続・絵を読む技術 Pythonで読むイラストの心理戦略 / The Art of Reading Illustrations 2nd

Slide 1

Slide 1 text

1Z$PO+1 ଓɾֆΛಡΉٕज़ 1ZUIPOͰಡΉΠϥετͷ৺ཧઓུ )JSPTBKJ !IJSPTBKJ ʗͻΖ͞͡ !IJSPTBKJ@F[

Slide 2

Slide 2 text

͸͡Ίʹ

Slide 3

Slide 3 text

ଓฤͰ͕͢ɺ୯ಠͰ΋ָ͠ΊΔ಺༰Ͱ͢ɻ΋ָ͠͠ΊͨΒɺڈ೥ͷൃද΋νΣοΫͯ͠Έ͍ͯͩ͘͞ɻ ͜ͷߨԋ͸ଓฤͰ͢ ࡢ೥ղઆ͖͠Εͳ͔ͬͨ಺༰Λਂ۷Γ͠ɺΑΓײੑతͳઓུΛඥղ͖·͢ ࠓ ճ

Slide 4

Slide 4 text

ʮͻΖ͞͡ )JSPTBKJʯͱ͍͏໊લͰ׆ಈ͢Δਓɻେ޷͖ͳΠϥετʹғ·Εɺ޾ͤͳ೔ʑΛૹ͍ͬͯΔɻ ࣾձਓֆඳ͖ ͻΖ͞͡ʢ!IJSPTBKJ@F[ʣ ɾ1ZUIPOྺ̒೥͘Β͍ ɾΠϥετΛ؍Δͷ͕޷͖ ɾσδλϧֆࢣ̏೥໨ ɾΠϥετΛඳ͘ͷ͕޷͖ ͜ͷϓϨθϯΛ͢Δਓ ޏΘΕ8FCΤϯδχΞ )JSPTBKJʢ!IJSPTBKJʣ

Slide 5

Slide 5 text

͜ͷ̎ϲ݄ͰɺֆࢣΛऔΓר͘؀ڥ͸େ͖͘มΘͬͨɻͦͯ͠ࠓ΋ɺֆࢣ͸ա౉ظʹཱ͍ͬͯΔɻ ·ͣ͸ɺ͜ͷ࿩୊ʹ৮Εͳ͚Ε͹… ͍·ɺ"*ֆࢣͷ੎͍͕ࢭ·Βͳ͍ɻ l"*͕ֆΛඳ͘ʁਐԽ͢Δը૾ੜ੒"*ͷ࠷લઢc/),lΑΓ ೥݄ը૾ੜ੒"*͕୆಄ ೥݄຤ֆฑֶश"*͕೾໲ ೥݄಄/PWFM"*͕୆಄ lΠϥετϨʔλʔͷݸੑΛֶΜͰֆΛlແݶੜ੒z͢Δ"*αʔϏc*5NFEJBlΑΓ l༷ʑͳݒ೦΍໰୊Λ๊͑ͭͭ΋ʮ͓ֆ͔͖"*ʯͷਐԽ͸ࢭ·Βͣc:BIPPχϡʔεlΑΓ

Slide 6

Slide 6 text

؆୯ͳϑϨʔζ΍ϥϑ͕͋Ε͹ɺ୭Ͱ΋ϓϩڃͷΠϥετΛੜ੒Ͱ͖Δ"*ֆࢣɻଟ͘ͷֆࢣ͸ಈ༳͢Δ͕ ͍·ɺ"*ֆࢣͷ੎͍͕ࢭ·Βͳ͍ɻ "*ֆࢣͷ͍͢͝ͱ͜Ζ ্ख͍ֆ͕͙͢ඳ͚Δ ΤϞ͍ֆ͕͙͢ඳ͚Δ lʮͱΜͰ΋ͳ͘ϋΠΫΦϦςΟʔʯ࿩୊ͷը૾"*ʮ/PWFM"*ʯͰͻͨ͢Βೋ࣍ݩඒগঁͱඒগ೥Λੜ੒ͯ͠Έͨc*5NFEJBlΑΓ AIʹֆࢣͷ࢓ࣄΛୣΘΕΔ... ͱ୰͘ਓ΋ ·ͣ͸ɺ͜ͷ࿩୊ʹ৮Εͳ͚Ε͹…

