發(fā)布時間：2018-03-30 10:53

  本文選題：羊絨　切入點：羊毛　出處：《紡織學(xué)報》2017年12期

【摘要】：為解決羊絨與羊毛纖維圖像難以鑒別的問題,提出一種基于卷積網(wǎng)絡(luò)和深度學(xué)習(xí)理論的鑒別方法。使用sigmoid分類器將卷積深度網(wǎng)絡(luò)提取的纖維圖像特征進(jìn)行粗分類,根據(jù)驗證集合驗證結(jié)果并記錄網(wǎng)絡(luò)的最優(yōu)權(quán)重。根據(jù)整體的分類網(wǎng)絡(luò)所獲取的權(quán)值,對每張樣本圖片使用改進(jìn)的局部增強整體的網(wǎng)絡(luò)模型提取局部特征,并對局部特征和整體特征進(jìn)行融合,根據(jù)這些融合特征建立新的分類網(wǎng)絡(luò)。在此基礎(chǔ)上,使用鄂爾多斯標(biāo)準(zhǔn)羊絨與羊毛數(shù)據(jù)集對網(wǎng)絡(luò)進(jìn)行50輪次的迭代訓(xùn)練,得到的最優(yōu)準(zhǔn)確率達(dá)92.1%。實驗結(jié)果表明:采用深度卷積網(wǎng)絡(luò)表征纖維,并對羊絨羊與毛纖維圖像進(jìn)行分類的方法,能夠有效解決羊絨、羊毛等類似纖維鑒別問題;若用于商業(yè)檢測,還需更多數(shù)據(jù)集的驗證。
[Abstract]:In order to solve the problem that the image of cashmere and wool fiber is difficult to distinguish, a method based on convolution network and depth learning theory is proposed. The feature of fiber image extracted by convolution depth network is roughly classified by sigmoid classifier. According to the verification result of the verification set and the optimal weight of the network, according to the weights obtained by the whole classification network, the improved local enhancement global network model is used to extract the local features for each sample picture. Based on the fusion of local and global features, a new classification network is established. On this basis, 50 rounds of iterative training of the network are carried out by using the Ordos standard cashmere and wool data sets. The experimental results show that the method of using deep convolution network to characterize the fiber and classify the image of cashmere and wool fiber can effectively solve the problem of identifying similar fibers such as cashmere wool and so on. If used for commercial detection, more data sets need to be validated.
【作者單位】： 東華大學(xué)紡織學(xué)院;東華大學(xué)紡織面料技術(shù)教育部重點實驗室;
【分類號】：TP391.41;TS102.31
，

本文編號：1685608