Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Food Image Object Detection and Classification
Search
Leszek Rybicki
February 16, 2017
Research
2
14k
Food Image Object Detection and Classification
Part 1: Detection
Leszek Rybicki
February 16, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
100
How to Patch Image Classifiers
lunardog
0
1.7k
Towards Realistic Predictors - EN
lunardog
0
1.6k
Towards Realistic Predictors
lunardog
1
2k
Deep Learning Hot Dog Detector
lunardog
0
230
Finding beans in burgers: paper reading notes
lunardog
0
1.3k
Kelner: Serve Your Models
lunardog
0
100
Image Analysis at Cookpad
lunardog
1
1.6k
Kelner: serve your models
lunardog
1
330
Other Decks in Research
See All in Research
データサイエンティストをめぐる環境の違い 2024年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
580
Language is primarily a tool for communication rather than thought
ryou0634
4
740
Generative Predictive Model for Autonomous Driving 第61回 コンピュータビジョン勉強会@関東 (後編)
kentosasaki
0
210
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
140
外積やロドリゲスの回転公式を利用した点群の回転
kentaitakura
1
650
秘伝:脆弱性診断をうまく活用してセキュリティを確保するには
okdt
PRO
3
740
Weekly AI Agents News! 9月号 プロダクト/ニュースのアーカイブ
masatoto
2
140
システムから変える 自分と世界を変えるシステムチェンジの方法論 / Systems Change Approaches
dmattsun
3
860
湯村研究室の紹介2024 / yumulab2024
yumulab
0
280
最近のVisual Odometryと Depth Estimation
sgk
1
270
EBPMにおける生成AI活用について
daimoriwaki
0
180
新規のC言語処理系を実装することによる 組込みシステム研究にもたらす価値 についての考察
zacky1972
0
130
Featured
See All Featured
Done Done
chrislema
181
16k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
232
17k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
246
1.3M
How to train your dragon (web standard)
notwaldorf
88
5.7k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
229
52k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
28
8.2k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
27
4.3k
Faster Mobile Websites
deanohume
305
30k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
364
24k
Scaling GitHub
holman
458
140k
What's new in Ruby 2.0
geeforr
343
31k
GraphQLの誤解/rethinking-graphql
sonatard
67
10k
Transcript
Food Image Object Detection and Classification Challenges and Solutions
Part 1: Detection
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
Warning! This presentation contains images that may cause severe drooling
and stomach grumbling. @cookpad
History 歴史
ImageNet KWWSLPDJHQHWRUJ
ImageNet Large Scale Visual Recognition Competition KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
ILSVRC 2010 task Classification )RUHDFKLPDJHDOJRULWKPV ZLOOSURGXFHDOLVWRIDWPRVW REMHFWFDWHJRULHVLQWKH GHVFHQGLQJRUGHURI FRQILGHQFH KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
ILSVRC 2011 tasks 1. Classification 2. *Classification with localization *tester
task
KWWSFVQVWDQIRUGHGXV\OODEXVKWPO Classification + Localization
ILSVRC 2012 tasks 1. Classification 2. Classification with localization 3.
Fine-grained classification
Fine-grained classification KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
AlexNet ,PDJHQHWFODVVLILFDWLRQZLWKGHHSFRQYROXWLRQDOQHXUDOQHWZRUNV $.UL]KHYVN\,6XWVNHYHU*(+LQWRQ$GYDQFHVLQQHXUDOLQIRUPDWLRQ SURFHVVLQJV\VWHPV
ILSVRC 2013 tasks 1. Detection 2. Classification 3. Classification with
localization
ILSVRC 2014 tasks 1. Detection 2. Classification 3. Classification with
localization
Object Detection KWWSFVQVWDQIRUGHGXV\OODEXVKWPO
Deep Learning KWWSVGHYEORJVQYLGLDFRP
ILSVRC 2015 tasks 1. Object detection 2. Object localization 3.
*Object detection from video 4. *Scene classification
ILSVRC 2016 tasks 1. Object localization 2. Object detection 3.
Object detection from video 4. Scene classification 5. Scene parsing
Cookpad 2016
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
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
Where is the food? 料理はどこですか?
ゴール )LQGIRRGLQWKHLPDJHGUDZ DERXQGLQJER[DURXQGWKH IRRGLWHPLQFOXGLQJWKH GLVKLIYLVLEOH
,IWKHUHDUHPXOWLSOHLWHPV GUDZDERXQGLQJER[ DURXQGHDFKRQH ゴール
ground truth bounding box > 0.9 We count it as
a positive detection if Intersection over Union ratio is greater than 0.9. ƴ
QXPEHURIWUXHSRVLWLYHV QXPEHURIJURXQGWUXWKER[HV ƴ ƴ ƴ QXPEHURIWUXHSRVLWLYHV QXPEHURIJHQHUDWHGER[HV 再現率 (precision) (recall)
ƴ ƴ
Methods
1. Build a classifier 2. Pick Regions of Interest 3.
Run classifier on each region 4. Remove duplicate detections IDEA
Fast, Faster R-CNN 5LFKIHDWXUHKLHUDUFKLHVIRUDFFXUDWHREMHFWGHWHFWLRQDQGVHPDQWLFVHJPHQWDWLRQ 5RVV*LUVKLFN-HII'RQDKXH7UHYRU'DUUHOO-LWHQGUD0DOLN )DVWHU5&117RZDUGV5HDO7LPH2EMHFW'HWHFWLRQZLWK5HJLRQ3URSRVDO1HWZRUNV 6KDRTLQJ5HQ.DLPLQJ+H5RVV*LUVKLFN-LDQ6XQ
)DVW5&11 5RVV*LUVKLFN
問題 1. Computational cost 2. Context is important 3. ...but
context can be confusing. KDQG IRRG JUDVV IRRG KWWSSL[DED\FRP
Single Shot Detector 66'6LQJOH6KRW0XOWL%R['HWHFWRU :HL/LX'UDJRPLU$QJXHORY'XPLWUX(UKDQ&KULVWLDQ6]HJHG\ 6FRWW5HHG&KHQJ<DQJ)X$OH[DQGHU&%HUJ
Either The Least Or Most Employable Person Ever 7KH+XIILQJWRQ3RVW JLWKXEFRPSMUHGGLH
SMUHGGLHFRPGDUNQHW ZZZNDJJOHFRPSMUHGGLH Joseph Redmon
You Only Look Once <RX2QO\/RRN2QFH8QLILHG 5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV *LUVKLFN$OL)DUKDGL 'HF
<2/2%HWWHU)DVWHU 6WURQJHU -RVHSK5HGPRQ$OL)DUKDGL
<RX2QO\/RRN2QFH8QLILHG5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV*LUVKLFN$OL)DUKDGL YOLO in Context
None