Slide 7

Slide 7 text

͋͘·Ͱ΋ɺֆͷ্ख͞͸ֆࢣͷٕೳͷҰͭɻֆ্͕ख͍ͱ͍͏ཧ༝͚ͩͰɺϑΝϯʹͳΔ༁Ͱ͸ͳ͍ɻ Q. ֆࢣ͸ֆ্͕ख͚Ε͹͍͍ͷʁ lʲϑΥϩϫʔ਺ʹըྗͳͷʁʳ͜ͷ౴͕͑Θ͔ͬͯΔਓ͸ɺΊͪΌͪ͘Ό੒௕͠·͢ʂzম·ΏΔͷ͓ֆ͔͖ͪΌΜͶΔc:PVUVCFʢʣlΑΓ "ɹॏཁͳͷ͸ɺϑΝϯΛت͹ͤΔ͜ͱɻ χʔζʹԠ͑Δ͜ͱͰɺϑΝϯ͸تͿɻֆͷ্ख͞͸χʔζʹԠ͑Δखஈɻ

Slide 8

Slide 8 text

ࠓޙ͸ɺ"*ͷීٴͰΠϥετͷΫΦϦςΟ͸શମతʹ্͕Δɻͦͯ͠ɺֆࢣͷϒϥϯυԽ͕͞ΒʹਐΉɻ Q. AIֆࢣͷొ৔ͰԿ͕มΘΔ͔ʁ lෆ͕͍҆ͬͺ͍ʜ😭৽ਓֆࢣ͸"*ʹͭͿ͞ΕΔʁʲ3BEJP$MPTFUʳσΟʔϓϒϦβʔυΕͰ͌͘ΖzσΟʔϓϒϦβʔυc:PVUVCFʢʣlΑΓ "ɹ"*͸ΠϥετΛ୹࣌ؒͰߴΫΦϦςΟʹ͢ΔิॿπʔϧʹͳΔɻ ͦͯ͠Πϥετ͸ʮͲΜͳֆࢣ͕ඳ͍͔ͨʯ͕ΑΓॏཁࢹ͞ΕΔͩΖ͏ɻ

Slide 9

Slide 9 text

"*ΛֆΛ্ख͘ඳͨ͘Ίͷಓ۩ͱͯ͠࢖͍ͭͭɺΑΓޮ཰తʹϑΝϯͷχʔζʹԠ͑ΔಓΛ୳Γଓ͚Α͏ɻ Q. ͜Ε͔Βֆࢣ͸Ͳ͏͢Δ΂͖ʁ "ɹֆΛ্ख͘ඳͨ͘Ίʹ"*Λ׆༻͢Δͷ͸΋ͪΖΜɺ ΋ͬͱ৭ΜͳՄೳੑʹ໨Λ޲͚Δ΂͖ɻ ͻ Ζ ͞ ͡ Ұॹʹ χʔζʹԠ͑ΔઓུΛߟ͑Αʂ θ ώ

Slide 10

Slide 10 text

͔͜͜Βຊ୊

Slide 11

Slide 11 text

"*ͱڞʹߟ͑Α͏ͱ͍ͬͨઓུɻ͜ͷϓϨθϯͰ͸ɺΠϥετͷ৺ཧઓུΛ1ZUIPOΛަ͑ͯղઆ͢Δɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ

Slide 12

Slide 12 text

ͪͳΈʹલճͷൃදͰ͸ɺઓུΛʮֆࢣͷૂ͍ʯͱݴ͍׵͑ͯղઆͨ͠ɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ ֆࢣͷૂ͍

