期刊文献+
共找到392篇文章
< 1 2 20 >
每页显示 20 50 100
Silhouette内固定系统治疗胸腰段脊椎骨折 被引量:1
1
作者 贺石生 赵杰 侯铁胜 《中国脊柱脊髓杂志》 CAS CSCD 2001年第4期245-245,共1页
关键词 silhouette内固定系统 治疗 胸腰段脊椎骨折
下载PDF
基于shape from silhouette方法的虚拟人体构造 被引量:4
2
作者 沈军行 孙守迁 +1 位作者 黄琦 潘云鹤 《中国图象图形学报(A辑)》 CSCD 北大核心 2002年第10期1089-1093,共5页
逼真的人体三维模型 (虚拟人体 )在产品设计、计算机动画、虚拟现实等领域都有着广泛的需求 .为此 ,提出了一种基于 shape from silhouette的人体三维模型构造方法 .该方法所需要的器材只是一个普通的数码相机 ,通过从不同角度对人体进... 逼真的人体三维模型 (虚拟人体 )在产品设计、计算机动画、虚拟现实等领域都有着广泛的需求 .为此 ,提出了一种基于 shape from silhouette的人体三维模型构造方法 .该方法所需要的器材只是一个普通的数码相机 ,通过从不同角度对人体进行拍摄 ,然后经过摄像机定标、体积生成、表面重建、纹理映射后就可重建出逼真的人体三维模型 .实验结果表明 ,此方法精度较高 ,整个过程简单快捷 ,是一种非常实用的方法 . 展开更多
关键词 虚拟人体 三维重建 ShapeFromsilhouette 表面重建 纹理映射 计算机动画 人体三维模型 产品设计 虚拟现实
下载PDF
Silhouette内固定系统治疗脊椎骨折的疗效分析
3
作者 冉博 刘洪文 +2 位作者 张尊 毛洪刚 刘岩 《贵州医药》 CAS 2018年第9期1068-1070,共3页
目的探讨Silhouette内固定系统联合椎体内注入医用硫酸钙与椎弓根螺钉内固定术治疗脊椎骨折的临床疗效。方法选择胸腰椎骨折患者80例,随机分为观察者和对照组,各40例,对照组患者行传统切开椎弓根螺钉内固定术治疗,观察者患者行Silhouett... 目的探讨Silhouette内固定系统联合椎体内注入医用硫酸钙与椎弓根螺钉内固定术治疗脊椎骨折的临床疗效。方法选择胸腰椎骨折患者80例,随机分为观察者和对照组,各40例,对照组患者行传统切开椎弓根螺钉内固定术治疗,观察者患者行Silhouette内固定系统联合椎体内注入医用硫酸钙,术后常规治疗,并定期随访,比较两组患者围术期参数、Franke1分级、临床指标、临床疗效以及影像学差异。结果观察者患者手术时间、手术出血量、住院时间等围术期参数以及VAS评分均低于对照组(P<0.05);治疗后两组患者的Franke1分级均较治疗前优,且观察组明显优于对照组(P<0.05);治疗后两组患者椎管侵占率和Cobb角均有明显降低,伤椎前高压缩比明显升高(P<0.05);观察组患者NEER评分优良率明显高于对照组(P<0.05);术后观察组患者CSC吸收良好,椎体高度未见有变化,影像学表现相对优于对照组。结论与传统的椎弓根螺钉内固定术相比,椎体内注入医用硫酸钙联合Silhouette内固定系统治疗的患者影像学表现和临床疗效较好,值得临床推广使用。 展开更多
关键词 silhouette内固定系统 椎弓根螺钉内固定术 脊椎骨折
下载PDF
Investigation of Jacket Silhouette Based on Ease Distribution 被引量:1
4
作者 王朝晖 NG Roger NEWTON Edward 《Journal of Donghua University(English Edition)》 EI CAS 2014年第3期316-319,共4页
The silhouette of women's garment is diversified in its design. In this paper,a new model was developed to predict the silhouette of jacket for the given girth measurements. Sixty-three princess-seam women's j... The silhouette of women's garment is diversified in its design. In this paper,a new model was developed to predict the silhouette of jacket for the given girth measurements. Sixty-three princess-seam women's jackets with seven styles and nine girth dimensions of each style were produced. Their ease distribution was investigated at bustline,waistline,and hipline,respectively. The widths of the cross-sections for bustline,waistline,and hipline were formulated by multiple linear regressions. Then the silhouette was captured from the ratio of waist width to bust width of a designed jacket,together with that of waist width to hip width. 展开更多
关键词 GARMENT silhouette ease allowance ease distribution
下载PDF
Topology evolutions of silhouettes 被引量:1
5
作者 DAI Jun-fei KIM Junho +2 位作者 ZENG Hua-yi GU Xian-feng YAU Shing-tung 《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 SCIE EI CAS CSCD 2007年第10期1671-1680,共10页
