Publications-Theses
Article View/Open
Publication Export
-
題名 根據時尚資料學習搭配性以自動化推薦服飾
Automatic Clothing Recommendation by Learning Clothing Compatibility from Fashion Data作者 陳彥蓉
Chen, Yen-Jung貢獻者 沈錳坤
Shan, Man-Kwan
陳彥蓉
Chen, Yen-Jung關鍵詞 服飾推薦
主題模型
卷積神經網路
Clothing recommendation
Topic modeling
Convolutional neural network日期 2018 上傳時間 1-Oct-2018 12:10:06 (UTC+8) 摘要 隨著網路購物的興起，流行服飾產業以網路行銷的方式蓬勃發展，許多研究開始致力於服飾類商品的推薦，幫助使用者挑選適當的商品，省去在龐大商品之海中茫然選擇的時間與精力，提供便利又迅速的方式，讓使用者獲取時髦好看的穿搭樣式。而針對服裝之間的搭配性，與大眾流行的元素，作為網路購物的商品推薦，不僅讓平時不善於流行穿搭的人，取得符合當今潮流趨勢且恰當的服飾搭配建議，藉由推薦可相互搭配的商品，更能同時提升商品的連帶銷售率，以增加商家的獲利。 本研究旨在提出一套基於風格與熱門度的服飾搭配推薦機制，並且實作出系統。首先，考量整體風格對於搭配關係的影響，從大量服飾資料，擷取套裝(Outfit)中所有單品(Item)的文字資訊，包含商品標題、內容描述、關鍵詞等文字詞袋，以Latent Dirichlet Allocation (LDA)進行Topic Modeling，計算每組套裝的主題分佈，將最具代表性的主題視為其套裝所屬之風格。另外，為了使系統有效判別輸入圖片的商品類別，再依照使用者所選風格，推薦相異類別且彼此適合搭配的單品，因此，利用Convolutional Neural Network (CNN)訓練兩種影像分類模型。其一是單品類別分類模型；其二，在學習服飾影像上的搭配概念時，根據套裝單品的影像內容和喜好分數，以熱門程度作為衡量搭配性的標準，建立套裝搭配分類模型，學習商品之間是否適合搭配的潛在規則。 最終開發一服飾搭配的網站系統，提供平台讓使用者選取喜歡的風格、上傳服飾圖片，由系統自動為圖片挑選在相同風格、相異類別中，最適宜搭配的服飾產品予以推薦。
With the rise of online shopping, the fashion industry has flourished by the mode of internet marketing. Much research has begun to focus on the recommendation of apparel products, helping users to select appropriate items for saving the time and effort in choosing from a huge amount of products, which provides a convenient and fast way for users to get a stylish and good-looking dressing patterns. By aiming at the clothing compatibilities and popular elements as factors of fashion product recommendation, to recommend items that can be matched with each other for online shopping, not only enables people who are not good at wearing to obtain the suitable clothing matching suggestions with today’s fashion trend, but also can increase the profits of business while improving joint sales rate of goods. This thesis proposes a clothing matching recommendation mechanism based on style and popularity, and implements the clothing recommendation system. First of all, we consider the influence of overall style on the collocation relationships. From a large number of fashion data, we capture the text information of all items in outfits, including the product title, category, description. Then, Latent Dirichlet Allocation (LDA) topic model is employed to calculate the theme distribution for each outfit, and the most representative theme is manually defined as the style of the outfit. In addition, in order to allow the system to effectively discriminate the item category of the input image, and to recommend matching items in heterogeneous categories according the style selected by the user, therefore, we use Convolutional Neural Network (CNN) to train two image classification models. The first one is the category classification model which can recognize the image is top or others. The second one is outfit compatibility classification model which automatically learn whether the item pairs are suitable matching between each other or not. When learning the concept of matching on item images, we utilize the image contents and user preference scores that indicate the popularity of the product as a measure of clothing compatibility. Finally, we develop a web system for clothing matching recommendation, that provides a platform for users to select the style they like and upload the clothing image. This system can automatically recommend users the suitable clothing products, that are matching with input image in the same style and different categories.