Slide 13

Slide 13 text

ࠓճͷ࿩͸୯ಠͰ΋ָ͠ΊΔ͕ɺલճͷൃදͱͷ஍ଓ͖ͳͷͰɺ؆୯ʹҐஔ෇͚ΛৼΓฦΔɻ ͜ͷϓϨθϯͷझࢫ Πϥετͷ৺ཧઓུΛ஌Δ ֆࢣͷૂ͍ Π લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍

Slide 14

Slide 14 text

લճ͸ɺΠϥετͷઓུΛ̎ͭʹେผͯ͠ղઆɻͦͷதͰʮͳʹΛ఻͑Δ͔ʯ͸ߏ੒ཁૉͷ঺հʹཹ·ͬͨɻ લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍ ֆࢣͷૂ͍ Ͳ͜Λ఻͑Δ͔ ͳʹΛ఻͑Δ͔ γΣΠϓ ϥΠϯ ৭ Πϥετͷ৺ཧઓུͷҐஔ෇͚ ޫʢ໌౓ʣ ΩϟϥΫλʔ ʜ ߏਤͷࠎ૊ΈΛߏ੒ ʜ ഑৭όϥϯεΛ౷੍ ʜ ʜ য఺ͷҹ৅Λ੍ޚ ײ৘໘Λࢧ഑ Τ Ϟ Έ ʜ ʢະղઆʣ ࡁ

Slide 15

Slide 15 text

ࠓճ͸ͦΜͳΠϥετͷߏ੒ཁૉͷதͰ΋ɺ৺ཧʹಇ̏ͭ͘ͷཁૉΛऔΓ্͛ͯਂ۷Γ͢Δɻ લ ճ · Ͱ ͷ ͋ Β ͢ ͡ ͥ Μ ͔ ͍ ֆࢣͷૂ͍ Ͳ͜Λ఻͑Δ͔ ͳʹΛ఻͑Δ͔ γΣΠϓ ϥΠϯ ৭ ޫʢ໌౓ʣ ΩϟϥΫλʔ ৺ཧʹޮ͘ ̏ཁૉ ࠓճͷ ਂ۷Γର৅ 🔎 Πϥετͷ৺ཧઓུͷҐஔ෇͚ ࡁ

Slide 16

Slide 16 text

ઓུϐϥϛουͰ੔ཧ͢Δͱ͜ͷ௨ΓɻҾ͖ग़͍ͨ͠ײ৘΍৘ಈʹ߹Θͤͯ৺ཧઓུΛඳ͚ΔΑ͏ʹͳΖ͏ɻ Πϥετͷ৺ཧઓུϐϥϛου ໨త ઓུ ઓज़ ΠϥετΛ؍Δਓͷײ৘΍৘ಈΛҾ͖ग़͢ ޮՌతͳΩϟϥΫλʔ΍ޫʗ৭ͷํ਑ΛબͿ બΜͩํ਑͔Β஌ࣝ΍࣮ײΛ΋ͱʹඳ͘ ୡ੒͍ͨ͠ΰʔϧ ໨తΛୡ੒͢ΔγφϦΦ ઓུΛୡ੒͢ΔΞΫγϣϯ

Slide 17

Slide 17 text

ࠓճͷϓϨθϯͷྲྀΕ͸ͪ͜ΒɻͦΕͧΕͷ৺ཧઓུΛɺదٓ1ZUIPOεΫϦϓτΛަ͑ͳ͕Βղઆ͢Δɻ આ໌͢ΔྲྀΕ ޫͱ৭ͷ৺ཧઓུ ɾશਓྨʹޮ͘ΩϟϥΫλʔͷັྗΛ୳Δ ɾ1ZUIPOͰΩϟϥΫλʔͷັྗΛݕग़͢Δ ɾ഑৭ʹΑΔίϯηϓτͱృΓʹΑΔͩ͜ΘΓΛ஌Δ ɾ1ZUIPOͰίϯηϓτͱͩ͜ΘΓΛ୳Δ ΩϟϥΫλʔͷ৺ཧઓུ ͸͡Ίʹ ࡁ

