作识别等方法,通过对比分析各类方法在计算复杂度、场景适应性和性能表现(准确性、实时性、鲁棒性等)等方面的特点,揭示了该技术领域面临的三维标注数据获取困难、复杂环境泛化能力不足及实时性与精度难以兼顾等核心挑战。针对未来发展趋势,本文探讨了轻量化模型设计、多模态融合、弱监督与自监督学习、三维时空建模、Transformer架构应用及领域自适应等关键研究方向,旨在为后续相关研究提供思路与借鉴。 展开更多
关键词 人体动作姿态识别 深度学习 计算机视觉 时空图卷积网络
在线阅读 下载PDF
多目视觉下的逆运动学三维人体建模仿真
10
作者 方国宇 李琰泽 +6 位作者 陈凯 赵晓冬 胡子卓 杨明实 武婉晴 王子晨 郭文凯 《系统仿真学报》 北大核心 2026年第1期99-111,共13页
自动驾驶仿真和工业虚拟现实仿真技术中对三维人体建模的准确性和鲁棒性具有较高的需求,现阶段基于关节点进行人体建模存在连续建模抖动、局部扭曲、遮挡适应性差等影响人体模型质量的问题,制约了智能驾驶和数字工厂等实际应用的发展。... 自动驾驶仿真和工业虚拟现实仿真技术中对三维人体建模的准确性和鲁棒性具有较高的需求,现阶段基于关节点进行人体建模存在连续建模抖动、局部扭曲、遮挡适应性差等影响人体模型质量的问题,制约了智能驾驶和数字工厂等实际应用的发展。针对上述问题,提出一种多目视觉下基于向量量化变分自编码器的逆运动学三维人体建模方法,通过梯度下降自动变分方法的联合训练与IK-VQ-VAE(inverse kinematics vector quantised-variational auto encoder)方法相结合,得到了多视角时序融合、遮挡适应且更具鲁棒性的方法,满足更加符合真实人体姿态的需求。在公开数据集Shelf上进行实验,结果显示所提方法的正确部件百分比(PCP)相比近年的优化工作最高提升23.7%,平均提升了8.7%,同时,定性实验分析结果也表明了所提方法对人体3D建模效果优于其他方法。 展开更多
关键词 多目视觉 人体网格恢复 向量量化变分自编码器 三维人体建模 人体姿态
原文传递
基于计算机视觉的羽毛球动作训练评估系统
11
作者 李朋 刘杰 谭肖 《工业控制计算机》 2026年第2期105-106,109,共3页
近年来,随着计算机视觉技术的发展,特别是人体三维重建的进步,为羽毛球运动的科学训练和评估提供了新的视角和方法。将人体动作三维重建技术应用于羽毛球运动教学中,对羽毛球挥拍动作进行三维重建与标准程度评估。首先,运用MotionCaptur... 近年来,随着计算机视觉技术的发展,特别是人体三维重建的进步,为羽毛球运动的科学训练和评估提供了新的视角和方法。将人体动作三维重建技术应用于羽毛球运动教学中,对羽毛球挥拍动作进行三维重建与标准程度评估。首先,运用MotionCapture技术,构建了一套羽毛球标准动作数据集。提出了一种称为TransGATify的Transformer和GAT的混合框架,该框架实现了基于SMPL目标表示的人体姿态网格3D重建。针对羽毛球挥拍动作特点,对羽毛球挥拍动作标准程度进行了定义。最后,基于以上环节搭建了一套智能化的羽毛球动作评估系统,为羽毛球运动教学提供了一个科学有效的工具。此外,该系统各个模块相较于现有计算机视觉领域方法都有显著提升,针对人体动作的细粒度分析取得良好效果。 展开更多
关键词 计算机视觉 人体三维重建 动作质量评估
在线阅读 下载PDF
基于机器视觉和HRNet网络的人体背部穴位识别方法
12
作者 刘娟 谢梦瑶 +1 位作者 袁佳俊 康轩源 《机电工程技术》 2026年第1期102-108,共7页
提出了一种融合改进HRNet网络与中医骨度折量理论的人体背部穴位识别方法,实现复杂个体化条件下的精准定位。针对传统方法及经典HRNet网络在密集穴位细微特征分辨上的不足,通过架构优化构建集成多阶门控聚合机制(MogaNet)的Moga-Conv异... 提出了一种融合改进HRNet网络与中医骨度折量理论的人体背部穴位识别方法,实现复杂个体化条件下的精准定位。针对传统方法及经典HRNet网络在密集穴位细微特征分辨上的不足,通过架构优化构建集成多阶门控聚合机制(MogaNet)的Moga-Conv异构卷积模块,显著增强网络对穴位细微特征差异的分辨能力;基于改进HRNet高精度检测的肩峰、脊柱中线等关键点信息,动态计算个体化“寸”单位长度及椎节高度,建立穴位位置与这些关键点之间的精准计量映射模型,大幅提升对不同体型和动态姿势的适应性与鲁棒性。为验证方法有效性,基于PyTorch框架,实现了改进型HRNet的轻量化部署及实时穴位坐标解析系统。在自建1000张图像背部腧穴数据集上的测试结果表明,该方法在脊柱中线及旁开穴位定位上展现出精度优势,相较于原始HRNet模型,AP提高了5.2%、PCK提高了1.6%、AR提高了1.5%。该方法为针灸机器人、智能艾灸设备等智慧中医诊疗系统提供了高精度、实时的可靠技术支撑,具有重要应用价值。 展开更多
关键词 机器视觉 HRNet 穴位识别 人体姿态估计
在线阅读 下载PDF
Spectral Test Instrument for Color Vision Measurement 被引量:1
13
作者 Balázs Vince Nagy Gyrgy brahám 《Journal of Bionic Engineering》 SCIE EI CSCD 2005年第2期75-79,共5页
