本文選題：深度學(xué)習(xí) + 卷積神經(jīng)網(wǎng)絡(luò)�。� 參考：《北方民族大學(xué)》2017年碩士論文

【摘要】：三維模型的數(shù)量在最近10年間呈現(xiàn)出幾何級增長的態(tài)勢。如何對數(shù)量龐大的三維模型進(jìn)行處理、分析和理解,已經(jīng)成為數(shù)字幾何領(lǐng)域研究的焦點(diǎn)。而其中的基礎(chǔ)問題則是三維形狀的分類。傳統(tǒng)的分類方式把人工設(shè)計的三維特征用于分類,其方法的優(yōu)劣完全取決于專家對三維模型及其分類目標(biāo)的理解和把握。存在主觀性強(qiáng)、分類精度低的問題。不同于傳統(tǒng)的方法,深度學(xué)習(xí)算法能夠讓機(jī)器自動學(xué)習(xí)特征及分類,近年來在圖像領(lǐng)域有著優(yōu)異的表現(xiàn)。視圖作為模型的直觀信息,符合人類的視覺系統(tǒng),可以作為深度學(xué)習(xí)的輸入信息。本文擬結(jié)合深度學(xué)習(xí)和視圖對三維CAD模型的分類問題進(jìn)行研究:首先進(jìn)行三維模型視圖提取;之后結(jié)合深度學(xué)習(xí)理論,給出深層神經(jīng)網(wǎng)絡(luò)的構(gòu)建方法;在應(yīng)用環(huán)節(jié),給出分類過程與結(jié)果。主要研究工作如下:⑴三維模型的視圖生成視圖是三維模型的描述信息,本文以視圖作為深度學(xué)習(xí)模型的輸入。視圖的數(shù)量以及獲取視圖的角度都會對最終分類結(jié)果有影響。光場描述符提取的視圖存在大量的冗余,而最簡單的三視圖卻會存在丟失模型空間信息的問題,我們需要研究合適的視圖獲取方法。本文利用兩種視圖提取技術(shù)得到混合視圖,輸入到深度學(xué)習(xí)模型。用以提高分類的精確度。⑵構(gòu)建深度卷積神經(jīng)網(wǎng)絡(luò)由于卷積神經(jīng)網(wǎng)絡(luò)在圖像處理方面具有極高的處理能力,所以本文使用了深度學(xué)習(xí)里的深度卷積神經(jīng)網(wǎng)絡(luò)。構(gòu)建的深層網(wǎng)絡(luò)分類器由多層組成:輸入層、若干隱藏層和輸出層。將提取出來的視圖作為輸入,由若干隱層來提取和合成更加抽象的概念特征,輸出層用來輸出模型所屬的類別。⑶輸出層分類器的選擇卷積神經(jīng)網(wǎng)絡(luò)的最后一層是輸出層。輸出層分類器一般選擇Logistic回歸或SoftMax回歸。Logistic回歸用來解決二分類問題,而CAD模型數(shù)據(jù)庫不止兩個類,SoftMax回歸模型是在多分類問題上的應(yīng)用,故而本文采用了SoftMax回歸模型。
[Abstract]:The number of 3D models has shown a geometric growth trend in the last 10 years. How to deal with, analyze and understand a large number of 3D models has become the focus of research in the field of digital geometry. The basic problem is the classification of three-dimensional shapes. The traditional classification method uses the artificially designed 3D feature to classify, and the advantages and disadvantages of the method depend on the experts' understanding and grasp of the 3D model and its classification target. There is the problem of strong subjectivity and low classification accuracy. Unlike the traditional methods, the depth learning algorithm can make the machine learn features and classification automatically, and it has excellent performance in the field of image in recent years. As visual information of model, view accords with human visual system and can be used as input information for deep learning. In this paper, the classification of 3D CAD model is studied in combination with depth learning and view: firstly, 3D model view extraction is carried out; then, combined with depth learning theory, the construction method of deep neural network is given. The classification process and results are given. The main research work is as follows: the view generation view of the 1: 1 3D model is the description information of the 3D model. In this paper, the view is used as the input of the depth learning model. The number of views and the angle at which they are obtained will have an impact on the final classification results. The view extracted by the light field descriptor has a lot of redundancy while the simplest three views have the problem of losing model space information. We need to study the appropriate view acquisition method. In this paper, we use two view extraction techniques to get the mixed view and input it into the depth learning model. In order to improve the accuracy of classification, the deep convolution neural network is constructed. Because the convolution neural network has very high processing ability in image processing, this paper uses the deep convolution neural network in depth learning. The constructed deep network classifier consists of several layers: input layer, hidden layer and output layer. The extracted view is used as input to extract and synthesize more abstract conceptual features by a number of hidden layers. The output layer is used to output the selected convolutional neural network of the class .3 output layer classifier to which the model belongs. The last layer of the output layer is the output layer. Output level classifiers generally choose Logistic regression or SoftMax regression. Logistic regression to solve the two-classification problem, and CAD model database more than two classes of SoftMax regression model is used in multi-classification problems, so this paper uses SoftMax regression model.
【學(xué)位授予單位】：北方民族大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.72

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 Fei-wei QIN;Lu-ye LI;Shu-ming GAO;Xiao-ling YANG;Xiang CHEN;;A deep learning approach to the classification of 3D CAD models[J];Journal of Zhejiang University-Science C(Computers & Electronics);2014年02期

2 孫志軍;薛磊;許陽明;王正;;深度學(xué)習(xí)研究綜述[J];計算機(jī)應(yīng)用研究;2012年08期

3 林佼;李重;金小剛;李亮;;基于凸殼與有向包圍盒的骨架提取方法[J];計算機(jī)輔助設(shè)計與圖形學(xué)學(xué)報;2012年06期

相關(guān)博士學(xué)位論文 前1條

1 李朋杰;面向三維模型檢索的特征提取算法研究[D];北京郵電大學(xué);2013年

相關(guān)碩士學(xué)位論文 前2條

1 劉鈺鵬;基于深度學(xué)習(xí)的三維CAD模型分類[D];北方民族大學(xué);2016年

2 楊冬蕾;針對圖像特征提取算法的并行加速研究[D];復(fù)旦大學(xué);2013年

，

本文編號：1960669