Slide 18

Slide 18 text

ΩϟϥΫλʔͷ৺ཧઓུ ̍

Slide 19

Slide 19 text

ΩϟϥΫλʔ͕ొ৔͢ΔΠϥετʹ͸ɺେ͖̎ͭ͘ͷझࢫ͕͋Δɻ̎ͭͷझࢫ͕ڞଘ͢Δ͜ͱ΋ଟ͍͕ ΩϟϥΫλʔΠϥετͷ̎େझࢫ ετʔϦʔ΍৔໘ Λ఻͑Δ ΩϟϥΫλʔͷັྗ Λ఻͑Δ

Slide 20

Slide 20 text

ࠓճ͸લऀͷʮΩϟϥΫλʔͷັྗΛ఻͑ΔʯʹղઆΛߜΔʢޙऀ͸ΩϟϥҎ֎ͷཁૉ͕ෳࡶʹབྷΉͨΊʣ ΩϟϥΫλʔΠϥετͷ̎େझࢫ ετʔϦʔ΍৔໘ Λ఻͑Δ ΩϟϥΫλʔͷັྗ Λ఻͑Δ Ω ϥ ͕ ओ ໾ Ω ϥ ͸ આ ໌ ࡐ ྉ

Slide 21

Slide 21 text

ΩϟϥΫλʔͷັྗ͕఻ΘΔ৚݅͸ɺϙʔζͱද৘ͰɺΩϟϥΫλʔੑ͕෼͔Γ΍͘͢දݱͰ͖͍ͯΔ͜ͱɻ ັྗతͳΩϟϥΫλʔΠϥετͷ৚݅ ΩϟϥΫλʔੑ ͕Θ͔Γ΍͍͢͜ͱ ΩϟϥΫλʔੑ ͦͷΩϟϥΫλʔͷ࣋ͪຯͱͳΔੑ֨΍ಛ௃ͷ͜ͱɻ ӳޠͰ͍͏lQFSTPOBMJUZzͷχϡΞϯε͕͍ۙɻ Πϥετɿ© ͻΖ͞͡ʢʮ΢Ϛ່ϓϦςΟʔμʔϏʔೋ࣍૑࡞ΨΠυϥΠϯʯ९कʣ lΩϟϥΫλʔΠϥετͷҾ͖ग़͠Λ૿΍͢ϙʔζͱද৘ͷԋग़ςΫχοΫΧϦϚϦΧcᠳӭࣾʢʣlΑΓ ϙʔζ ද৘ ʴ Ͱදݱ ΩϟϥΫλʔɿΠΫϊσΟΫλεʢ© ΢Ϛ່ϓϦςΟʔμʔϏʔ$ZHBNFTʣ

Slide 22

Slide 22 text

ΩϟϥΫλʔੑʢϙʔζʗද৘ʣ͸ɺ఻͍͑ͨײ৘΍γνϡΤʔγϣϯΛ΋ͱʹࢼߦࡨޡͯ͠σβΠϯ͢Δɻ Q. ϙʔζʗද৘͸Ͳ͏ܾ·Δ͔ lʲΠϥετϝΠΩϯάʳߏਤΛܾΊΔ࣌ʹߟ͍͑ͯΔ͜ͱʲ΢Ϛ່ϚϠϊτοϓΨϯʳzֆ༿·͠ΖͷͪΌΜͶΔc:PVUVCFʢʣlΑΓ "ɹશͯΦʔμʔϝΠυɻ ඳ͘ΩϟϥΫλʔΛܾΊɺදݱ͍ͨ͜͠ͱΛܾΊɺ࢓্͛Δֆͷߏ૝͢Δɻ ΩϟϥΫλʔɿϚϠϊτοϓΨϯʢ© ΢Ϛ່ϓϦςΟʔμʔϏʔ$ZHBNFTʣ :PVUVCFಈըɿ© ֆ༿·͠Ζ