We give the topology changing of the silhouette in 3D space while others study the projections in an image. Silhou- ettes play a crucial role in visualization, graphics and vision. This work focuses on the global beha... We give the topology changing of the silhouette in 3D space while others study the projections in an image. Silhou- ettes play a crucial role in visualization, graphics and vision. This work focuses on the global behaviors of silhouettes, especially their topological evolutions, such as splitting, merging, appearing and disappearing. The dynamics of silhouettes are governed by the topology, the curvature of the surface, and the view point. In this paper, we work on a more theoretical level to give enu- merative properties of the silhouette including: the integration of signed geodesic curvature along a silhouette is equal to the view cone angle; in elliptic regions, no silhouette can be contained in another one; in hyperbolic regions, if a silhouette is homotopic to a point, then it has at least 4 cusps; finally, critical events can only happen when the view point is on the aspect surfaces (ruled surface of the asymptotic lines of parabolic points with surface itself). We also introduce a method to visualize the evolution of silhouettes, especially all the critical events where the topologies of the silhouettes change. The results have broad applications in computer vision for recognition, graphics for rendering and visualization. 展开更多
关键词 Topological change silhouette Geodesic curvature CUSP
下载PDF
Panicle-3D: A low-cost 3D-modeling method for rice panicles based on deep learning, shape from silhouette, and supervoxel clustering 被引量:1
6
作者 Dan Wu Lejun Yu +10 位作者 Junli Ye Ruifang Zhai Lingfeng Duan Lingbo Liu Nai Wu Zedong Geng Jingbo Fu Chenglong Huang Shangbin Chen Qian Liu Wanneng Yang 《The Crop Journal》 SCIE CSCD 2022年第5期1386-1398,共13页
Self-occlusions are common in rice canopy images and strongly influence the calculation accuracies of panicle traits. Such interference can be largely eliminated if panicles are phenotyped at the 3 D level.Research on... Self-occlusions are common in rice canopy images and strongly influence the calculation accuracies of panicle traits. Such interference can be largely eliminated if panicles are phenotyped at the 3 D level.Research on 3 D panicle phenotyping has been limited. Given that existing 3 D modeling techniques do not focus on specified parts of a target object, an efficient method for panicle modeling of large numbers of rice plants is lacking. This paper presents an automatic and nondestructive method for 3 D panicle modeling. The proposed method integrates shoot rice reconstruction with shape from silhouette, 2 D