Common displays such as CRT or LCD screens have limited capabilities in displaying most color spectra correctly. The main disadvantage of these devices is that they work with three primaries and the colors displayed a... Common displays such as CRT or LCD screens have limited capabilities in displaying most color spectra correctly. The main disadvantage of these devices is that they work with three primaries and the colors displayed are the mixture of these three colours. Consequently these devices can be confusing in testing human color identification, because the spectral distribution of the colors displayed is the combined spectrum of the three primaries. We have developed a new instrument for spectrally correct color vision measurement. This instrument uses light emitting diodes (LEDs) and is capable of producing all spectra of perceivable colors, thus with appropriate test methods this instrument can be a reliable and useful tool in test~ing human color vision and in verifying color vision correction. 展开更多
关键词 human color vision color vision measurement color spectrum LED instrument
在线阅读 下载PDF
Human eye ocular component analysis for refractive state and refractive surgery 被引量:3
14
作者 Chao-Kai Chang Jui-Teng Lin Yong Zhang 《International Journal of Ophthalmology(English edition)》 SCIE CAS 2017年第7期1076-1080,共5页
AIM: To analyze the clinical factors influencing the human vision corrections via the changing of ocular components of human eye in various applications; and to analyze refractive state via a new effective axial leng... AIM: To analyze the clinical factors influencing the human vision corrections via the changing of ocular components of human eye in various applications; and to analyze refractive state via a new effective axial length.METHODS: An effective eye model was introduced by the ocular components of human eye including refractive indexes, surface radius(r1, r2, R1, R2) and thickness(t, T) of the cornea and lens, the anterior chamber depth(S1) and the vitreous length(S2). Gaussian optics was used to calculate the change rate of refractive error per unit amount of ocular components of a human eye(the rate function M). A new criterion of myopia was presented via an effective axial length.RESULTS: For typical corneal and lens power of 42 and 21.9 diopters, the rate function Mj(j=1 to 6) were calculated for a 1% change of r1, r2, R1, R2, t, T(in diopters) M1=+0.485, M2=-0.063, M3=+0.053, M4=+0.091, M5=+0.012, and M6=-0.021 diopters. For 1.0 mm increase of S1 