參考文獻 [1] L. Bossard, M. Dantone, C. Leistner, C. Wengert, T. Quack, and L. Van Gool, Apparel classification with style. Asian conference on computer vision, 2012. [2] H. Chen, A. Gallagher, and B. Girod, Describing clothing by semantic attributes. Computer Vision–ECCV 2012, 609-623, 2012. [3] N. Dalal and B. Triggs, Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005. [4] J. Dong, Q. Chen, X. Shen, J. Yang, and S. Yan, Towards unified human parsing and pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. [5] M. Hadi Kiapour, X. Han, S. Lazebnik, A. C. Berg, and T. L. Berg, Where to buy it: Matching street clothing photos in online shops. Proceedings of the IEEE International Conference on Computer Vision, 2015. [6] R. He, C. Packer, and J. Mcauley, Learning Compatibility Across Categories for Heterogeneous Item Recommendation. arXiv preprint arXiv:1603.09473, 2016. [7] Y. Hu, X. Yi, and L. S. Davis, Collaborative fashion recommendation: a functional tensor factorization approach. Proceedings of the 23rd ACM international conference on Multimedia, 2015. [8] C.-M. Huang, C.-P. Wei, and Y.-C. F. Wang, Active learning based clothing image recommendation with implicit user preferences. Multimedia and Expo Workshops (ICMEW), 2013 IEEE International Conference on, 2013. [9] J. Huang, R. S. Feris, Q. Chen, and S. Yan, Cross-domain image retrieval with a dual attribute-aware ranking network. Proceedings of the IEEE International Conference on Computer Vision, 2015. [10] T. Iwata, S. Wanatabe, and H. Sawada, Fashion coordinates recommender system using photographs from fashion magazines. IJCAI, 2011. [11] V. Jagadeesh, R. Piramuthu, A. Bhardwaj, W. Di, and N. Sundaresan, Large scale visual recommendations from street fashion images. Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014. [12] J. Jia, J. Huang, G. Shen, T. He, Z. Liu, H.-B. Luan, and C. Yan, Learning to Appreciate the Aesthetic Effects of Clothing. AAAI, 2016. [13] M. H. Kiapour, K. Yamaguchi, A. C. Berg, and T. L. Berg, Hipster wars: Discovering elements of fashion styles. European conference on computer vision, 2014. [14] K. Lin, H.-F. Yang, K.-H. Liu, J.-H. Hsiao, and C.-S. Chen, Rapid clothing retrieval via deep learning of binary codes and hierarchical search. Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, 2015. [15] S. Liu, J. Feng, Z. Song, T. Zhang, H. Lu, C. Xu, and S. Yan, Hi, magic closet, tell me what to wear! Proceedings of the 20th ACM international conference on Multimedia, 2012. [16] S. Liu, L. Liu, and S. Yan, Fashion analysis: Current techniques and future directions. IEEE MultiMedia, 21(2), 72-79, 2014. [17] S. Liu, Z. Song, G. Liu, C. Xu, H. Lu, and S. Yan, Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012. [18] J. Mcauley, C. Targett, Q. Shi, and A. Van Den Hengel, Image-based recommendations on styles and substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015. [19] M. Moreira, J. A. Dos Santos, and A. Veloso, Learning to Rank Similar Apparel Styles with Economically-Efficient Rule-Based Active Learning. Proceedings of International Conference on Multimedia Retrieval, 2014. [20] D. Sha, D. Wang, X. Zhou, S. Feng, Y. Zhang, and G. Yu, An Approach for Clothing Recommendation Based on Multiple Image Attributes. International Conference on Web-Age Information Management, 2016. [21] E. Simo-Serra, S. Fidler, F. Moreno-Noguer, and R. Urtasun, Neuroaesthetics in fashion: Modeling the perception of fashionability. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. [22] E. Simo-Serra and H. Ishikawa, Fashion style in 128 floats: joint ranking and classification using weak data for feature extraction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. [23] K. Vaccaro, S. Shivakumar, Z. Ding, K. Karahalios, and R. Kumar, The Elements of Fashion Style. Proceedings of the 29th Annual Symposium on User Interface Software and Technology, 2016. [24] A. Veit, B. Kovacs, S. Bell, J. Mcauley, K. Bala, and S. Belongie, Learning visual clothing style with heterogeneous dyadic co-occurrences. Proceedings of the IEEE International Conference on Computer Vision, 2015. [25] S. Vittayakorn, K. Yamaguchi, A. C. Berg, and T. L. Berg, Runway to realway: Visual analysis of fashion. Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on, 2015. [26] X. Wang, T. Zhang, D. R. Tretter, and Q. Lin, Personal clothing retrieval on photo collections by color and attributes. IEEE Transactions on Multimedia, 15(8), 2035-2045, 2013. [27] K. Yamaguchi, T. L. Berg, and L. E. Ortiz, Chic or social: Visual popularity analysis in online fashion networks. Proceedings of the 22nd ACM international conference on Multimedia, 2014. [28] K. Yamaguchi, M. Hadi Kiapour, and T. L. Berg, Paper doll parsing: Retrieving similar styles to parse clothing items. Proceedings of the IEEE International Conference on Computer Vision, 2013. [29] K. Yamaguchi, M. H. Kiapour, L. E. Ortiz, and T. L. Berg, Parsing clothing in fashion photographs. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012. [30] K. Yamaguchi, T. Okatani, K. Sudo, K. Murasaki, and Y. Taniguchi, Mix and Match: Joint Model for Clothing and Attribute Recognition. BMVC, 2015. [31] W. Yang, P. Luo, and L. Lin, Clothing co-parsing by joint image segmentation and labeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. 描述 碩士
國立政治大學
資訊科學系
103753020資料來源 http://thesis.lib.nccu.edu.tw/record/#G0103753020 資料類型 thesis dc.contributor.advisor 沈錳坤 zh_TW dc.contributor.advisor Shan, Man-Kwan en_US dc.contributor.author (Authors) 陳彥蓉 zh_TW dc.contributor.author (Authors) Chen, Yen-Jung en_US dc.creator (作者) 陳彥蓉 zh_TW dc.creator (作者) Chen, Yen-Jung en_US dc.date (日期) 2018 en_US dc.date.accessioned 1-Oct-2018 12:10:06 (UTC+8) - dc.date.available 1-Oct-2018 12:10:06 (UTC+8) - dc.date.issued (上傳時間) 1-Oct-2018 12:10:06 (UTC+8) - dc.identifier (Other Identifiers) G0103753020 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/120255 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 103753020 zh_TW dc.description.abstract (摘要) 隨著網路購物的興起，流行服飾產業以網路行銷的方式蓬勃發展，許多研究開始致力於服飾類商品的推薦，幫助使用者挑選適當的商品，省去在龐大商品之海中茫然選擇的時間與精力，提供便利又迅速的方式，讓使用者獲取時髦好看的穿搭樣式。而針對服裝之間的搭配性，與大眾流行的元素，作為網路購物的商品推薦，不僅讓平時不善於流行穿搭的人，取得符合當今潮流趨勢且恰當的服飾搭配建議，藉由推薦可相互搭配的商品，更能同時提升商品的連帶銷售率，以增加商家的獲利。 本研究旨在提出一套基於風格與熱門度的服飾搭配推薦機制，並且實作出系統。首先，考量整體風格對於搭配關係的影響，從大量服飾資料，擷取套裝(Outfit)中所有單品(Item)的文字資訊，包含商品標題、內容描述、關鍵詞等文字詞袋，以Latent Dirichlet Allocation (LDA)進行Topic Modeling，計算每組套裝的主題分佈，將最具代表性的主題視為其套裝所屬之風格。另外，為了使系統有效判別輸入圖片的商品類別，再依照使用者所選風格，推薦相異類別且彼此適合搭配的單品，因此，利用Convolutional Neural Network (CNN)訓練兩種影像分類模型。其一是單品類別分類模型；其二，在學習服飾影像上的搭配概念時，根據套裝單品的影像內容和喜好分數，以熱門程度作為衡量搭配性的標準，建立套裝搭配分類模型，學習商品之間是否適合搭配的潛在規則。 最終開發一服飾搭配的網站系統，提供平台讓使用者選取喜歡的風格、上傳服飾圖片，由系統自動為圖片挑選在相同風格、相異類別中，最適宜搭配的服飾產品予以推薦。 zh_TW dc.description.abstract (摘要) With the rise of online shopping, the fashion industry has flourished by the mode of internet marketing. Much research has begun to focus on the recommendation of apparel products, helping users to select appropriate items for saving the time and effort in choosing from a huge amount of products, which provides a convenient and fast way for users to get a stylish and good-looking dressing patterns. By aiming at the clothing compatibilities and popular elements as factors of fashion product recommendation, to recommend items that can be matched with each other for online shopping, not only enables people who are not good at wearing to obtain the suitable clothing matching suggestions with today’s fashion trend, but also can increase the profits of business while improving joint sales rate of goods. This thesis proposes a clothing matching recommendation mechanism based on style and popularity, and implements the clothing recommendation system. First of all, we consider the influence of overall style on the collocation relationships. From a large number of fashion data, we capture the text information of all items in outfits, including the product title, category, description. Then, Latent Dirichlet Allocation (LDA) topic model is employed to calculate the theme distribution for each outfit, and the most representative