第五章 討論
5.2 影像標籤解析率與歷程探討
‧ 國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
從歷程記錄的統計表中，我們發現跳過此題的頻率在外文的餐點名稱照片上高出中 文的餐點名稱照片許多，主要的原因在於群眾大多為台灣人，在外文的餐點名稱照片需 要等待其他熟悉外文的群眾來新增選項方可選擇，在此之前也只能選擇跳過。在選擇選 項的頻率上，外文的餐點名稱照片則是高出中文的餐點名稱照片些許，可能的原因在於 發佈至社群網站的期間，恰巧在外文餐點名稱照片多時，有較多的群眾在參與解析。在 新增選項的頻率上，中文的部分，在新增選項頻率上為 2.027，表示平均每一個中文餐 點名稱照片約有兩個選項，而外文新增選項的頻率為 1.467，表示約有一半的外文餐點 名稱照片會有兩個選項。因此我們認為，群眾在熟悉的事情上雖然解析之準確率高，但 也因為熟悉之緣故，而導致在過多貢獻的情形下使得群眾之共識容易分散以及惡意破壞 的程度上較具有影響力，因此並不是最好的方法，如同表 6 中的編號 4,5 之選項。相反 的，群眾在不熟悉的事情上只能仰賴少部分熟悉事情的群眾提供貢獻，因此不會有過多 的貢獻，也使得群眾之共識不易分散，且在惡意破壞之程度上較不具影響力，反而能減
少問題產生，進而得到較好之結果。
‧
之時間。因此，我們認為 iPARIS-Plus 能讓使用者在保有便利性的同時，也能兼顧記錄 的完整性，期盼透過這樣的服務，能有效提升人們記錄的意願，讓他們不再將記錄視為 一種麻煩。而研究貢獻之二在於，我們藉由群眾外包的力量將影像標籤轉換為文字後儲 存 於 資 料 庫 中 ， 解 決 原 先 因 多 國 語 系 註 釋 問 題 所 造 成 的 資 料 空 缺 ， 以 使 提 供 給‧ 國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
iPARIS-Plus 使用者可直接點選使用之資料更加完整，同時也節省了使用者進行記錄之 時間。
我們對於 iPARIS-Plus 未來的方向提出兩點看法，詳細說明如下：
1. 目前在 iPARIS-Plus 上僅有基於 iPARIS 原先所設計的地點檢索以及時間與地點 的階層性分類，期盼在未來能加入照片的內容檢索，搜尋照片所註釋之標籤，
以及對於照片所註釋之標籤進行分類，如人、事、食物等等，將有助於使用者 對於照片之管理與瀏覽。
2. 我們期盼在未來能對於 iPARIS-Plus 以使用性工程反覆開發，除了使用介面之 外，更將影像標籤註釋之方法加以改良，讓製作標籤的過程更易於操作且能符 合更多使用者的需要，例如影像之內容排列特殊而難以框起，使其在應用上更 加多元。
‧
1 Bolaños, Marc, Maite Garolera, and Petia Radeva. "Active labeling application applied to food-related object recognition." Proceedings of the 5th international workshop on Multimedia for cooking & eating activities. ACM, 2013.
2 Bush, Vannevar, and As We May Think. "The atlantic monthly." As We May Think 176.1 (1945): 101-108.
3 Buykx, Lucy, and Helen Petrie. "What Cooks Needs from Multimedia and Textually Enhanced Recipes." Multimedia (ISM), 2011 IEEE International Symposium on.
IEEE, 2011.
4 Camera Finder. http://www.flickr.com/cameras.
5 Doan, Anhai, Raghu Ramakrishnan, and Alon Y. Halevy. "Crowdsourcing systems on the world-wide web." Communications of the ACM 54.4 (2011): 86-96.
6 Pishva, Davar, et al. "Bread recognition using color distribution analysis." IEICE TRANSACTIONS on Information and Systems 84.12 (2001): 1651-1659.