Slide 23

Slide 23 text

ΩϟϥΫλʔੑʢϙʔζʗද৘ʣ͸ɺ఻͍͑ͨײ৘΍γνϡΤʔγϣϯΛ΋ͱʹࢼߦࡨޡͯ͠σβΠϯ͢Δɻ Q. ϙʔζʗද৘͸Ͳ͏ܾ·Δ͔ lʲΠϥετϝΠΩϯάʳߏਤΛܾΊΔ࣌ʹߟ͍͑ͯΔ͜ͱʲ΢Ϛ່ϚϠϊτοϓΨϯʳzֆ༿·͠ΖͷͪΌΜͶΔc:PVUVCFʢʣlΑΓ "શͯΦʔμʔϝΠυɻ ɹඳ͘ΩϟϥΫλʔΛܾΊɺදݱ͍ͨ͜͠ͱΛܾΊɺ࢓্͛Δֆͷߏ૝͢Δɻ ౎౓ΦʔμʔϝΠυͱ͸͍͑ ఆੴ͸Կ͔͋Δ͸ͣ 🤔

Slide 24

Slide 24 text

ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴ͸͋ΔɻதͰ΋ࠓճ͸ɺશਓྨʹޮ͍͘͢͝ఆੴΛ̎ͭ঺հ͢Δɻ ັྗతͳΩϟϥΫλʔͷఆੴ ᶃίϯτϥϙετ ࠷΋ݪ࢝తͳఆੴ ࠷΋୅දతͳఆੴ ᶄੑઓུ

Slide 25

Slide 25 text

ఆੴͷҰͭ͸ɺίϯτϥϙετɻلݩલɺݹ୅ΪϦγΞ࣌୅ͷூࠁͰൃ໌͞Εɺࠓ΋ड͚ܧ͕ΕΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ίϯτϥϙετͱ͸ +PIO4JOHFS4BSHFOU r cQVCMJDEPNBJO 4BOESP#PUUJDFMMJ r cQVCMJDEPNBJO 5IFCJSUIPG7FOVT .BEBNF9 .JDIFMBOHFMP r c$$#:4" %BWJE ίϯτϥϙετ͸ɺ ମॏͷଟ͕͘ย٭ʹ͔͔ͬͨ࢟੎ͷ͜ͱɻ ༂ಈײΛੜΉ࢟੎ͱͯ͠لݩલ̐ੈلࠒʹൃ໌ɻ ݱ୅ʹ΋޿͘ड͚ܧ͕Ε͍ͯΔɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ

Slide 26

Slide 26 text

ͳͥίϯτϥϙετ͕ΩϟϥΫλʔΛັྗతʹ͢Δͷ͔ɻ·ͣ͸ɺͦͷҰͭͷཧ༝Λղઆ͢Δɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ

Slide 27

Slide 27 text

ย଍ʹମॏ͕͔͔Δͱࠎ൫͕܏͖ɺͦΕʹ࿈ΕΒΕͯ਎ମதͷ෦ҐͰόϥϯε͕औΒΕΔʢཱͪ௚Γ൓Ԡʣ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ

Slide 28

Slide 28 text

ͭ·Γɺશ਎ͰͷδΣενϟʔ͕ൃੜ͠ɺߦಈ΍ҙࢥɺͻ͍ͯ͸ΩϟϥΫλʔੑ͕෼͔Γ΍͍͢ঢ়ଶʹͳΔɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾย଍ʹମॏ͕͔͔ͬͨ࢟੎͸ɺ ɹߦಈͷ్தͰෆ҆ఆͳঢ়ଶɻ ɾମͷॏ৺ʹζϨ͕ੜ͡ɺ ɹແҙࣝతʹ಄ɾମɾ྆ख଍ͰόϥϯεΛऔΔɻ 㲈શ਎Λ࢖ͬͨδΣενϟʔ ΩϟϥΫλʔੑ͕શ਎ʹදΕͨঢ়ଶ

