# 專題資料筆記 ###### tags: `fju`、`MLDL` # 臉部表情 ## 資料集(重要) http://cvfiasd.pixnet.net/blog/post/179250644-%E4%BA%BA%E8%87%89%E8%A1%A8%E6%83%85%E8%BE%A8%E8%AD%98%E8%B3%87%E6%96%99%E5%BA%AB https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/overview http://www.whdeng.cn/RAF/model1.html ## pretrain model https://github.com/JostineHo/real-time_emotion_analyzer https://github.com/gitshanks/fer2013 ## 建構神經網路教學 https://blog.csdn.net/walilk/article/details/58709611 > 農場文: https://www.itread01.com/content/1546298662.html https://blog.csdn.net/sinat_26917383/article/details/72885715 https://zhuanlan.zhihu.com/p/33021960 ## paper 1. http://140.119.115.26/bitstream/140.119/37112/9/100309.pdf 臉部表情識別系統 **喔喔喔** 2. https://www.ctolib.com/IcedDoggie-Micro-Expression-with-Deep-Learning.html CVPR 2018 微表情识别论文实现代码 3. https://ictjournal.itri.org.tw/Content/Messagess/contents.aspx?&MmmID=654304432061644411&CatID=654313611255143006&MSID=1002354340410301105 > http://shuoyang1213.me/WIDERFACE/ widerface dataset 4. http://tanet2014.kuas.edu.tw/ezfiles/28/1028/img/686/SS01-04.pdf 以區域為基礎之表情辨識系統 5. http://oplab.im.ntu.edu.tw/csimweb/system/application/views/files/ICIM/20110147 6. https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22098CYU05392003%22.&searchmode=basic#XXX 7. https://tanet2019.nsysu.edu.tw/assets/TANET2019_thesis/B1_008.pdf VV ## 報導 1. https://technews.tw/2019/03/17/emotional-recognition-business/ 讓機器了解人類的表情含義,情緒辨識價值逾 6 千億元的產業 **還不錯** > https://www.paulekman.com/product-category/facs/ 2. https://www.viatech.com/tw/2018/08/things-you-can-do-with-facial-recognition-tw/ 人臉辨識技術的五大驚人應用 3. https://www.most.gov.tw/most/attachments/f682d042-5d85-4373-bfda-256eb3fe85d1 4. https://www.ithome.com.tw/tech/121694 **人臉辨識的應用** 5. https://tw.news.yahoo.com/ai%E8%BE%A8%E8%AD%98%E6%83%85%E7%B7%92%E9%82%84%E6%98%AF%E7%9B%A3%E8%A6%96%E6%83%85%E7%B7%92-071714442.html ## api 1. https://cloud.google.com/vision/?hl=zh-tw Vision AI 2. https://azure.microsoft.com/zh-tw/services/cognitive-services/face/ 臉部API **ohohoho太神啦** ## 有關於api的報導 1. https://3c.yipee.cc/63167/google-cloud-vision-%E5%9C%96%E5%83%8F%E8%AD%98%E5%88%A5-api-%E6%AD%A3%E5%BC%8F%E4%B8%8A%E7%B7%9A%E5%9B%89%EF%BC%81?fb_comment_id=1156131377804022_1156132667803893 2. https://technews.tw/2015/11/12/microsoft-emotion-apis/ **ohohoho太神啦** ## api使用教學 1. https://docs.microsoft.com/zh-tw/azure/cognitive-services/face/quickstarts/python ## 無關聯的paper 1. http://ip.csie.ncu.edu.tw/research/research-c21.htm ## 無關的報導 1. https://www.ithome.com.tw/news/122006 2. https://www.mile.cloud/zh-hant/face-detection-for-future/ ## 比較沒有相關的資料 1. https://www.futuretech.org.tw/futuretech/index.php?action=product_detail&prod_no=P0008700001928 ## dlib https://tpu.thinkpower.com.tw/tpu/articleDetails/950 **大推** https://blog.csdn.net/suibianshen2012/article/details/41451287 https://ithelp.ithome.com.tw/articles/10212669 http://hjwang520.pixnet.net/blog/post/404096783-%E5%9C%A8anaconda%E6%88%90%E5%8A%9F%E5%AE%89%E8%A3%9Dopencv%E3%80%81dlib%E5%92%8Cface_recognition