panicle segmentation with a deep convolutional neural network, and 3 D panicle segmentation with ray tracing and supervoxel clustering. A multiview imaging system was built to acquire image sequences of rice canopies with an efficiency of approximately 4 min per rice plant. The execution time of panicle modeling per rice plant using 90 images was approximately 26 min. The outputs of the algorithm for a single rice plant are a shoot rice model, surface shoot rice model, panicle model, and surface panicle model, all represented by a list of spatial coordinates. The efficiency and performance were evaluated and compared with the classical structure-from-motion algorithm. The results demonstrated that the proposed method is well qualified to recover the 3 D shapes of rice panicles from multiview images and is readily adaptable to rice plants of diverse accessions and growth stages. The proposed algorithm is superior to the structure-from-motion method in terms of texture preservation and computational efficiency. The sample images and implementation of the algorithm are available online. This automatic, cost-efficient, and nondestructive method of 3 D panicle modeling may be applied to high-throughput 3 D phenotyping of large rice populations. 展开更多
关键词 Panicle phenotyping Deep convolutional neural network 3D reconstruction Shape from silhouette Point-cloud segmentation Ray tracing Supervoxel clustering
下载PDF
短节段Silhouette内固定结合BAK治疗腰椎滑脱症的体会
7
作者 耿桂平 赵杰 《实用骨科杂志》 2002年第5期368-369,共2页
关键词 短节段silhouette内固定 BAK 腰椎滑脱症 腰腿痛
下载PDF
IDENTIFICATION OF 3-D OBJECTS FROM THREE ORTHOGONAL SILHOUETTES USING NORMALIZED LINEAR QUAD-OCTREES
8
作者 张田文 李仲荣 《Journal of Electronics(China)》 1991年第1期52-59,共8页
Linear octrees offer a volume representation of 3-D objects, which is quite compactand lends itself to traditional object processing operations. However, the linear octree structurefor generating the representation of... Linear octrees offer a volume representation of 3-D objects, which is quite compactand lends itself to traditional object processing operations. However, the linear octree structurefor generating the representation of 3-D objects from three orthogonal silhouettes by using thevolume intersection technique is dependent on viewpoints. The recognition achieved from match-ing object representations to model representations requires that the representations of objectsare independent of viewpoints. In order to obtain independent representations of viewpoints,the three principal axes of the object should be obtained from the moment of inertia matrix bycomputing its eigenvectors. The linear octree is projected onto the image planes of the three prin-cipal views (along the principal axes) to obtain the three