本文關(guān)鍵詞：植物圖像識(shí)別方法研究及實(shí)現(xiàn)　出處：《浙江大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 藥用植物 微差圖像 圖像識(shí)別 深度學(xué)習(xí) 卷積神經(jīng)網(wǎng)絡(luò) 特征提取

【摘要】：圖像識(shí)別技術(shù)目前廣泛應(yīng)用于傳統(tǒng)制造業(yè)、安保以及互聯(lián)網(wǎng)行業(yè),相關(guān)方法都較為成熟。但是,在生物、醫(yī)學(xué)以及食品等領(lǐng)域上還有很多空白需要填補(bǔ),主要在于現(xiàn)在的識(shí)別方法往往面向"大"類別識(shí)別,例如區(qū)分貓和狗、人和車輛、動(dòng)物和植物等,并非細(xì)粒度(微差)圖像識(shí)別的范疇,例如同為菊科下的秋菊和野菊的識(shí)別。本文針對(duì)微差圖像識(shí)別領(lǐng)域中的植物圖像識(shí)別進(jìn)行了方法研究,主要工作如下:1.從圖像底層特征入手,重點(diǎn)研究了 BoV和費(fèi)雪向量特征編碼方法,提出了基于費(fèi)雪向量的多特征融合圖像識(shí)別方案。實(shí)驗(yàn)表明,在植物圖像識(shí)別應(yīng)用中,基于費(fèi)雪向量的特征編碼方案具有更好的效果。2.從深度學(xué)習(xí)方法入手,首先設(shè)置對(duì)比實(shí)驗(yàn)進(jìn)行模型初選,研究分析不同訓(xùn)練模式以及卷積神經(jīng)網(wǎng)絡(luò)深度對(duì)植物圖像識(shí)別的影響;其次提出了基于選擇性搜索算法的植物圖像關(guān)鍵區(qū)域生成方法;最后提出了面向關(guān)鍵區(qū)域的基于VGGNet16的植物圖像識(shí)別模型,并驗(yàn)證了本文提出方法的有效性。3.構(gòu)建植物圖像數(shù)據(jù)集。數(shù)據(jù)庫的構(gòu)建包含兩部分,一是面向圖像識(shí)別的公開數(shù)據(jù)集,用于方法的橫向比較;二是自建的植物領(lǐng)域圖像數(shù)據(jù)集,并在該數(shù)據(jù)集的基礎(chǔ)上構(gòu)建了常用藥用植物圖像集,用于驗(yàn)證方法的實(shí)用性。并將本文所提方法在數(shù)據(jù)集上進(jìn)行實(shí)驗(yàn)。4.設(shè)計(jì)和實(shí)現(xiàn)藥用植物圖像識(shí)別系統(tǒng)。系統(tǒng)利用本文提出的具有較好效果的方法,在此基礎(chǔ)上,設(shè)計(jì)了中間結(jié)果和最終結(jié)果的用戶反饋機(jī)制,用以提高系統(tǒng)的圖像識(shí)別準(zhǔn)確率。
[Abstract]:Image recognition technology has been widely used in traditional manufacturing, security and Internet industries. However, there are still many gaps to be filled in biology, medicine and food. This is mainly due to the fact that current recognition methods are often oriented towards "large" category recognition, such as distinguishing between cats and dogs, humans and vehicles, animals and plants, and is not a category of fine-grained (micro-differential) image recognition. In this paper, the method of plant image recognition in the field of differential image recognition is studied. The main work is as follows: 1. Starting from the bottom features of the image. The method of BoV and Fisher vector feature coding is studied emphatically, and a multi-feature fusion image recognition scheme based on Fisher vector is proposed. The experimental results show that it is applied in plant image recognition. The feature coding scheme based on Fisher vector has a better effect. 2. Starting with the depth learning method, we first set up a comparative experiment to select the model. The effects of different training modes and the depth of convolution neural network on plant image recognition were studied. Secondly, based on the selective search algorithm, the key region generation method of plant image is proposed. Finally, a plant image recognition model based on VGGNet16 for key regions is proposed. The validity of the proposed method is verified. 3. The construction of plant image data set. The construction of database consists of two parts: one is the open data set for image recognition, which is used for the horizontal comparison of methods; Secondly, the image data set of plant domain was built, and the common medicinal plant image set was constructed on the basis of the data set. This method is used to verify the practicability of the method. The method proposed in this paper is tested on the data set. 4. The design and implementation of medicinal plant image recognition system. The system uses the method proposed in this paper with better results. On this basis, the user feedback mechanism of intermediate and final results is designed to improve the accuracy of image recognition.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 嵇朋朋;閆勝業(yè);李林;劉青山;;基于區(qū)域非均勻空間采樣特征的圖像分類方法[J];電子與信息學(xué)報(bào);2014年11期

2 劉俊梅;;基于小波變換的圖像紋理特征提取技術(shù)[J];計(jì)算機(jī)工程與設(shè)計(jì);2007年13期

相關(guān)碩士學(xué)位論文 前2條

1 譚亮;基于內(nèi)容的中草藥圖像檢索關(guān)鍵技術(shù)研究[D];浙江大學(xué);2016年

2 任曉琳;植物圖像檢索系統(tǒng)的關(guān)鍵技術(shù)研究與實(shí)現(xiàn)[D];浙江大學(xué);2015年

，

本文編號(hào)：1403668