1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 學位論文
  5. Item

學術產出-學位論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 臉書相片分類及使用者樣貌分析
Identifying User Profile Using Facebook Photos.
作者 張婷雅
Chang, Ting Ya
貢獻者 廖文宏
Liao, Wen Hung
張婷雅
Chang,Ting Ya
關鍵詞 臉書
人臉偵測
環境識別
影像標籤
使用者樣貌分析
Facebook
face detection
scene understanding
image tag
user behavior analysis
日期 2016
上傳時間 1-三月-2016 10:40:21 (UTC+8)
摘要 除了文字訊息，張貼相片也是臉書使用者常用的功能，這些上傳的照片種類繁多，可能是自拍照、風景照、或食物照等等，本論文的研究以影像分析為出發點，探討相片內容跟發佈者間之關係，希望藉由相片獲得的資訊，輔助分析使用者樣貌。
本研究共收集32位受測者上傳至臉書的相片，利用電腦視覺技術分析圖像內容，如人臉偵測、環境識別、找出影像上視覺顯著的區域等，藉由這些工具所提供的資訊，將照片加註標籤，以及進行自動分類，並以此兩個層次的資訊做為特徵向量，利用階層式演算法進行使用者分群，再根據實驗結果去分析每一群的行為特性。
透過此研究，可對使用者進行初步分類、瞭解不同的使用者樣貌，並嘗試回應相關問題，如使用者所張貼之相片種類統計、不同性別使用者的上傳行為、 依據上傳圖像內容，進行使用者樣貌分類等，深化我們對於臉書相片上傳行為的理解。
Apart from text messages, photo posting is a popular function of Facebook. The uploaded photos are of various nature, including selfie, outdoor scenes, and food. In this thesis, we employ state-of-the-art computer vision techniques to analyze image content and establish the relationship between user profile and the type of photos posted.
We collected photos from 32 Facebook users. We then applied techniques such as face detection, scene understanding and saliency map identification to gather information for automatic image tagging and classification. Grouping of users can be achieved either by tag statistics or photo classes. Characteristics of each group can be further investigated based on the results of hierarchical clustering.
We wish to identify profiles of different users and respond to questions such as the type of photos most frequently posted, gender differentiation in photo posting behavior and user classification according to image content, which will promote our understanding of photo uploading activities on Facebook.
參考文獻 [1] Viola, Paul, and Michael J. Jones. "Robust real-time face detection." International journal of computer vision 57.2 (2004): 137-154.
[2] ImageNet
http://image-net.org/.
[3] Russakovsky, Olga, et al. "Imagenet large scale visual recognition challenge." arXiv preprint arXiv:1409.0575 (2014).
[4] Vinyals, Oriol, et al. "Show and tell: A neural image caption generator." arXiv preprint arXiv:1411.4555 (2014).
[5] Hu, Yuheng, Lydia Manikonda, and Subbarao Kambhampati. "What we instagram: A first analysis of instagram photo content and user types." Proceedings of ICWSM. AAAI (2014).
[6] Ensky’s Album Downloader for Facebook,
https://sofree.cc/download-fb-album-photo/.
[7] Face++,
http://www.faceplusplus.com/.
[8] Rekognition,
https://rekognition.com/.
[9] Itti, Laurent, Christof Koch, and Ernst Niebur. "A model of saliency-based visual attention for rapid scene analysis." IEEE Transactions on Pattern Analysis & Machine Intelligence 11 (1998): 1254-1259.
[10] Cheng, Ming, et al. "Global contrast based salient region detection." Pattern Analysis and Machine Intelligence, IEEE Transactions on 37.3 (2015): 569-582.
[11] Perazzi, Federico, et al. "Saliency filters: Contrast based filtering for salient region detection." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
[12] Team, R. Core. "R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria, 2012." (2014).
https://www.r-project.org/.
[13] 階層式分群法(Hierarchical Clustering),
http://goo.gl/mDfDp.