normalized linear quadtrees. The objectmatching procedure has two phases: the first phase is to match the normalized linear quadtrees ofthe unknown object to a subset of models contained in a library utilizing a measure of symmetricdifference; the second phase is to generate the normalized linear octrees of the object and theseselected models and then to match the normalized linear octree of the unknown object with themodel having the minimum symmetric difference. 展开更多
关键词 Normalized LINEAR quad-octree THREE ORTHOGONAL silhouetteS Principal axes Object matching Symmetric difference
下载PDF
Facial Asymmetry Correction in Facial Palsy Patients with Silhouette Sutures
9
作者 María Luisa Navarrete Ricard Palao +2 位作者 Lluisa Torrent Juan Fernando Fuentes Mireia González 《International Journal of Clinical Medicine》 2012年第1期55-59,共5页
Introduction: over the last few decades several techniques static and dynamics, have been performed to improve facial asymmetry and functionality alter suffering facial paralysis. Methods: we present a pilot study to ... Introduction: over the last few decades several techniques static and dynamics, have been performed to improve facial asymmetry and functionality alter suffering facial paralysis. Methods: we present a pilot study to show and evaluate the benefits of a new form of facial suspension, with Silhouette sutures. We performed two patients with total and complete facial palsy due to otical tuberculosis in one case and to parotid carcinoma in the other. Results: one year after surgery, both patients have improved facial asymmetry, mastication and speech production which have lead to a higher self-esteem and major social interaction. Conclusions: static facial suspension with Silhouette sutures is a non invasive alternative to dynamic techniques in patients who don’t want or can’t undergo more complex surgeries. 展开更多
关键词 FACIAL PARALYSIS SUTURE SUSPENSION Static Technique silhouette SUTURES
下载PDF
View-invariant Gait Authentication Based on Silhouette Contours Analysis and View Estimation 被引量:1
10
作者 Songmin Jia Lijia Wang Xiuzhi Li 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI 2015年第2期226-232,共7页
In this paper, we propose a novel view-invariant gait authentication method based on silhouette contours analysis and view estimation. The approach extracts Lucas-Kanade based gait flow image and head and shoulder mea... In this paper, we propose a novel view-invariant gait authentication method based on silhouette contours analysis and view estimation. The approach extracts Lucas-Kanade based gait flow image and head and shoulder mean shape (LKGFI-HSMS) of a human by using the Lucas-Kanade0s method and procrustes shape analysis (PSA). LKGFI-HSMS can