Slide 29

Slide 29 text

ɾҰํͰɺΩϟϥΫλʔΛݟΔਓͷ࿩ɻ ɾਓؒ͸ຊೳతʹɺ໨ͷલͷةػΛճආ͢ΔͨΊʹɺ ɹ໨ͷલͰ࣍ʹى͜Γ͏Δ͜ͱΛৗʹਪଌ͍ͯ͠Δɻ ɾߦಈͷ్தͷΩϟϥΫλʔ͸ਅͬઌʹ෼ੳͨ͘͠ͳΔɻ ҰํͰͦΕΛݟΔਓ͸ɺةػճආͷੜཧ൓Ԡ͕ಇ͖ɺ໨ͷલͷδΣενϟʔʹ໨ΛୣΘΕΔɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ

Slide 30

Slide 30 text

ͦͯ͠ΩϟϥΫλʔੑͷ໌շ͔͞Β಺໘Λ஌Γɺ಺໘Λ஌Δͱਓ͸ͦͷਓ෺ʹ޷ײΛ࣋ͭʢख़஌ੑͷݪཧʣ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ɾҰํͰɺΩϟϥΫλʔΛݟΔਓͷ࿩ɻ ɾਓؒ͸ຊೳతʹɺ໨ͷલͷةػΛճආ͢ΔͨΊʹɺ ɹ໨ͷલͰ࣍ʹى͜Γ͏Δ͜ͱΛৗʹਪଌ͍ͯ͠Δɻ ɾߦಈͷ్தͷΩϟϥΫλʔ͸ਅͬઌʹ෼ੳͨ͘͠ͳΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ΩϟϥΫλʔͷ಺໘Λ஌Δͱɺͦͷਓ෺΁ͷ޷ײ͕૿͢

Slide 31

Slide 31 text

ͦΜͳҰ࿈ͷਓؒͷशੑΛύοέʔδԽͨ͠ͷ͕ίϯτϥϙετɻ͜Ε͕ັྗΛҾ͖ग़͢࿦ཧͷҰͭɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̍ɿࣗવͱΩϟϥΫλʔੑ͕ݱΕΔ ίϯτϥϙετ͸ɺ͜ΕΒਓؒͷशੑΛύοέʔδԽͨ͠ϙʔζ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ΩϟϥΫλʔੑ͕Θ͔Γ΍͍͢ ࢥΘͣݟͪΌ͏ ޷ײ΍਌ۙײΛ࣋ͭ

Slide 32

Slide 32 text

ͦͯ͠΋͏Ұͭͷ࿦ཧ͸୯७ɻϓϩϙʔγϣϯ͕ྑ͍ΩϟϥΫλʔͷັྗɺ೑ମඒΛڧௐ͢ΔޮՌ͕͋Δɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̎ɿ೑ମඒ͕ڧௐ͞ΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ɾྑ͍ϓϩϙʔγϣϯΛҰ૚ڧௐ͢ΔޮՌ͕͋Δɻ ɾಛʹݦஶͳͷ͕ɺେ͖ͳ4ࣈΧʔϒΛඳ͘λΠϓɻ

Slide 33

Slide 33 text

ಛʹޮՌ͕ߴ͍ͷ͕4ࣈϙʔζɻ਎ମͷߏ଄্ɺঁੑ͕ಘҙɻϘσΟϥΠϯ΍ࠎ൫ͷ޿͕͞ڧௐ͞ΕΔɻ lιοΧͷඒज़ղ๤ֶϊʔτιΫδϣϯώϣϯcΦʔϜࣾʢʣlଞΑΓ ίϯτϥϙετͷ࿦ཧͦͷ̎ɿ೑ମඒ͕ڧௐ͞ΕΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ 4ࣈϙʔζ͸਎ମͷߏ଄্ɺঁੑ͕ಘҙ ਎ମͷϥΠϯ΍Ԝತ͕ࡍཱͪɺ ݩʑྑ͍ϓϩϙʔγϣϯ͕ߋʹڧௐ͞ΕΔ ɾྑ͍ϓϩϙʔγϣϯΛҰ૚ڧௐ͢ΔޮՌ͕͋Δɻ ɾಛʹݦஶͳͷ͕ɺେ͖ͳ4ࣈΧʔϒΛඳ͘λΠϓɻ