and S2, the rate functions were M7=+1.35, and M8=-2.67 diopter/mm, respectively. These rate functions were used to analyze the clinical outcomes in various applications including laser in situ keratomileusis surgery, corneal cross linking procedure, femtosecond laser surgery and scleral ablation for accommodation.CONCLUSION: Using Gaussian optics, analytic formulas are presented for the change of refractive power due to various ocular parameter changes. These formulas provide useful clinical guidance in refractive surgery and other related procedures. 展开更多
关键词 Gaussian optics human eye ocular components refractive errors vision correction laser in situ keratomileusis corneal collagen crosslinking
原文传递
Inspection and Reflection of Strategic Human Resource Management 被引量:1
15
作者 Liu Dawei 《学术界》 CSSCI 北大核心 2018年第5期250-258,共9页
关键词 strategic human resource management corporate vision corporate culture HRBP
在线阅读 下载PDF
A Critical Review of Healthcare Human Resource Development: A Saudization Perspective
16
作者 Fahad Alhazmi 《Health》 2021年第12期1496-1510,共15页
Saudi Arabia is currently in a transformation phase, which has resulted in a significant demand for healthcare services in the country’s healthcare system to provide better healthcare facilities for the fast-growing ... Saudi Arabia is currently in a transformation phase, which has resulted in a significant demand for healthcare services in the country’s healthcare system to provide better healthcare facilities for the fast-growing population and the growing elderly population. The lack of trained healthcare professionals and strong dependence on foreign labour are important aspects for policymakers to address, thus requiring Human Resource Development (HRD) initiatives to provide adequate learning and competence to a huge reserve of healthcare professionals in Saudi Arabia. In this regard, this paper contributes to Saudi Arabian health care by reporting healthcare professionals’ experiences of working in the Saudi health sector under the newly proposed Vision 2030 and NTP 2020 interventions in the HRD sphere of healthcare. The Vision 2030 is a testimony to a revolutionary step taken by the Government to reform the Saudi healthcare sector and provide HRD opportunities. 展开更多
关键词 Healthcare human Resource Development Saudization LOCALISATION vision 2030 NTP 2020
暂未订购
从生理之眼到赛博格之眼:图像技术进化与人类视觉未来
17
作者 于德山 《山东师范大学学报(社会科学版)》 北大核心 2025年第3期93-101,共9页