[14] 蔣佳欣 (2006)，室內/戶外與建築物/自然風景之影像分類研究，碩士論文，南台科技大學資訊工程所，臺南。
[15] Kawano, Yoshiyuki, and Keiji Yanai. "FoodCam: A Real-Time Mobile Food Recognition System Employing Fisher Vector." MultiMedia Modeling. Springer International Publishing, 2014.
[16] Zhang, Weiwei, Jian Sun, and Xiaoou Tang. "Cat head detection-how to effectively exploit shape and texture features." Computer Vision–ECCV 2008. Springer Berlin Heidelberg, 2008. 802-816.
[17] 王石番（1991），《傳播內容分析法》，幼獅
描述 碩士
國立政治大學
資訊科學學系
102753007
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0102753007
資料類型 thesis
dc.contributor.advisor 廖文宏zh_TW
dc.contributor.advisor Liao, Wen Hungen_US
dc.contributor.author (作者) 張婷雅zh_TW
dc.contributor.author (作者) Chang,Ting Yaen_US
dc.creator (作者) 張婷雅zh_TW
dc.creator (作者) Chang, Ting Yaen_US
dc.date (日期) 2016en_US
dc.date.accessioned 1-三月-2016 10:40:21 (UTC+8)-
dc.date.available 1-三月-2016 10:40:21 (UTC+8)-
dc.date.issued (上傳時間) 1-三月-2016 10:40:21 (UTC+8)-
dc.identifier (其他 識別碼) G0102753007en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/81525-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 102753007zh_TW
dc.description.abstract (摘要) 除了文字訊息，張貼相片也是臉書使用者常用的功能，這些上傳的照片種類繁多，可能是自拍照、風景照、或食物照等等，本論文的研究以影像分析為出發點，探討相片內容跟發佈者間之關係，希望藉由相片獲得的資訊，輔助分析使用者樣貌。
本研究共收集32位受測者上傳至臉書的相片，利用電腦視覺技術分析圖像內容，如人臉偵測、環境識別、找出影像上視覺顯著的區域等，藉由這些工具所提供的資訊，將照片加註標籤，以及進行自動分類，並以此兩個層次的資訊做為特徵向量，利用階層式演算法進行使用者分群，再根據實驗結果去分析每一群的行為特性。
透過此研究，可對使用者進行初步分類、瞭解不同的使用者樣貌，並嘗試回應相關問題，如使用者所張貼之相片種類統計、不同性別使用者的上傳行為、 依據上傳圖像內容，進行使用者樣貌分類等，深化我們對於臉書相片上傳行為的理解。		zh_TW
dc.description.abstract (摘要) Apart from text messages, photo posting is a popular function of Facebook. The uploaded photos are of various nature, including selfie, outdoor scenes, and food. In this thesis, we employ state-of-the-art computer vision techniques to analyze image content and establish the relationship between user profile and the type of photos posted.
We collected photos from 32 Facebook users. We then applied techniques such as face detection, scene understanding and saliency map identification to gather information for automatic image tagging and classification. Grouping of users can be achieved either by tag statistics or photo classes. Characteristics of each group can be further investigated based on the results of hierarchical clustering.
