Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Food Image Object Detection and Classification

C1595f6a99fc51c0fb8e04b54863dbeb?s=47 Leszek Rybicki
February 16, 2017
Research
2
14k

Food Image Object Detection and Classification

Part 1: Detection

C1595f6a99fc51c0fb8e04b54863dbeb?s=128

Leszek Rybicki

February 16, 2017
Tweet

More Decks by Leszek Rybicki

See All by Leszek Rybicki
Let's talk about Fakes
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
26
How to Patch Image Classifiers
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
1.1k
Towards Realistic Predictors - EN
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
1k
Towards Realistic Predictors
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
1
1.2k
Deep Learning Hot Dog Detector
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
130
Finding beans in burgers: paper reading notes
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
980
Kelner: Serve Your Models
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
0
81
Image Analysis at Cookpad
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
1
830
Kelner: serve your models
C1595f6a99fc51c0fb8e04b54863dbeb?s=48 lunardog
1
140

Other Decks in Research

See All in Research
意思決定を最大化するための”ループ”とループを回すための”施策”
2037edbccc4e9b1be0b328cd9d032dc0?s=48 masadooon
0
720
2021年度官庁訪問に関するアンケート調査
Cf20487f38f9ad92fb7f867fb1c215d7?s=48 xkasumi
0
280
PLDI '21論文読み会: Cyclic Program Synthesis
5148cbb852e980b3b3d0e71d579ddbf8?s=48 ideininc
0
590
中国のオープンソースムーブメント：その現状と可能性 #中国オープンソース
9db5ad8f2c24b5cfaa9c9e09ca275af6?s=48 takasumasakazu
2
630
Generating a Pairwise Dataset for Click-through Rate Prediction of News Articles Considering Positions and Contents
B1cc148711c6a37a5c922b6e72a4ad52?s=48 upura
0
110
幼少期の自然体験が理科学習への態度に及ぼす影響
4e437713540d4a32369b9c9f1b624e9c?s=48 arumakan
0
860
JGS594 Lecture 18
B546a9b97d993392e4b22b74b99b91fe?s=48 javiergs
PRO
0
350
Blockchains dans la cybersécurité et cybersécurité des blockchains
9b368ee76aa2b65a870563d4829a4d5e?s=48 rlifchitz
0
110
論述リビジョンのためのメタ評価基盤
2d4315a0cfbfeb12fdc48bbadd955cd9?s=48 chemical_tree
0
140
第14回チャンピオンズミーティング・ジェミニ杯ラウンド1集計 / Umamusume Gemini 2022 Round１
9782dd351a8f1737d4ef02d839e821f9?s=48 kitachan_black
0
580
Adversarial Training
310b7634b5b2a5926a6987720c884170?s=48 hirokiadachi
4
1.4k
データサイエンティストと博士の専門性
E0e299d5e09e4726e1a6c808eb58b7a3?s=48 mtakano
1
180

Featured

See All Featured
XXLCSS - How to scale CSS and keep your sanity
1b8ad785acdd1ce1c99914b1c2a4e10e?s=48 sugarenia
236
1M
Designing with Data
F57e2136eb9895eb95ff5dc8a1c02677?s=48 zakiwarfel
91
3.9k
Three Pipe Problems
11c84dff30266b907714802088852677?s=48 jasonvnalue
89
8.7k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
95d9f37115fbb0d13135d0f77132f856?s=48 morganepeng
104
16k
Typedesign – Prime Four
A0517b08532aec8ab2aae3f65d40ad86?s=48 hannesfritz
33
1.3k
Streamline your AJAX requests with AmplifyJS and jQuery
9cde37f47e4a800ea081ea42de8d749a?s=48 dougneiner
126
8.5k
Clear Off the Table
Ef32e0b1ac5082450dc8c1fca3a26b5c?s=48 cherdarchuk
79
280k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
3d4519fd34b76fb265fc0237f3792bd4?s=48 danielanewman
212
20k
Visualization
170b760e0147792d0140e59ec78e9893?s=48 eitanlees
124
11k
The Power of CSS Pseudo Elements
5b6a2bd86ef643786a381a212e0ef2f1?s=48 geoffreycrofte
46
3.9k
Creatively Recalculating Your Daily Design Routine
48c098b6579220a67a6ba949be6e4b5a?s=48 revolveconf
207
10k
Building Flexible Design Systems
91cefdf141106fa10674aae74ce05890?s=48 yeseniaperezcruz
310
34k

Transcript

  1. Food Image Object Detection and Classification Challenges and Solutions

  2. Part 1: Detection

  3. 自己紹介 • リビツキ　レシェック • ポーランド出身 • 2016~ クックパッド • github:

    lunardog

  4. Warning! This presentation contains images that may cause severe drooling

    and stomach grumbling. @cookpad

  5. History 歴史

  6. ImageNet KWWSLPDJHQHWRUJ

  7. ImageNet Large Scale Visual Recognition Competition KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&

  8. ILSVRC 2010 task Classification )RUHDFKLPDJHDOJRULWKPV ZLOOSURGXFHDOLVWRIDWPRVW REMHFWFDWHJRULHVLQWKH GHVFHQGLQJRUGHURI FRQILGHQFH KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&