preserve the dynamic and static features of a gait sequence. The view between a person and a camera is identified for selecting the target's gait feature to overcome view variations. The similarity scores of LKGFI and HSMS are calculated. The product rule combines the two similarity scores to further improve the discrimination power of extracted features. Experimental results demonstrate that the proposed approach is robust to view variations and has a high authentication rate. © 2014 Chinese Association of Automation. 展开更多
关键词 AUTHENTICATION Gait analysis Image analysis Rapid thermal annealing
下载PDF
Papercut Silhouette A Treasure of Chinese Folk Art
11
《China & The World Cultural Exchange》 1994年第5期38-39,共2页
关键词 Papercut silhouette A Treasure of Chinese Folk Art
下载PDF
跳跃跟踪SSA交叉迭代AP聚类算法
12
作者 黄鹤 李文龙 +3 位作者 杨澜 王会峰 高涛 陈婷 《电子学报》 EI CAS CSCD 北大核心 2024年第3期977-990,共14页
针对传统近邻传播聚类算法以数据点对之间的相似度作为输入度量,由于需要预设偏向参数p和阻尼系数λ,算法精度无法精确控制的问题,提出了一种跳跃跟踪麻雀搜索算法优化的交叉迭代近邻传播聚类方法.首先,针对麻雀搜索算法中发现者和加入... 针对传统近邻传播聚类算法以数据点对之间的相似度作为输入度量,由于需要预设偏向参数p和阻尼系数λ,算法精度无法精确控制的问题,提出了一种跳跃跟踪麻雀搜索算法优化的交叉迭代近邻传播聚类方法.首先,针对麻雀搜索算法中发现者和加入者位置更新不足的问题,设计了一种跳跃跟踪优化策略,通过考虑偏好阻尼因子的跳跃策略设计大步长更新发现者,增加麻雀搜索算法的全局勘探能力和寻优速度,加入者设计动态小步长跟踪领头雀更新位置,同时,利用自适应种群划分机制更新发现者和加入者的比重,增加算法的后期局部开发能力和寻优速度;其次,设计基于扰动因子的Tent映射,在此基础上增加3个参数,使映射分布范围增大,并避免了陷入小周期点和不稳周期点;最后,引入轮廓系数作为评价函数,跳跃跟踪麻雀搜索算法自动寻找较优的p和λ,代替手动输入参数,并融合基于扰动因子的Tent映射优化近邻传播算法,交叉迭代确定最优簇数.使用多种算法聚类University of California Irvine数据集的10种公共数据集,仿真结果表明,本文提出的聚类算法与经典近邻传播算法、基于差分改进的仿射传播聚类算法、基于麻雀搜索算法优化的近邻传播聚类算法和进化近邻传播算法相比具有更优的搜索效率以及聚类精度.对国家信息数据进行了聚类分析,提出的方法更加准确有效合理,具有较好的应用价值. 展开更多
关键词 近邻传播聚类 改进Tent映射 改进麻雀搜索算法 轮廓系数 聚类数据集
下载PDF
基于改进K-means算法的物流配送中心选址研究 被引量:1
13
作者 姚佼 吴秀荣 +3 位作者 李皓 谢贝贝 王诗璇 梁益铭 《物流科技》 2024年第5期10-13,19,共5页
针对传统K-means算法需要主观设定K值及无法处理类别型数据问题,文章运用肘部法及轮廓系数法确定合理K值,对类别型数据采取独热编码(One-Hot Encoding)转换为可以处理的连续型数据,并将其运用到在物流配送中心选址中;并综合考虑多种类... 针对传统K-means算法需要主观设定K值及无法处理类别型数据问题,文章运用肘部法及轮廓系数法确定合理K值,对类别型数据采取独热编码(One-Hot Encoding)转换为可以处理的连续型数据,并将其运用到在物流配送中心选址中;并综合考虑多种类别的影响因素,构建了相应的影响因素指标体系,提出的模型能够识别输入数据的数值型及类别型数据,实现样本的有效聚类。相关的案例分析结果表明,相比传统K-means聚类,文章的改进K-means算法选址结果可使物流总成本降低8.76%,运营成本降低14.85%,固定成本降低8.09%,效果显著。 展开更多
关键词 物流配送中心选址 K-MEANS聚类算法 肘部法 轮廓系数法 独热编码
下载PDF
基于自适应LTTB与DTW-DBA-Means的动力电池组不一致性评估方法
14
作者 吴凤和 柴海宁 +4 位作者 章正柱 张宁 王正明 蒋展鹏 郭保苏 《计量学报》 CSCD 北大核心 2024年第6期890-898,共9页
针对电动汽车动力电池组不一致性难以通过外部参数有效评估问题,在对电池组电压数据进行分析时,引入轮廓系数作为不一致性评价指标,并融合自适应降采样(LTTB)与时序聚类(DTW-DBA-Means)算法,提出一种新的动力电池组不一致性评估方法。... 针对电动汽车动力电池组不一致性难以通过外部参数有效评估问题,在对电池组电压数据进行分析时,引入轮廓系数作为不一致性评价指标,并融合自适应降采样(LTTB)与时序聚类(DTW-DBA-Means)算法,提出一种新的动力电池组不一致性评估方法。自适应LTTB能够根据电池组电压序列特点自适应分配压缩区间采样点数目并调整压缩比,可提高DTW-DBA-Means运算效率的同时保证聚类效果。通过运行9个月的实车数据进行实验验证,结果表明,自适应LTTB降采样效果优于动态LTTB与LTTB,且DTW-DBA-Means时序聚类效果优于k-Shape,所提方法在保证评估准确性同时可节省约96.7%的运算时间。 展开更多
关键词 电学计量 动力电池组 不一致性评估 轮廓系数 降采样 时序数据聚类
