本文關(guān)鍵詞： 馬鈴薯典型病害 Hough變換 主成分分析 加權(quán)融合 支持向量機(jī)　出處：《農(nóng)業(yè)機(jī)械學(xué)報(bào)》2017年12期 　論文類(lèi)型：期刊論文

【摘要】：針對(duì)自然條件下馬鈴薯典型病害區(qū)域定位和識(shí)別難的問(wèn)題,提出了一種馬鈴薯典型病害圖像的自適應(yīng)特征融合與快速識(shí)別方法。該方法利用K-means、Hough變換與超像素算法定位葉片,結(jié)合二維Otsu與形態(tài)學(xué)法分割病斑區(qū)域,通過(guò)病斑圖像顏色、形狀、紋理的自適應(yīng)主成分分析(PCA)特征加權(quán)融合,進(jìn)行支持向量機(jī)(SVM)病害識(shí)別。對(duì)3類(lèi)馬鈴薯典型病害圖像進(jìn)行識(shí)別試驗(yàn),結(jié)果表明:SVM識(shí)別模型下,自適應(yīng)特征融合方法相比PCA降維、特征排序選擇等傳統(tǒng)自適應(yīng)方法,平均識(shí)別率至少提高了1.8個(gè)百分點(diǎn);13個(gè)自適應(yīng)融合特征下,識(shí)別方法平均識(shí)別率為95.2%,比人工神經(jīng)網(wǎng)絡(luò)、貝葉斯分類(lèi)器提高了3.8個(gè)百分點(diǎn)和8.5個(gè)百分點(diǎn),運(yùn)行時(shí)間為0.600 s,比人工神經(jīng)網(wǎng)絡(luò)縮短3 s,可有效保證識(shí)別精度,大大加快了識(shí)別速度。
[Abstract]:An adaptive feature fusion and fast recognition method based on K-means-Hough transform and super-pixel algorithm is proposed to locate the leaves of potato typical diseases. Combining two-dimensional Otsu and morphological method to segment the disease spot region, the adaptive principal component analysis (PCA) method of image color, shape and texture is used for weighted fusion. Three kinds of typical potato disease images are identified by using support vector machine (SVM). The results show that the adaptive feature fusion method is better than the traditional adaptive methods such as PCA dimension reduction, feature ranking selection and so on. The average recognition rate is at least 1.8 percentage points higher than that of the artificial neural network, and the average recognition rate of 13 adaptive fusion features is 95.2 percentage points, which is 3.8 percentage points and 8.5 percentage points higher than that of the artificial neural network and Bayesian classifier. The operating time is 0.600 s, which is 3 s shorter than that of artificial neural network, which can effectively guarantee the recognition accuracy and greatly accelerate the recognition speed.
【作者單位】： 內(nèi)蒙古工業(yè)大學(xué)電力學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61661042) 內(nèi)蒙古自治區(qū)自然科學(xué)基金項(xiàng)目(2015MS0617)
【分類(lèi)號(hào)】：S435.32;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 盧弘斌;;馬鈴薯為什么會(huì)退化[J];農(nóng)業(yè)科學(xué)實(shí)驗(yàn);1978年07期

2 高志強(qiáng);王s，

本文編號(hào)：1552980