从图像技术进化论的角度分析,照相术与机械印刷术的发明促使人类图像技术进入新的阶段。其后百年之中,图像技术的器具化、机械化、自动化等特点不断强化,图像技术形成自我完备的进化系统,并与人类视觉的技术化发展交互在一起。当下,在... 从图像技术进化论的角度分析,照相术与机械印刷术的发明促使人类图像技术进入新的阶段。其后百年之中,图像技术的器具化、机械化、自动化等特点不断强化,图像技术形成自我完备的进化系统,并与人类视觉的技术化发展交互在一起。当下,在政策、商业与个体需求等因素的巨大驱动之下,图像技术在数字化的基础上不断向仿真化、器官化、智能化、多功能化与社交化等方向高速演进。各种图像新设备与新应用层出不穷并且快速换代更迭,人类的生理之眼有可能演进到赛博格之眼。由此,新型图像技术的发展促进了当代视觉文化传播的新一轮崛起,左右着人类视觉的未来。 展开更多
关键词 图像符号 图像技术特性 图像技术进化 赛博格之眼 人类视觉未来
在线阅读 下载PDF
基于多尺度与多级语义融合Transformer的人体姿态估计
18
作者 李俊 袁通达 陈黎 《武汉大学学报(理学版)》 北大核心 2025年第4期473-484,共12页
针对人体姿态估计任务中视觉Transformer模型存在的尺度多样性受限和近距离信息忽视问题,提出多尺度与多级语义融合Transformer(MMSF)模型。该模型通过引入关键点标记作为代理的交叉Transformer操作,实现了不同分辨率视觉信息的相互学习... 针对人体姿态估计任务中视觉Transformer模型存在的尺度多样性受限和近距离信息忽视问题,提出多尺度与多级语义融合Transformer(MMSF)模型。该模型通过引入关键点标记作为代理的交叉Transformer操作,实现了不同分辨率视觉信息的相互学习,提高了估计精度。同时,利用深度卷积和稠密连接复用标记技术,有效提取了含有多级语义信息的交叉标记,减少了编码器层堆叠,降低了模型复杂度。通过交叉标记与标准标记的交叉融合注意力操作,整合了多级语义信息,进一步增强了姿态估计效果。实验结果表明,在相同的条件下,MMSF模型在COCO数据集上达到了78.1%的平均精度,比TokenPose基准模型高2.3%;在MPII数据集上验证了其有效性,与近几年经典的基于Transformer的人体姿态估计方法相比取得了更好的性能。 展开更多
关键词 视觉Transformer 人体姿态估计 深度卷积 标记融合 交叉注意力
原文传递
多元视觉-语义联合嵌入的人-物交互检测网络
19
作者 吕学强 王晓英 +1 位作者 韩晶 陈玉忠 《计算机辅助设计与图形学学报》 北大核心 2025年第10期1811-1824,共14页
人-物交互检测对理解以人为中心的场景任务十分重要,但其因动词的一词多义带来的视觉偏差问题以及图像的层次信息和语义关系,面临难以合理利用的挑战.为此,提出多元视觉特征和语言先验联合嵌入的网络,设计了视觉-语义双分支结构.在视觉... 人-物交互检测对理解以人为中心的场景任务十分重要,但其因动词的一词多义带来的视觉偏差问题以及图像的层次信息和语义关系,面临难以合理利用的挑战.为此,提出多元视觉特征和语言先验联合嵌入的网络,设计了视觉-语义双分支结构.在视觉分支上,将人-物对中人、对象和交互的多元层次关系在层次视觉融合模块中进行丰富的上下文交换,增加用于关系推理的细粒度的上下文信息;在语义分支上,将交互三元组标签中的名词、交互动词和三元组短语联合编码成一个语义汇聚一致性图注意网络,进行信息传递和多义感知;最后通过视觉-语义联合嵌入模块计算视觉和语义之间的拟合程度,得到交互三元组的检测结果.实验结果表明,在V-COCO数据集上,代理平均精度达到70.7%,角色平均精度达到72.4%;在HICO-DET数据集上,默认场景下,完整类、罕见类和非罕见类的平均精度分别达到35.91%,33.65%和36.28%;所提网络优于对比的网络,在少样本和零样本情况下同样表现出色. 展开更多
关键词 人-物交互 语言先验 层次视觉 图注意力机制
在线阅读 下载PDF
基于人类视觉认知机制的表面缺陷检测 被引量:1
20
作者 崔丽莎 代润鹏 +3 位作者 姜晓恒 李飞蝶 陈恩庆 徐明亮 《浙江大学学报(理学版)》 北大核心 2025年第1期38-49,共12页
进行表面缺陷检测是确保产品性能、质量、美观度以及生产效率的重要手段。尽管人工智能在视觉检测领域取得了飞速发展,但基于生物视觉认知指导机器视觉学习的方法,仍是研究难点。提出了一种基于人类视觉认知机制的表面缺陷检测网络(HVCM... 进行表面缺陷检测是确保产品性能、质量、美观度以及生产效率的重要手段。尽管人工智能在视觉检测领域取得了飞速发展,但基于生物视觉认知指导机器视觉学习的方法,仍是研究难点。提出了一种基于人类视觉认知机制的表面缺陷检测网络(HVCM-Net)。在宏观层面,模拟视网膜上中央凹和中央凹外区域的工作原理,提出了中央视觉分支和外周视觉分支并行的骨干网络,分别负责学习缺陷图像的高空间频率局部细节信息和低空间频率全局语义信息。在微观层面,动态权重融合模块(DWFM)以自适应的方式融合两个分支的输出特征图,可学习和过滤更全面、准确和互补的缺陷特征。另外,融合分支引入特征保存下采样(FPD)模块,采用特征拼接技术,有效缓解了传统采样可能产生的微弱缺陷信息丢失问题。HVCM-Net在缺陷数据集GB-DET、NEU-DET和DAGM2007上取得了优于其他方法的检测性能,验证了其有效性。 展开更多
关键词 缺陷检测 人类视觉 中央视觉 外周视觉 特征融合
在线阅读 下载PDF
上一页 1 2 33 下一页 到第
使用帮助 返回顶部