We wish to identify profiles of different users and respond to questions such as the type of photos most frequently posted, gender differentiation in photo posting behavior and user classification according to image content, which will promote our understanding of photo uploading activities on Facebook.		en_US
dc.description.tableofcontents 第一章 緒論 1
1.1 研究背景與目的 1
1.2 流程架構與方法 3
1.3 論文貢獻 4
1.4 論文架構 4
第二章 相關研究與技術背景 6
2.1 文獻探討 6
2.2 研究工具及技術背景介紹 9
2.2.1 Facebook相片蒐集 9
2.2.2 Face++ 10
2.2.3 Rekognition 11
2.2.4 Saliency map 12
2.2.5 階層式分群演算法 12
第三章 研究方法 16
3.1 定義相片的類別 16
3.1.1 人物照 16
3.1.2 景物照 17
3.1.3 主題照 18
3.1.4 非寫實照 19
3.1.5食物照 20
3.1.6 動物照 21
3.1.7 文字照 22
3.1.8 其他 23
3.2 圖像分類方法研究 24
3.2.1 人物照 24
3.2.2 景物照 27
3.2.3 主題照 29
3.2.4 非寫實照 30
3.2.5 食物照 32
3.2.6 動物照 33
3.2.7 文字照 33
3.3 標籤探討 35
3.3.1 過濾 35
3.3.2 考慮權重 36
3.3.3 合併意義相似的標籤項目 39
第四章 實驗結果與討論 41
4.1 使用者所張貼之相片，以哪種種類的相片最多? 43
4.2 男性、女性所張貼的相片內容，是否有所差異? 52
4.3如何依據資料內容，進行使用者樣貌分析? 55
4.3.1 相片種類樣貌分析 55
4.3.2 人物照樣貌分析 58
4.3.3 標籤樣貌分析 60
4.4用標籤將使用者分群是否會和用照片分類結果將使用者分群的結果一致? 62
4.5對於現有的資料，有何其他相關的應用? 64
第五章 結論與未來研究方向 70
參考文獻 72
附錄 74		zh_TW
dc.format.extent 5198915 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0102753007en_US
dc.subject (關鍵詞) 臉書zh_TW
dc.subject (關鍵詞) 人臉偵測zh_TW
dc.subject (關鍵詞) 環境識別zh_TW
dc.subject (關鍵詞) 影像標籤zh_TW
dc.subject (關鍵詞) 使用者樣貌分析zh_TW
dc.subject (關鍵詞) Facebooken_US
dc.subject (關鍵詞) face detectionen_US
dc.subject (關鍵詞) scene understandingen_US
dc.subject (關鍵詞) image tagen_US
dc.subject (關鍵詞) user behavior analysisen_US
dc.title (題名) 臉書相片分類及使用者樣貌分析zh_TW
dc.title (題名) Identifying User Profile Using Facebook Photos.en_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Viola, Paul, and Michael J. Jones. "Robust real-time face detection." International journal of computer vision 57.2 (2004): 137-154.
[2] ImageNet
http://image-net.org/.
[3] Russakovsky, Olga, et al. "Imagenet large scale visual recognition challenge." arXiv preprint arXiv:1409.0575 (2014).
[4] Vinyals, Oriol, et al. "Show and tell: A neural image caption generator." arXiv preprint arXiv:1411.4555 (2014).
[5] Hu, Yuheng, Lydia Manikonda, and Subbarao Kambhampati. "What we instagram: A first analysis of instagram photo content and user types." Proceedings of ICWSM. AAAI (2014).
[6] Ensky’s Album Downloader for Facebook,
https://sofree.cc/download-fb-album-photo/.
[7] Face++,
http://www.faceplusplus.com/.
[8] Rekognition,
https://rekognition.com/.
[9] Itti, Laurent, Christof Koch, and Ernst Niebur. "A model of saliency-based visual attention for rapid scene analysis." IEEE Transactions on Pattern Analysis & Machine Intelligence 11 (1998): 1254-1259.
[10] Cheng, Ming, et al. "Global contrast based salient region detection." Pattern Analysis and Machine Intelligence, IEEE Transactions on 37.3 (2015): 569-582.
[11] Perazzi, Federico, et al. "Saliency filters: Contrast based filtering for salient region detection." Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012.
[12] Team, R. Core. "R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria, 2012." (2014).
https://www.r-project.org/.
[13] 階層式分群法(Hierarchical Clustering),
http://goo.gl/mDfDp.
[14] 蔣佳欣 (2006)，室內/戶外與建築物/自然風景之影像分類研究，碩士論文，南台科技大學資訊工程所，臺南。
[15] Kawano, Yoshiyuki, and Keiji Yanai. "FoodCam: A Real-Time Mobile Food Recognition System Employing Fisher Vector." MultiMedia Modeling. Springer International Publishing, 2014.
[16] Zhang, Weiwei, Jian Sun, and Xiaoou Tang. "Cat head detection-how to effectively exploit shape and texture features." Computer Vision–ECCV 2008. Springer Berlin Heidelberg, 2008. 802-816.
[17] 王石番（1991），《傳播內容分析法》，幼獅		zh_TW