7 Geiger, David, Michael Rosemann, and Erwin Fielt. "Crowdsourcing information systems: a systems theory perspective." Proceedings of the 22nd Australasian Conference on Information Systems (ACIS 2011). 2011.
8 Bell, C. Gordon, and Jim Gemmell. Total recall: How the e-memory revolution will change everything. Dutton, 2009.
9 Hoashi, Hajime, Taichi Joutou, and Keiji Yanai. "Image recognition of 85 food
categories by feature fusion." Multimedia (ISM), 2010 IEEE International Symposium on. IEEE, 2010.
‧
10 ISO/IEC 15938-1:2002, “Information technology — Multimedia content description interface — Part 1: Systems,” 2002.
11 ISO/IEC 15938-2:2002, “Information technology — Multimedia content description interface — Part 2: Description definition language,” 2002.
12 ISO/IEC 15938-3:2002, “Information technology — Multimedia content description interface — Part 3: Visual,” 2002.
13 ISO/IEC 15938-4:2002, “Information technology — Multimedia content description interface — Part 4: Audio,” 2002.
14 ISO/IEC 15938-5:2003, “Information technology — Multimedia content description interface — Part 5: Multimedia description schemes,” 2003.
15 ISO/IEC 15938-6:2003, “Information technology — Multimedia content description interface — Part 6: Reference software,” 2003.
16 ISO/IEC 15938-7:2003, “Information technology — Multimedia content description interface — Part 7: Conformance testing,” 2003.
17 ISO/IEC TR 15938-8:2002, “Information technology — Multimedia content description interface — Part 8: Extraction and use of MPEG-7 descriptions,” 2002.
18 ISO/IEC 15938-9:2005, “Information technology — Multimedia content description interface — Part 9: Profiles and levels,” 2005.
19 ISO/IEC 15938-10:2005, “Information technology — Multimedia content description interface — Part 10: Schema definition,” 2005.
20 ISO/IEC TR 15938-11:2005, “Information technology — Multimedia content
‧
23 Kitamura, Keigo, Toshihiko Yamasaki, and Kiyoharu Aizawa. "Food log by analyzing food images." Proceeding of the 16th ACM international conference on Multimedia.
ACM, 2008.
24 Kitamura, Keigo, Toshihiko Yamasaki, and Kiyoharu Aizawa. "Food-Log: Capture, analysis and retrieval of personal food images via web." Proc. Int’l Symposium on Applications and the Internet Workshops. 2009.
25 Kitamura, Keigo, Toshihiko Yamasaki, and Kiyoharu Aizawa. "Image processing based approach to food balance analysis for personal food logging." Multimedia and Expo (ICME), 2010 IEEE International Conference on. IEEE, 2010.
26 KPCB Internet Trends.
http://www.scribd.com/doc/115395317/2012-KPCB-Internet-Trends-Year-End-Updat e.
27 Kuo, Fang-Fei, et al. "Intelligent menu planning: recommending set of recipes by ingredients." Proceedings of the ACM multimedia 2012 workshop on Multimedia for cooking and eating activities. ACM, 2012.
28 Kuo, Pei-Jeng, Terumasa Aoki, and Hiroshi Yasuda. "Building personal digital photograph libraries: An approach with ontology-based MPEG-7 dozen dimensional digital content architecture." Computer Graphics International, 2004. Proceedings.
IEEE, 2004.
29 Kuo, Pei-Jeng, Terumasa Aoki, and Hiroshi Yasuda. "MPEG-7 based dozen dimensional digital content architecture for semantic image retrieval services."
e-Technology, e-Commerce and e-Service, 2004. EEE'04. 2004 IEEE International Conference on. IEEE, 2004.