  9. ILSVRC 2011 tasks 1. Classification 2. *Classification with localization *tester

    task

  10. KWWSFVQVWDQIRUGHGXV\OODEXVKWPO Classification + Localization

  11. ILSVRC 2012 tasks 1. Classification 2. Classification with localization 3.

    Fine-grained classification

  12. Fine-grained classification KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&

  13. AlexNet ,PDJHQHWFODVVLILFDWLRQZLWKGHHSFRQYROXWLRQDOQHXUDOQHWZRUNV $.UL]KHYVN\,6XWVNHYHU*(+LQWRQ$GYDQFHVLQQHXUDOLQIRUPDWLRQ SURFHVVLQJV\VWHPV

  14. ILSVRC 2013 tasks 1. Detection 2. Classification 3. Classification with

    localization

  15. ILSVRC 2014 tasks 1. Detection 2. Classification 3. Classification with

    localization

  16. Object Detection KWWSFVQVWDQIRUGHGXV\OODEXVKWPO

  17. Deep Learning KWWSVGHYEORJVQYLGLDFRP

  18. ILSVRC 2015 tasks 1. Object detection 2. Object localization 3.

    *Object detection from video 4. *Scene classification

  19. ILSVRC 2016 tasks 1. Object localization 2. Object detection 3.

    Object detection from video 4. Scene classification 5. Scene parsing

  20. Cookpad 2016

  21. 画像データセット 1997年~ レシピ数：国内約260万 + 国外 + つくれぽ + 手順写真 17言語、60カ国

    ※数字は2017年02月時点のものです

  22. 画像解析の研究関心 • これは料理ですか？ • どの料理ですか？ • 料理はどこですか？ • 。。。 Part

    2

  23. Where is the food? 料理はどこですか？

  24. ゴール )LQGIRRGLQWKHLPDJHGUDZ DERXQGLQJER[DURXQGWKH IRRGLWHPLQFOXGLQJWKH GLVKLIYLVLEOH

  25. ,IWKHUHDUHPXOWLSOHLWHPV GUDZDERXQGLQJER[ DURXQGHDFKRQH ゴール

  26. ground truth bounding box > 0.9 We count it as

    a positive detection if Intersection over Union ratio is greater than 0.9. ƴ

  27. QXPEHURIWUXHSRVLWLYHV QXPEHURIJURXQGWUXWKER[HV ƴ ƴ ƴ QXPEHURIWUXHSRVLWLYHV QXPEHURIJHQHUDWHGER[HV 再現率 (precision) (recall)

    ƴ ƴ

  28. Methods

  29. 1. Build a classifier 2. Pick Regions of Interest 3.

    Run classifier on each region 4. Remove duplicate detections IDEA

  30. Fast, Faster R-CNN  5LFKIHDWXUHKLHUDUFKLHVIRUDFFXUDWHREMHFWGHWHFWLRQDQGVHPDQWLFVHJPHQWDWLRQ 5RVV*LUVKLFN-HII'RQDKXH7UHYRU'DUUHOO-LWHQGUD0DOLN  )DVWHU5&117RZDUGV5HDO7LPH2EMHFW'HWHFWLRQZLWK5HJLRQ3URSRVDO1HWZRUNV 6KDRTLQJ5HQ.DLPLQJ+H5RVV*LUVKLFN-LDQ6XQ 

    )DVW5&11 5RVV*LUVKLFN

  31. 問題 1. Computational cost 2. Context is important 3. ...but

    context can be confusing. KDQG IRRG JUDVV IRRG KWWSSL[DED\FRP

  32. Single Shot Detector  66'6LQJOH6KRW0XOWL%R['HWHFWRU :HL/LX'UDJRPLU$QJXHORY'XPLWUX(UKDQ&KULVWLDQ6]HJHG\ 6FRWW5HHG&KHQJ<DQJ)X$OH[DQGHU&%HUJ

  33. Either The Least Or Most Employable Person Ever 7KH+XIILQJWRQ3RVW JLWKXEFRPSMUHGGLH

    SMUHGGLHFRPGDUNQHW ZZZNDJJOHFRPSMUHGGLH Joseph Redmon

  34. You Only Look Once  <RX2QO\/RRN2QFH8QLILHG 5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV *LUVKLFN$OL)DUKDGL 'HF

    <2/2%HWWHU)DVWHU 6WURQJHU -RVHSK5HGPRQ$OL)DUKDGL

  35. <RX2QO\/RRN2QFH8QLILHG5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV*LUVKLFN$OL)DUKDGL YOLO in Context

  36. None