下载PDF
贝叶斯优化模糊聚类地级行政区声环境
15
作者 曾宇 姚琨 +1 位作者 任爽 户文成 《应用声学》 CSCD 北大核心 2024年第2期385-392,共8页
声环境功能区划是噪声污染管理的重要手段。当前声环境功能区划研究大多是基于某个特定的地级行政区来进行的,难以反映各地级行政区声环境的异同。该文基于134个地级行政区的人口、面积、各声环境功能区面积和及面积占比,进行地级行政... 声环境功能区划是噪声污染管理的重要手段。当前声环境功能区划研究大多是基于某个特定的地级行政区来进行的,难以反映各地级行政区声环境的异同。该文基于134个地级行政区的人口、面积、各声环境功能区面积和及面积占比,进行地级行政区声环境表征和归一化处理。以轮廓系数作为聚类有效性评价指标,基于贝叶斯优化模糊聚类方法对地级行政区声环境表征进行聚类分析。通过与谱聚类、K-medoids聚类、高斯混合模型聚类的聚类性能对比,验证了该方法的有效性。结果表明,我国地级行政区声环境分为9类,城市规模和用地情况发生显著变化导致其声环境表征和归类发生变化后应重新评估当前噪声污染管理政策,并借鉴同类的地级行政区的噪声污染管理政策做出必要的调整。 展开更多
关键词 声环境功能区 地级行政区 模糊聚类 贝叶斯优化 轮廓系数
下载PDF
一种基于轮廓稀疏对抗的视频步态隐私保护算法
16
作者 许可 李嘉怡 +1 位作者 蒋兴浩 孙锬锋 《信息网络安全》 CSCD 北大核心 2024年第1期48-59,共12页
深度网络模型可以从视频步态序列中获取人体步态生物特征并识别人物身份,造成严重的隐私泄露安全威胁。现有方法一般通过对视频画面中的人体进行模糊、变形等处理来保护隐私,这些方法可以在一定程度上改变人体外观,但很难改变人物行走姿... 深度网络模型可以从视频步态序列中获取人体步态生物特征并识别人物身份,造成严重的隐私泄露安全威胁。现有方法一般通过对视频画面中的人体进行模糊、变形等处理来保护隐私,这些方法可以在一定程度上改变人体外观,但很难改变人物行走姿态,难以逃避深度网络模型的识别,且这种处理往往伴随着对视频质量的严重破坏,降低了视频的视觉可用性。针对该问题,文章提出一种基于轮廓稀疏对抗的视频步态隐私保护算法,通过对步态识别模型的对抗攻击来计算画面中人体轮廓周围的有效修改位置。与传统方法相比,在具有相同隐私保护能力的情况下,该算法减少了对画面的修改,在隐私安全性和视觉可用性上达到了较好的均衡。该算法在公开步态数据库CASIA-B和OUMVLP上对4种步态识别模型进行测试,通过与不同步态隐私保护方法对比,验证了该算法在步态隐私保护上的有效性和可用性。 展开更多
关键词 步态隐私保护 步态识别 轮廓稀疏对抗 对抗样本
下载PDF
An Imbalanced Data Classification Method Based on Hybrid Resampling and Fine Cost Sensitive Support Vector Machine 被引量:1
17
作者 Bo Zhu Xiaona Jing +1 位作者 Lan Qiu Runbo Li 《Computers, Materials & Continua》 SCIE EI 2024年第6期3977-3999,共23页
When building a classification model,the scenario where the samples of one class are significantly more than those of the other class is called data imbalance.Data imbalance causes the trained classification model to ... When building a classification model,the scenario where the samples of one class are significantly more than those of the other class is called data imbalance.Data imbalance causes the trained classification model to be in favor of the majority class(usually defined as the negative class),which may do harm to the accuracy of the minority class(usually defined as the positive class),and then lead to poor overall performance of the model.A method called MSHR-FCSSVM for solving imbalanced data classification is proposed in this article,which is based on a new hybrid resampling approach(MSHR)and a new fine cost-sensitive support vector machine(CS-SVM)classifier(FCSSVM).The MSHR measures the separability of each negative sample through its Silhouette value calculated by Mahalanobis distance between samples,based on which,the so-called pseudo-negative samples are screened out to generate new positive samples(over-sampling step)through linear interpolation and are deleted finally(under-sampling step).This approach replaces pseudo-negative samples with generated new positive samples one by one to clear up