30 Kuo, Pei-Jeng, Terumasa Aoki, and Hiroshi Yasuda. "Continuous Archiving of Personal Digital Photograph Collections with a MPEG-7 Based Dozen Dimensional Digital Content Architecture." Archiving Conference. Vol. 2005. No. 1. Society for
‧
31 Messina, Virginia, Vesanto Melina, and Ann Reed Mangels. "A New Food Guide: For North American Vegetarians." Canadian Journal of Dietetic Practice and Research 64.2 (2003): 82-86.
32 Miyawaki, Kenzaburo, et al. "A cooking support system for people with higher brain dysfunction." Proceedings of the ACM multimedia 2009 workshop on Multimedia for cooking and eating activities. ACM, 2009.
33 Morikawa, Chamin, Haruki Sugiyama, and Kiyoharu Aizawa. "Food region segmentation in meal images using touch points." Proceedings of the ACM
multimedia 2012 workshop on Multimedia for cooking and eating activities. ACM, 2012.
34 MPEG. "About MPEG - Achievements". chiariglione.org.
http://mpeg.chiariglione.org/achievements.htm. Retrieved 2009-10-31.
35 MPEG. "Terms of Reference". chiariglione.org.
http://mpeg.chiariglione.org/terms_of_reference.htm. Retrieved 2009-10-31.
36 MPEG. "MPEG standards - Full list of standards developed or under development".
chiariglione.org. http://mpeg.chiariglione.org/standards.htm. Retrieved 2009-10-31.
37 Ota, Saori, et al. "Comparison of Experts' between Non-experts' Apple Peeling Skills and the Designing of Learning Support System." Multimedia (ISM), 2010 IEEE International Symposium on. IEEE, 2010.
38 Po-Yen Chen and Pei-Jeng Kuo, “Archiving of Personal Digital Photograph Collections with a MPEG-7 based Geotag Related Annotation Methodology,”
‧ 國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
40 Viitamaki, S. "The FLIRT model of crowdsourcing: planning and executing collective customer collaboration." Masterarbeit an der Helsinki School of Economics,
Department of Marketing and Management, Helsinki (2008).
41 Xie, Haoran, Lijuan Yu, and Qing Li. "A Hybrid Semantic Item Model for Recipe Search by Example." Multimedia (ISM), 2010 IEEE International Symposium on.
IEEE, 2010.
42 Yamakata, Yoko, et al. "A study of object naming according to the manufacturing processes in a cooking activity." Proceedings of the ACM multimedia 2009 workshop on Multimedia for cooking and eating activities. ACM, 2009.
43 Yin, Wenyuan, Tao Mei, and Chang Wen Chen. "Crowdsourced Learning to Photograph via Mobile Devices." Multimedia and Expo (ICME), 2012 IEEE International Conference on. IEEE, 2012.
44 Zepeda, Lydia, and David Deal. "Think before you eat: photographic food diaries as intervention tools to change dietary decision making and attitudes." International Journal of Consumer Studies 32.6 (2008): 692-698
‧
‧ 國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
9. 請問您在使用 APP「以照片註釋照片」的功能時，您覺得在「從餐點名稱照片中框 選出餐點名稱之部分」的步驟於操作上是否需要改善 ? 是 否
10. 請問您在使用 APP「以照片註釋照片」的功能時，您覺得在「儲存註釋完成之照片」
的步驟於操作上是否需要改善 ? 是 否
Part 3
1. 請問「以照片註釋照片」是否減少您輸入文字註釋照片上的困擾 ? 是 否 2. 請問對您而言，以「照片」作為標籤用來註釋照片的方法，是否能作為以「文字」
來註釋照片之外的另一種註釋方法？ 是 否 ; 原因：
3. 請問在輸入文字註釋時，多少個中文「文字」就會讓您想改以「照片」作為註釋 ? 1 個 2 個 3 個 3 個以上
4. 請問在輸入文字註釋時，多少個外文「文字」就會讓您想改以「照片」作為註釋 ? 1 個 2 個 3 個 3 個以上