基於卷積神經網路特徵之餐廳影像分類系統;Multiclass restaurant image classification based on Convolutional Neural Networks

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/81113

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/81113

题名:	基於卷積神經網路特徵之餐廳影像分類系統;Multiclass restaurant image classification based on Convolutional Neural Networks
作者:	趙永霖;Chao, Yung-Lin
贡献者:	資訊工程學系
关键词:	機器學習;卷積神經網路;Inception;主成分分析(PCA);支持向量機 (;Machine learning;Convolutional nerual network;Inception;Principal components analysis(PCA);Support vector machine(SVM)
日期:	2019-07-23
上传时间:	2019-09-03 15:35:01 (UTC+8)
出版者:	國立中央大學
摘要:	人工智慧與深度學習現今已被廣泛使用在各個領域，無論是影像辨識、電子商業，亦或是新興媒體產業等，其效能也遠遠高於以往之傳統處理方式。現今網路世界，各個餐廳往往會將餐廳照片放置網路，以供大眾參考，或是網美們會將去過的餐廳分享至 Instagram 、 Facebook 等社群軟體，但照片內容琳瑯滿目，沒有重點。所以我們想設計一個應用介面，能將雜亂的圖片做適當的分類，讓使用者一目了然。本論文使用卷積神經網路 VGG16 及 Inception ，配合 PCA Principal components analysis 的降維，將雜亂的圖片簡單分為五類食物、菜單、室內場景、室外場景、其他，以 I magenet 作為預訓練模型，再將從 G oogle map 抓取之 90 000 張各式餐廳場景圖片當作訓練資料，擷取之全連接 6 層之特徵經過 PCA 降維處理後輸入進 SVM support vector machine 做分類，得到最後之分類結果。;Artificial intelligence and deep learning are now widely used in various fields, For example,image recognition, electronic commerce, or the new media industry... its performance is much higher than the traditional way. In today′s online world, restaurants often place photos of restaurants on the Internet for public reference, or Internet celebrities will share the restaurants they have visited to social media such as Instagram and Facebook, but the photos are dazzling and unfocused. So we want to design an application that can properly classify cluttered images for the user to see at a glance. This paper uses convolutional neural network-Inception, combined with PCA′s dimensionality reduction, to divide the messy pictures into five categories: food, menu, indoor scene, outdoor scene, and others. Imagenet is used as the Pretrain model, and then from Google map. The 93,000 pictures of various restaurant scenes were used as training data. The features of the Global Pooling layer captured by the PCA were inputted to the SVM for classification and the final classification result was obtained.
显示于类别:	[資訊工程研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	181	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....