本文選題：SIFT描述子　切入點：詞袋模型BoW　出處：《南京財經大學》2016年碩士論文

【摘要】：電子商務的迅猛發(fā)展改變了人們傳統(tǒng)的購物習慣。然而,現(xiàn)有的利用分類搜索和關鍵字搜索的商品搜索技術,存在搜索結果量大而匹配精確度低的問題。本文以商品圖像搜索為研究焦點,重點研究了其核心問題-商品圖像的特征抽取和匹配問題。本文工作的主要貢獻是針對經典的尺度不變特征變換描述子SIFT(Scale Invariant Feature Transform),在應用于商品圖像識別中,存在的在較大仿射變換和視角變換的情況下,無法進行有效匹配的問題,提出了一種新的融合多視角的仿射不變描述子。該描述子首先將商品圖像進行模擬視角轉換,生成一組模擬視角圖像序列,然后檢測序列圖像的視覺特征,最后利用隨機抽樣一致算法RANSAC(Random Sample Consensus),將模擬視角圖像序列中的視覺特征映射到原始圖像中,共同構成原始圖像的特征點。本文還對傳統(tǒng)詞袋模型BoW(Bag-of-Words)中視覺詞典的構造方法和視覺特征的量化方法進行了改進。針對構造視覺詞典的傳統(tǒng)K-Means聚類算法存在的初始聚類中心的隨機選取,所導致的聚類結果不穩(wěn)定,且易存在局部極值點的問題,提出采用密度敏感相似性度量方法確定K-Means聚類算法的初始聚類中心;并針對傳統(tǒng)視覺特征量化采用硬量化方法HQ(Hard Quantization),而忽視了視覺特征與視覺單詞之間聯(lián)系的問題,提出采用軟量化方法SQ(Soft Quantization)方法進行視覺特征量化。用從淘淘搜、最美搜衣、唯品會等購物網站上抓取的13000幅服裝商品的圖像構造商品圖像數(shù)據(jù)庫,對本文提出的方法進行測試,并與采用梯度方向直方圖HOG(Histogram of Oriented Gradient),常規(guī)SIFT特征以及傳統(tǒng)BoW的方法進行比較,證明了本文提出的圖像特征提取算法和改進的BoW算法的有效性。
[Abstract]:The rapid development of electronic commerce has changed people's traditional shopping habits.However, the existing commodity search techniques using classified search and keyword search have the problem of large amount of search results and low matching accuracy.In this paper, we focus on commodity image search, and focus on the feature extraction and matching of commodity image.The main contribution of this paper is that the classical scale-invariant feature transform descriptor SIFT(Scale Invariant Feature transform can not match effectively when it is applied to commodity image recognition under the condition of large affine transformation and angle of view transformation.A new affine invariant descriptor is proposed.The descriptor first transforms the commodity image into a set of simulated visual angle images, and then detects the visual features of the sequence images.Finally, a random sampling algorithm, RANSAC(Random Sample Consensusn, is used to map the visual features of the simulated visual angle image sequence to the original image, so as to form the feature points of the original image.This paper also improves the method of constructing visual dictionaries and quantifying visual features in the traditional word bag model BoW-Bag-of-Words'.According to the random selection of the initial clustering center in the traditional K-Means clustering algorithm, the clustering results are unstable and the problem of local extremum is easy to exist.The initial clustering center of K-Means clustering algorithm is determined by using density-sensitive similarity measure, and HQ(Hard quantization method is used for traditional visual feature quantization, which neglects the connection between visual features and visual words.A soft quantization method (SQ(Soft quantization) is proposed for visual feature quantization.Using the images of 13000 clothing items seized on shopping websites such as Amoy search, most Beautiful clothing search, VIPSHOP and so on, to construct a commodity image database, and to test the methods proposed in this paper.Compared with the methods of HOG(Histogram of Oriented gradient histogram, conventional SIFT features and traditional BoW, the effectiveness of the proposed image feature extraction algorithm and the improved BoW algorithm is proved.
【學位授予單位】：南京財經大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP391.41

【相似文獻】

相關期刊論文 前10條

1 李瑞帥;余淑華;潘凱;王圓;;圖像特征金字塔快速計算方法[J];電子世界;2014年07期

2 曾喜良;王金娟;;指紋分割的塊圖像梯度因子聚類法[J];計算機與數(shù)字工程;2008年07期

3 劉陳;王欣欣;李鳳霞;趙相坤;;一種快速保邊的圖像對象分割方法[J];北京理工大學學報;2010年02期

4 朱薇;劉利剛;;圖像適應算法中非冗余顯著圖的計算[J];中國圖象圖形學報;2011年08期

5 柳有權;吳宗勝;韓紅雷;吳恩華;;線條增強的建筑物圖像抽象畫生成[J];計算機輔助設計與圖形學學報;2013年09期

6 吳駿,唐紅梅,肖志濤,賈志成;一種基于相位信息的圖像對稱性檢測方法[J];信號處理;2004年01期

7 邵靜;高雋;趙瑩;張旭東;;一種基于圖像固有維度的感知物體檢測方法[J];儀器儀表學報;2008年04期

8 潘如如;高衛(wèi)東;;高緊度機織物圖像傾斜的自動糾正[J];紡織學報;2009年10期

9 劉貴喜,趙曙光,楊萬海;基于梯度塔形分解的多傳感器圖像融合[J];光電子·激光;2001年03期

10 呂冀;高洪民;汪渤;周志強;;圖像制導的目標匹配算法與系統(tǒng)設計[J];彈箭與制導學報;2009年05期

相關會議論文 前5條

1 張一鳴;劉亞t，

本文編號：1711885