Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
色恒常性仮説に基づく色補正ライブラリcolorcorrect / 2015-01-31-kan...
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
shunsukeaihara
January 30, 2015
Technology
2.6k
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
色恒常性仮説に基づく色補正ライブラリcolorcorrect / 2015-01-31-kantocv27
@関東CV勉強会 2015/01/31
shunsukeaihara
January 30, 2015
More Decks by shunsukeaihara
See All by shunsukeaihara
BONXを支える技術:発話区間検出(VAD)の話/Akerun & BONX Tech Talk
shunsukeaihara
4
7.8k
Goのnet.TCPConnの話/shibuya.go01
shunsukeaihara
3
890
Norikra in Gunosy Network Ads@Norikra meetup #2
shunsukeaihara
1
6.1k
LevelDB on S3 As A KVS
shunsukeaihara
1
3k
Sparkによる分散処理 / 2015-01-16 PyData.Tokyo#3
shunsukeaihara
11
3.6k
ゼロから始めた Gunosyアドサーバ開発運用記 / 2014-12-16-dots
shunsukeaihara
6
1.2k
Gunosy.Go#5 index/io/log
shunsukeaihara
0
200
Gunosy.go#2 package/compress
shunsukeaihara
0
150
Other Decks in Technology
See All in Technology
Classmethod Company Deck
satoshi7
1
820
How to Design Configuration for Rails Applications
willnet
1
1.1k
Railsで挑む大量データ永続化 〜600億件を永続化するための設計とボトルネックとの戦い〜
occhi
1
1.1k
LLM-as-a-Judgeは本当に信頼できるのか――評価器を評価する話
taka_aki
3
1.1k
freeeにおけるSoftware Factory
freee
PRO
0
360
Metadata - Section 2: Simple Metadata & Meta Tags
mohab1
0
120
Browser Spec: Testing Hotwire with Ruby
takahashim
1
160
トークン化預金DCJPYの取り組みと活用ユースケース
finengine
0
240
Refining Active Record
shugo
0
190
[JAWS-UG彩の国埼玉#12]そろそろ準備する?re:Invent2026をやさしく解説 / reinvent2026-sainokuni
sh_fk2
1
400
Claude for Google Workspaces ポン出し/claude-for-google-workspace-slide-conversion
emiki
0
340
freeeにおける AI を用いた ブラウザ動作確認の自動化の取り組み
freee
PRO
0
160
Featured
See All Featured
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
2
6.3k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.8k
Prompt Engineering for Job Search
mfonobong
0
530
The Power of CSS Pseudo Elements
geoffreycrofte
82
6.6k
The Pragmatic Product Professional
lauravandoore
37
7.5k
sira's awesome portfolio website redesign presentation
elsirapls
0
460
SEO Brein meetup: CTRL+C is not how to scale international SEO
lindahogenes
2
2.9k
