發(fā)布時間：2018-03-28 15:09

  本文選題：服裝檢索　切入點：服裝搭配　出處：《電子科技大學(xué)》2017年碩士論文

【摘要】：隨著服裝電子商務(wù)的發(fā)展和大數(shù)據(jù)時代的來臨,互聯(lián)網(wǎng)上存儲著海量的服裝數(shù)據(jù),用戶對服裝檢索和搭配的需求也日益增加。幫助用戶快速精確的找到心儀的服裝,并且推薦合適的搭配方案,是服裝電商平臺提升用戶體驗和銷量的重要手段。正因如此,對服裝檢索和搭配技術(shù)的研究就變得十分有意義。服裝檢索和搭配技術(shù)都依賴于對服裝圖像內(nèi)容信息的理解,這種理解就轉(zhuǎn)化為對服裝特征的表示上。本文基于深度學(xué)習(xí)對圖像特征的表示,研究了其在服裝檢索和搭配技術(shù)上的應(yīng)用。本文主要完成以下工作:1.本文介紹了局部特征和深度學(xué)習(xí)特征兩種圖像特征的表示方法,分別分析這兩種特征的優(yōu)勢和不足,給出了服裝檢索與搭配技術(shù)的理論依據(jù)。在局部特征方面,重點介紹了SIFT特征、SURF特征和基于這兩種特征編碼的BoF特征模型;在深度學(xué)習(xí)方面,重點介紹了自動編碼器和卷積神經(jīng)網(wǎng)絡(luò)。2.提出了基于卷積神經(jīng)網(wǎng)絡(luò)的服裝屬性多標簽分類模型用于服裝圖像特征提取。服裝圖像中含有豐富的服裝特有的屬性信息,比如顏色、花紋、袖子的長短等等。本文通過訓(xùn)練一個深度卷積神經(jīng)網(wǎng)絡(luò)對這些服裝屬性進行分類,并使用該神經(jīng)網(wǎng)絡(luò)的深層激活值表示服裝特征。在網(wǎng)絡(luò)訓(xùn)練過程中,為了彌補服裝訓(xùn)練數(shù)據(jù)的不足,運用遷移學(xué)習(xí)的方法對網(wǎng)絡(luò)進行再訓(xùn)練。實驗結(jié)果表明,該深度卷積網(wǎng)絡(luò)提取的特征對服裝的屬性特點能夠很好的表示,并且獲得了較好的服裝檢索效果。3.提出了基于相似性度量學(xué)習(xí)的服裝特征優(yōu)化網(wǎng)絡(luò)。本文基于Triplet相似性度量學(xué)習(xí)和雙卷積神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu),使用三元組服裝圖像訓(xùn)練網(wǎng)絡(luò)參數(shù),對服裝特征匹配進行了優(yōu)化。使用該網(wǎng)絡(luò)提取服裝特征后,用近似最近鄰查找相似服裝。實驗結(jié)果表明,優(yōu)化后的特征在服裝商品圖和用戶拍照圖檢索效果上都有提升,對服裝的光照和形變等干擾因素魯棒性較高。4.提出了基于服裝圖像深度特征和局部編碼特征的服裝搭配空間構(gòu)建方法。本文基于卷積神經(jīng)網(wǎng)絡(luò)提取的特征和SIFT特征編碼的BoF特征融合形成服裝搭配特征,并使用去噪自動編碼器對服裝特征降維,然后基于搭配數(shù)據(jù)集中的搭配頻繁項集構(gòu)建關(guān)聯(lián)規(guī)則,使用服裝搭配特征和關(guān)聯(lián)規(guī)則構(gòu)建服裝搭配空間。實驗結(jié)果表明,基于該服裝搭配空間能夠為用戶找到合適的服裝搭配方案。
[Abstract]:With the development of the clothing e-commerce and big data coming, Internet stores clothing data, users on the increasing demand. Clothing retrieval and collocation to find the right clothing to help users quickly and accurately, and recommend appropriate collocation scheme, clothing is an important means to enhance the user experience and business platform sales. Because of this, the study of clothing collocation retrieval and technology becomes very meaningful. Clothing retrieval and collocation techniques rely on the clothing image content information understanding, this understanding into the clothing features. This paper expressed deep learning representation of image feature based on of clothing and retrieval collocation application technology. This paper mainly completes the following work: 1. this paper introduces the representation of local features and deep learning characteristics of two kinds of image features, analysis of the two respectively. A feature of the advantages and disadvantages of the theory and technology of clothing collocation is given. In the local feature retrieval, introduces SIFT feature, SURF feature and BoF feature model based on the characteristics of two kinds of encoding; learning in depth, focuses on automatic convolution encoder and.2. neural network is proposed for the clothing image feature extraction of clothing attribute convolutional neural network model based on multi label classification. With attribute information, unique rich clothing clothing image such as color, pattern, sleeve length and so on. Through the training of a deep convolutional neural network to classify these clothing attributes, deep and using the neural network's activation value represents the garment feature in the process of network training, in order to compensate for the lack of clothing training data, using the method of transfer learning and training of the network. The experimental results show that the deep The characteristics of attribute extraction convolutional network of clothing can be expressed very well, and get a better retrieval effect.3. presented similar clothing clothing characteristics of network optimization based on metric learning. In this paper, Triplet similarity metric learning and double convolutional neural network structure based on three tuple clothing image training network parameters of garment feature matching was optimized. The extraction of clothing characteristics using the network, using the approximate nearest neighbor searching similar clothing. The experimental results show that the optimized features in clothing product map and user photograph map retrieval effect has improved, the clothing of illumination and deformation of interference factors such as the robust.4. method was proposed to build the depth of clothing image features and local features of clothing collocation based on spatial encoding. This encoding BoF feature and SIFT feature extraction of the convolutional neural network based on Fusion Form the clothing collocation features, and use the denoising auto encoder to reduce the dimensionality of the garment feature, then collocation data set collocation of frequent itemsets constructing based on association rules, the use of clothing collocation features and association rules to construct the clothing collocation space. The experimental results show that the clothing collocation space for users to find suitable clothing collocation scheme based on.

【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP181

【參考文獻】

相關(guān)期刊論文 前2條

1 杜丹;張千惠;;基于極速學(xué)習(xí)機的服裝搭配智能推薦系統(tǒng)設(shè)計[J];中國科技信息;2012年17期

2 羅娟;吳奕葦;;服裝搭配TPO原則與混搭風格之比較[J];廣西輕工業(yè);2011年06期

相關(guān)碩士學(xué)位論文 前1條

1 徐略輝;基于模糊粗集等價聚類的不確定性屬性約簡及其在服裝搭配上的應(yīng)用[D];東華大學(xué);2008年

，

本文編號：1676854