theme is manually defined as the style of the outfit. In addition, in order to allow the system to effectively discriminate the item category of the input image, and to recommend matching items in heterogeneous categories according the style selected by the user, therefore, we use Convolutional Neural Network (CNN) to train two image classification models. The first one is the category classification model which can recognize the image is top or others. The second one is outfit compatibility classification model which automatically learn whether the item pairs are suitable matching between each other or not. When learning the concept of matching on item images, we utilize the image contents and user preference scores that indicate the popularity of the product as a measure of clothing compatibility. Finally, we develop a web system for clothing matching recommendation, that provides a platform for users to select the style they like and upload the clothing image. This system can automatically recommend users the suitable clothing products, that are matching with input image in the same style and different categories. en_US dc.description.tableofcontents 第一章 緒論 1 1.1研究背景、動機與目的 1 1.2論文貢獻 4 1.3論文架構 5 第二章 相關研究 6 2.1服裝解析與識別 6 2.2服裝檢索 7 2.3服裝推薦 8 2.3.1單品推薦 9 2.3.2套裝推薦 10 2.4時尚趨勢分析與預測 10 第三章 研究方法 12 3.1系統架構 12 3.2 Outfit Style Recognition 14 3.2.1 Bag-of-Word (BOW) 14 3.2.2 Latent Dirichlet Allocation (LDA) 16 3.3服飾推薦 19 3.3.1 Convolutional Neural Network (CNN) 19 3.3.2 Item Category Recognition 23 3.3.3 Outfit Compatibility Prediction 24 第四章 系統實作 26 4.1 Web系統架構 26 4.2開發框架與工具 27 4.2.1 Django 27 4.2.2 D3.js 28 4.2.3 PostgreSQL 28 4.3系統介面設計 29 第五章 實驗 32 5.1資料搜集 32 5.2資料前處理 36 5.3實驗設計與評估 37 5.3.1分群模型評估 37 5.3.2分類模型評估 38 5.4實驗結果 39 5.4.1套裝風格分群結果 40 5.4.2單品類別分類結果 44 5.4.3套裝搭配分類結果 45 第六章 結論與未來研究 46 參考文獻 47 zh_TW dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0103753020 en_US dc.subject (關鍵詞) 服飾推薦 zh_TW dc.subject (關鍵詞) 主題模型 zh_TW dc.subject (關鍵詞) 卷積神經網路 zh_TW dc.subject (關鍵詞) Clothing recommendation en_US dc.subject (關鍵詞) Topic modeling en_US dc.subject (關鍵詞) Convolutional neural network en_US dc.title (題名) 根據時尚資料學習搭配性以自動化推薦服飾 zh_TW dc.title (題名) Automatic Clothing Recommendation by Learning Clothing Compatibility from Fashion Data en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] L. Bossard, M. Dantone, C. Leistner, C. Wengert, T. Quack, and L. Van Gool, Apparel classification with style. Asian conference on computer vision, 2012. [2] H. Chen, A. Gallagher, and B. Girod, Describing clothing by semantic attributes. Computer Vision–ECCV 2012, 609-623, 2012. [3] N. Dalal and B. Triggs, Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005. [4] J. Dong, Q. Chen, X. Shen, J. Yang, and S. Yan, Towards unified human parsing and pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. [5] M. Hadi Kiapour, X. Han, S. Lazebnik, A. C. Berg, and T. L. Berg, Where to buy it: Matching street clothing photos in online shops. Proceedings of the IEEE International Conference on Computer Vision, 2015. [6] R. He, C. Packer, and J. Mcauley, Learning Compatibility Across Categories for Heterogeneous Item Recommendation. arXiv preprint arXiv:1603.09473, 2016. [7] Y. Hu, X. Yi, and L. S. Davis, Collaborative fashion recommendation: a functional tensor factorization approach. Proceedings of the 23rd ACM international conference on Multimedia, 2015. [8] C.-M. Huang, C.-P. Wei, and Y.-C. F. Wang, Active learning based clothing image recommendation with implicit user preferences. Multimedia and Expo Workshops (ICMEW), 2013 IEEE International Conference on, 2013. [9] J. Huang, R. S. Feris, Q. Chen, and S. Yan, Cross-domain image retrieval with a dual attribute-aware ranking network. Proceedings of the IEEE International Conference on Computer Vision, 2015. [10] T. Iwata, S. Wanatabe, and H. Sawada, Fashion coordinates recommender system using photographs from fashion magazines. IJCAI, 2011. [11] V. Jagadeesh, R. Piramuthu, A. Bhardwaj, W. Di, and N. Sundaresan, Large scale visual recommendations from street fashion images. Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014. [12] J. Jia, J. Huang, G. Shen, T. He, Z. Liu, H.-B. Luan, and C. Yan, Learning to Appreciate the Aesthetic Effects of Clothing. AAAI, 2016. [13] M. H. Kiapour, K. Yamaguchi, A. C. Berg, and T. L. Berg, Hipster wars: Discovering elements of fashion styles. European conference on computer vision, 2014. [14] K. Lin, H.-F. Yang, K.-H. Liu, J.-H. Hsiao, and C.-S. Chen, Rapid clothing retrieval via deep learning of binary codes and hierarchical search. Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, 2015. [15] S. Liu, J. Feng, Z. Song, T. Zhang, H. Lu, C. Xu, and S. Yan, Hi, magic closet, tell me what to wear! Proceedings of the 20th ACM international conference on Multimedia, 2012. [16] S. Liu, L. Liu, and S. Yan, Fashion analysis: Current techniques and future directions. IEEE MultiMedia, 21(2), 72-79, 2014. [17] S. Liu, Z. Song, G. Liu, C. Xu, H. Lu, and S. Yan, Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012. [18] J. Mcauley, C. Targett, Q. Shi, and A. Van Den Hengel, Image-based recommendations on styles and substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015. [19] M. Moreira, J. A. Dos Santos, and A. Veloso, Learning to Rank Similar Apparel Styles with Economically-Efficient Rule-Based Active Learning. Proceedings of International Conference on Multimedia Retrieval, 2014. [20] D. Sha, D. Wang, X. Zhou, S. Feng, Y. Zhang, and G. Yu, An Approach for Clothing Recommendation Based on Multiple Image Attributes. International Conference on Web-Age Information Management, 2016. [21] E. Simo-Serra, S. Fidler, F. Moreno-Noguer, and R. Urtasun, Neuroaesthetics in fashion: Modeling the perception of fashionability. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. [22] E. Simo-Serra and H. Ishikawa, Fashion style in 128 floats: joint ranking and classification using weak data for feature extraction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016. [23] K. Vaccaro, S. Shivakumar, Z. Ding, K. Karahalios, and R. Kumar, The Elements of Fashion Style. Proceedings of the 29th Annual Symposium on User Interface Software and Technology, 2016. [24] A. Veit, B. Kovacs, S. Bell, J. Mcauley, K. Bala, and S. Belongie, Learning visual clothing style with heterogeneous dyadic co-occurrences. Proceedings of the IEEE International Conference on Computer Vision, 2015. [25] S. Vittayakorn, K. Yamaguchi, A. C. Berg, and T. L. Berg, Runway to realway: Visual analysis of fashion. Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on, 2015. [26] X. Wang, T. Zhang, D. R. Tretter, and Q. Lin, Personal clothing retrieval on photo collections by color and attributes. IEEE Transactions on Multimedia, 15(8), 2035-2045, 2013. [27] K. Yamaguchi, T. L. Berg, and L. E. Ortiz, Chic or social: Visual popularity analysis in online fashion networks. Proceedings of the 22nd ACM international conference on Multimedia, 2014. [28] K. Yamaguchi, M. Hadi Kiapour, and T. L. Berg, Paper doll parsing: Retrieving similar styles to parse clothing items. Proceedings of the IEEE International Conference on Computer Vision, 2013. [29] K. Yamaguchi, M. H. Kiapour, L. E. Ortiz, and T. L. Berg, Parsing clothing in fashion photographs. Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, 2012. [30] K. Yamaguchi, T. Okatani, K. Sudo, K. Murasaki, and Y. Taniguchi, Mix and Match: Joint Model for Clothing and Attribute Recognition. BMVC, 2015. [31] W. Yang, P. Luo, and L. Lin, Clothing co-parsing by joint image segmentation and labeling. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014. zh_TW dc.identifier.doi (DOI) 10.6814/THE.NCCU.CS.016.2018.B02 en_US