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
420
The agentic SEO stack - context over prompts
schlessera
0
970
Technical Leadership for Architectural Decision Making
baasie
3
610
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
1.1k
Transcript
colorcorrect ৭߃ৗੑԾઆʹجͮ͘৭ิਖ਼ϥΠϒϥϦ Gunosy inc Shunsuke Aihara
ࣗݾհ • ҄൧ݪढ़հ (http://argmax.jp) @shunsukeaihara • GunosyͷϚωʔδϟʔ • ࠂ৴γεςϜͷ։ൃશମͱR&DܥΛ୲ •
ઐ: ܭࢉݴޠֶ • PythonͱඇಉظࢄγεςϜΛΉ • DNN࣭มͱ͔झຯͰͬͯΔ • ը૾ॲཧɾԻ৴߸ॲཧͰ͍Ζ͍ΖϥΠϒϥϦ࡞ͬͯΔ • https://bitbucket.org/aihara
͜Εը૾ೝࣝͷͨΊͷ ຯͳલॲཧͷͰ͢
colorcorrect
৭߃ৗੑ/໌Δ͞߃ৗੑͷԾઆʹج͖ͮ ม৭ɾwhite baranceͷζϨΛࣗಈิਖ਼
ը૾ͷޫݯ৭ͱϗϫΠτόϥϯε ࣮σʔλͰόϥόϥ • ৭Λ༻͍ͨମೝࣝΛߦ͓͏ͱ͢Δͱɺֶशσʔληοτͱ৭͕ͣΕ͍ͯΔͱఆਫ਼ མͪΔ • ৭ใΛ༻͍ͨBag-Of-Keypointܥͷख๏Ͱ݁ߏ৭ิਖ਼͕ޮ͍ͯ͘Δ • ྨࣅը૾ݕࡧ /
ܠ؍ը૾͔Βͷମݕग़ͱ͔࡞ͬͨ࣌ʹ૬ϋϚͬͨ • Deep Learningͱ͔͍Ζ͍Ζظͯ͠Δ͚Ͳɺ࣮ࡍʹࣄͰֶशσʔληοτूΊΔͱ ͳΔͱ͍ΖΜͳࡱӨ݅ͷը૾ूΊΔͷ݁ߏେม • ෳর໌݅ʹର͢ΔData AugmentationΑ͘Θ͔Βͳ͍ • ͋ͱɺը૾ͷݟͨΩϨΠʹ͍ͨ͠ͱ͔͍Ζ͍Ζ͋Δ • ͳΜͱָ͔͔ͨͬͨ͠ͷͰิਖ਼ख๏ͷจͱ͔͍Ζ͍Ζௐͨ
༻్ • ม৭ͨࣸ͠ਅͷิਖ਼ • ઃఆϛεͬͯࡱͬͨࣸਅͷमਖ਼ • ίϯσδͰઃఆؒҧ͑ͯࡱͬͨࣸਅͱ͔ • ମೝࣝͷલॲཧ •
దʹެ։͓͍ͯͨ͠ΒCVPR2013ͷจͰ࣮ ࡍʹΘΕͨʂ
͋ͱ᧙৭ը૾Λ͔ͨͬͨ͠ ͜Ε৭ͷใ͕ࣦΘΕ͍ͯΔͷͰͲ͏ͬͯϜϦ
pip install colorcorrect
৭߃ৗੑ (Color Constancy) ໌Δ͞߃ৗੑ (lightness constancy)
• র໌ޫͷεϖΫτϧ͕มԽͯ͠ɺମ৭ͷ ೝେ͖͘มԽ͠ͳ͍(ݩͷ৭͕ೝࣝͰ͖Δ) ৭߃ৗੑ
νΣοΧʔγϟυʔࡨࢹ ໌Δ͞ͱਓ͕ؒೝͨ͠ͷͱҟͳΔ ྡ෦ҐͷίϯτϥετʹӨڹΛड͚ͯҟͳΔೝ 'SPN8JLJNFEJB$PNNPOT
৭ͷ֮ͷ؆୯ͳϞσϧ • ʹೖࣹ͢ΔޫޫݯޫͱରͷޫࣹͰܾ· Δ • ৭߃ৗੑೖࣹޫ͔ΒޫݯޫΛਪఆͯ͠ɺޫࣹ Λਪఆ͢Δͱఆٛग़དྷΔ S( ) =
I( ) · R( ) • S(λ) ೖࣹޫ • I(λ) ޫݯޫ • R(λ) ମͷޫࣹ
৭߃ৗੑԾઆͷ؆୯ͳ • փ৭Ծઆ • ന৭ޫݯԼͷ߹ɺࢹ֮ͷ৭ͷฏۉΛऔΔͱփ৭ (127,127,127)ʹͳΔͣͳͷͰͦͷζϨΛิਖ਼͢Δ • ً - ৭૬ؔ
• ࢹ֮ͷ৭ʹภΓ͕͋Δ߹փ৭ԾઆͰ߃ৗੑΛ୲อग़ དྷͳ͍ͷͰɺًͱ৭ͷ૬͔ؔΒ৭ͷภΓ͕ޫݯʹΑΔ͔ݩ ͷମ৭ʹΑΔ͔ਪఆͯ͠ิਖ਼ • ͜ΕΒΛϕʔεʹ༷ʑͳΞϧΰϦζϜ͕ఏҊ͞Ε͍ͯΔ
Algorithms
࣮ͨ͠৭߃ৗੑΞϧΰϦζϜ • gray world • max white • stretch •
retinex, retinex with adjust • weighted grey world • standard deviation weighted grey world • luminance weighted gray world • standard deviation and luminance weighted gray world • automatic color equalization • ->ώϡʔϦεςΟΫε͚ͩͲิਖ਼ྗ͕͍͢͝
Implementation
࣮ • PythonʹΑΔ࣮(2ܥ) • PIL • Numpy • ͕ඞཁͳ෦C++ͷϥΠϒϥϦΛ numpy.ctypesͰϥοϓ
• pip install colorcorrectͰར༻Մೳ
DEMO http://colorcorrect.argmax.jp/
·ͱΊ • खܰʹը૾ͷ৭ิਖ਼͕ग़དྷͯศརͳͷͰͬͯΈ ͍ͯͩ͘͞ • Python3ܥ + PillowରԠͦΖͦΖ͠·͢ • ԻͷલॲཧϥΠϒϥϦͱ͔ެ։ͯ͠·͢
• https://bitbucket.org/aihara/pyssp • Gunosyʹମೝࣝɾը૾clipͷࣄ͋Γ·͢