本文關(guān)鍵詞： 隨機(jī)森林算法 服裝D人體 次B樣條 特征識別　出處：《北京服裝學(xué)院學(xué)報(bào)(自然科學(xué)版)》2017年03期 　論文類型：期刊論文

【摘要】：提出了一種基于隨機(jī)森林算法的3D人體特征識別算法.首先,利用bootsrap重抽樣從3D人體特征樣本中抽取多個樣本,并對每個bootsrap樣本進(jìn)行建模,生成一定數(shù)量的決策樹,在此基礎(chǔ)上組合多個決策樹的預(yù)測,通過投票預(yù)測特征點(diǎn),把投票比例最高的點(diǎn)作為特征點(diǎn).然后,利用3次B樣條對特征點(diǎn)進(jìn)行擬合得到3D掃描人體輪廓線,并測定人體尺寸數(shù)據(jù).最后,將測試結(jié)果與標(biāo)準(zhǔn)測量結(jié)果進(jìn)行比較,計(jì)算誤差值.仿真實(shí)驗(yàn)表明,該方法對不同的3D掃描人體模型具有良好的識別效果.
[Abstract]:A 3D human body feature recognition algorithm based on stochastic forest algorithm is proposed. Firstly, bootsrap re-sampling is used to extract multiple samples from 3D human feature samples. Each bootsrap sample is modeled to generate a certain number of decision trees. On this basis, the prediction of multiple decision trees is combined, and the feature points are predicted by voting. The points with the highest voting ratio are taken as feature points. Then, 3D scanning human body contour is obtained by fitting the feature points with three B-spline. Finally, the human body size data are measured. The error value is calculated by comparing the test results with the standard ones. The simulation results show that the method has a good recognition effect on different 3D scanned human models.
【作者單位】： 北京服裝學(xué)院信息工程學(xué)院;
【基金】：北京服裝學(xué)院創(chuàng)新項(xiàng)目(120301990122)
【分類號】：TP391.41
【正文快照】： 3D人體特征識別是數(shù)字化服裝研發(fā)過程中的一個關(guān)鍵環(huán)節(jié),數(shù)字化服裝研發(fā)的進(jìn)度與質(zhì)量直接決定于特征點(diǎn)識別的快速性和準(zhǔn)確性.虛擬現(xiàn)實(shí)和數(shù)字圖像處理等技術(shù)的發(fā)展,為3D人體特征的識別提供了理論依據(jù),如何準(zhǔn)確、快速、低成本地獲取3D掃描人體的特征數(shù)據(jù),成為當(dāng)前諸多學(xué)者和科研，

本文編號：1461433