https://blog.gtwang.org/programming/python-opencv-dlib-face-detection-implementation-tutorial/ https://chtseng.wordpress.com/2016/12/23/dlib-%E5%A5%BD%E7%94%A8%E7%9A%84%E7%9A%84machine-learning%E5%B7%A5%E5%85%B7-%E4%B8%80/ https://chtseng.wordpress.com/2016/12/31/dlib-%e5%a5%bd%e7%94%a8%e7%9a%84%e7%9a%84machine-learning%e5%b7%a5%e5%85%b7-%e4%ba%8c/ https://www.cnblogs.com/qsyll0916/p/8893790.html **大推** ## opencv https://blog.gtwang.org/tag/opencv/ https://blog.gtwang.org/programming/opencv-basic-image-read-and-write-tutorial/ https://blog.gtwang.org/programming/python-opencv-dlib-face-detection-implementation-tutorial/ **極度大推** https://blog.gtwang.org/programming/opencv-drawing-functions-tutorial/ **大推** https://zhuanlan.zhihu.com/p/52344534 **推** https://www.jianshu.com/p/dd08418c306f **推** https://www.cnblogs.com/skyfsm/p/8276501.html **推** ## compare 1. opencv 速度快 但他的通道是BGR **雷** 2. PIL load圖片是img類別 但其他的是numpy矩陣 opencv matplotlib skimage x PIL x ## 部落格 https://chtseng.wordpress.com/ https://blog.gtwang.org/ http://hemingwang.blogspot.com/2019/08/ai-2020.html http://hemingwang.blogspot.com/ ## android http://tw.gitbook.net/android/android_mediaplayer.html ## 音樂推薦 https://zhuanlan.zhihu.com/p/44188154 https://speakerdeck.com/fukuball/machine-learning-and-the-intelligent-music-application https://speakerdeck.com/fukuball/machine-learning-and-the-intelligent-music-application https://36kr.com/p/5098074 https://buzzorange.com/techorange/2018/01/24/how-ai-find-spotify-weekly-discovery/ https://www.managertoday.com.tw/articles/view/53369 https://ithelp.ithome.com.tw/articles/10196130 https://jerrynest.io/recommender-system/ ## 與資料科學家合作 https://medium.com/@irischenblog/ai%E6%99%82%E4%BB%A3%E7%9A%84%E6%95%B8%E4%BD%8D%E7%94%A2%E5%93%81%E7%B6%93%E7%90%86-%E8%88%87%E8%B3%87%E6%96%99%E7%A7%91%E5%AD%B8%E5%AE%B6%E5%90%88%E4%BD%9C%E7%9A%8410%E5%80%8B%E9%97%9C%E9%8D%B5-1b4eb80a2c93 ## airtable https://support.airtable.com/hc/en-us/articles/206452848-Linked-record-fields https://support.airtable.com/hc/en-us/articles/218734758-A-beginner-s-guide-to-many-to-many-relationships 多對多關聯 https://support.airtable.com/hc/en-us/articles/203255215-Formula-field-reference 使用formula https://support.airtable.com/hc/en-us/articles/202576519 > if 中間表有欄位: > 另建中間表&&將兩者pk使用formula組合成中間表的pk > else: > 不須另建中間表 > end > ## 小demo https://www.storm.mg/lifestyle/440350 **情緒辨識應用在汽車(疲勞)駕駛** https://ictjournal.itri.org.tw/Content/Messagess/contents.aspx?&MmmID=654304432061644411&CatID=654313611255143006&MSID=1002354340410301105 **情緒辨識應用在醫療上** https://www.most.gov.tw/most/attachments/f682d042-5d85-4373-bfda-256eb3fe85d1 **情緒辨識應用在廣告投放(行銷)** https://technews.tw/2019/03/17/emotional-recognition-business/ 讓機器了解人類的表情含義,情緒辨識價值逾 6 千億元的產業 **還不錯** https://3smarket-info.blogspot.com/2016/05/blog-post_30.html **很宏觀的精闢講解!不錯!!** ### 心理學佐證 1. https://cindytaiwan.com/em/Types_of_Emotions.htm 2. https://pansci.asia/archives/14171 **跟我們的主題契合** 3. https://3smarket-info.blogspot.com/2016/05/blog-post_30.html **不錯**
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up