the inter-class overlap on the borderline,without changing the overall scale of the dataset.The FCSSVM is an improved version of the traditional CS-SVM.It considers influences of both the imbalance of sample number and the class distribution on classification simultaneously,and through finely tuning the class cost weights by using the efficient optimization algorithm based on the physical phenomenon of rime-ice(RIME)algorithm with cross-validation accuracy as the fitness function to accurately adjust the classification borderline.To verify the effectiveness of the proposed method,a series of experiments are carried out based on 20 imbalanced datasets including both mildly and extremely imbalanced datasets.The experimental results show that the MSHR-FCSSVM method performs better than the methods for comparison in most cases,and both the MSHR and the FCSSVM played significant roles. 展开更多
关键词 Imbalanced data classification silhouette value Mahalanobis distance RIME algorithm CS-SVM
下载PDF
融合轮廓增强和注意力机制的改进GaitSet步态识别方法 被引量:1
18
作者 陈万志 唐浩博 王天元 《电子测量与仪器学报》 CSCD 北大核心 2024年第1期203-210,共8页
针对传统基于轮廓的步态识别方法受限于输入特征及模型特征提取的能力,从而导致识别准确率不高的问题,提出一种融合轮廓增强和注意力机制的改进GaitSet步态识别方法。首先通过预处理获取行人的轮廓图,求得其均值,合成步态GEI能量图,将... 针对传统基于轮廓的步态识别方法受限于输入特征及模型特征提取的能力,从而导致识别准确率不高的问题,提出一种融合轮廓增强和注意力机制的改进GaitSet步态识别方法。首先通过预处理获取行人的轮廓图,求得其均值,合成步态GEI能量图,将其作为神经网络模型的输入特征,增强了人体外观的表示。其次在提取特征的过程中引入注意力机制,增强模型的特征提取能力,从而提高步态识别的精度。最后在CASIA-B和OU-MVLP数据集上进行实验,所提方法的平均Rank-1准确率分别为87.7%和88.1%。特别是在最复杂的穿大衣行走条件下,相较于GaitSetv2算法,准确率提升了6.7%,表明所提出方法具有更强的准确性。此外,所提方法几乎没有增加额外的参数量、计算复杂度和推理时间,说明其各模块的快速性。 展开更多
关键词 步态识别 交叉视角 深度学习 轮廓增强 注意力机制
下载PDF
基于Vision Transformer与迁移学习的裤装廓形识别与分类
19
作者 应欣 张宁 申思 《丝绸》 CAS CSCD 北大核心 2024年第11期77-83,共7页
针对裤装廓形识别与分类模型的分类不准确问题,文章采用带有自注意力机制的Vision Transformer模型实现裤装廓形图像的分类,对于图片背景等无关信息对廓形识别的干扰,添加自注意力机制,增强有用特征通道。为防止因裤型样本数据集较少产... 针对裤装廓形识别与分类模型的分类不准确问题,文章采用带有自注意力机制的Vision Transformer模型实现裤装廓形图像的分类,对于图片背景等无关信息对廓形识别的干扰,添加自注意力机制,增强有用特征通道。为防止因裤型样本数据集较少产生过拟合问题,可通过迁移学习方法对阔腿裤、喇叭裤、紧身裤、哈伦裤4种裤装廓形进行训练和验证,将改进的Vision Transformer模型与传统CNN模型进行对比实验,验证模型效果。实验结果表明:使用Vision Transformer模型在4种裤装廓形分类上的分类准确率达到97.72%,与ResNet-50和MobileNetV2模型相比均有提升,可为服装廓形的图像分类识别提供有力支撑,在实际服装领域中有较高的使用价值。 展开更多
关键词 裤装廓形 自注意力机制 Vision transformer 迁移学习 图像分类 廓形识别
下载PDF
基于关键点检测的服装廓形识别
20
作者 陶金之 夏明 王伟 《纺织学报》 EI CAS CSCD 北大核心 2024年第6期142-148,共7页
为精准且快速地实现对服装廓形的判断,以秀场连衣裙为研究对象,提出了基于关键点检测的服装廓形分类算法。使用YOLO v8-Pose模型对秀场连衣裙进行关键点检测,提取服装的肩部、胸部、腰部、臀部和底摆两侧共10个关键点,并生成服装廓形图... 为精准且快速地实现对服装廓形的判断,以秀场连衣裙为研究对象,提出了基于关键点检测的服装廓形分类算法。使用YOLO v8-Pose模型对秀场连衣裙进行关键点检测,提取服装的肩部、胸部、腰部、臀部和底摆两侧共10个关键点,并生成服装廓形图。通过加入Sobel边缘提取算法改进的DenseNet网络深度提取服装廓形特征,采用余弦相似度算法将其与标准的廓形库中提取的特征相比较,最终实现服装廓形的判别与分类。结果表明,该方法能够快速且准确地实现服装廓形的分类,廓形分类准确率达到了95.9%。 展开更多
关键词 服装 廓形分类 YOLO v8-Pose 关键点检测 DenseNet网络 相似度算法 连衣裙
下载PDF
上一页 1 2 20 下一页 到第
使用帮助 返回顶部