Slide 34

Slide 34 text

·ͨɺٯసͷΞϓϩʔνͱͯ͠ɺϙʔδϯάͷࢿྉ͔Βย଍ཱͪҎ֎ͷ̎ͭͷ৚݅Λݟग़͞Εͨɻ ϙʔδϯάʹ࢖ΘΕΔίϯτϥϙετͷ৚݅ lඳ͖͍ͨ΋ͷΛཧ࿦Ͱ͔ͭΉϙʔζͷఆཧࣰ๪࿡࿠c,"%0,"8"ʢʣlΑΓ ਓΛऒ͖͚ͭΔϙʔδϯάʹ͸ڞ௨఺͕͋Γ·͢ɻ “ ” ঁੑͷࣸਅࢿྉͷଟ͕͘ɺ͜ͷ̏ͭͷ৚݅Λຬͨ͢ɻ ɾย଍ཱͪPSͦΕʹ͍ۙॏ৺όϥϯε ɾ಑ମʹཱମతͳͻͶΓ͕͋Δ ɾݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍ ( ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ

Slide 35

Slide 35 text

Ͱ͸͜͜Ͱɺͦͷ৚݅ͷҰͭʹண໨͠ɺ1ZUIPOͰίϯτϥϙετͷݕग़ʹ௅ΜͰΈΔɻ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFWK+3MB&6W*CQE36I,FYIR#@*%LH4 ίϯτϥϙετΛݕग़͢Δ ɾย଍ཱͪPSͦΕʹ͍ۙॏ৺όϥϯε ɾ಑ମʹཱମతͳͻͶΓ͕͋Δ ɾݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍ ( ͷ৚݅Λຬͨ͢ϙʔζΛݕग़͢Δ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ

Slide 36

Slide 36 text

·ͣ%ը૾͔Β%ͷΩʔϙΠϯτਪఆΛ͢Δɻਪఆ͸ɺ405"ͷख๏ʢ.F53"CTʣʹͯ4.1-Λ׆༻ɻ ίϯτϥϙετΛݕग़͢Δ ʢ5'ʹͯ%࢟੎ਪఆϞσϧ 4.1- Λར༻ʣ # import library import tensorflow as tf # load model model = tf.saved_model.load(download_model('metrabs_mob3l_y4t')) # load input image image = tf.image.decode_jpeg(tf.io.read_file(img_name)) pred = model.detect_poses(image, skeleton='smpl_24') # visualize by MeTRAbs demo method visualize( image.numpy(), pred['boxes'].numpy(), pred['poses3d'].numpy(), pred['poses2d'].numpy(), model.per_skeleton_joint_edges['smpl_24'].numpy()) ࢟੎ਪఆ͸શ਎ֆͷΈ༗ޮɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ ಥඈͳϙʔζ͸ɺ ͏·࢟͘੎ਪఆͰ͖ͳ͍

Slide 37

Slide 37 text

ਪఆͨ͠ΩʔϙΠϯτͷ࠲ඪಉ࢜ͷ૬ରతͳҐஔؔ܎Λܭࢉ͠ɺݞͱࠊͷࠨӈͷߴ͕͞ޓ͍ҧ͍͔൑ผɻ ίϯτϥϙετΛݕग़͢Δ ʢ5'ʹͯ%࢟੎ਪఆϞσϧ 4.1- Λར༻ʣ # adjusting the visualize method def visualize(…): ... # detect contrast per estimated humans # using coordinate transformation is_contra = detect_contra(pred['poses3d'].numpy()[i]) ... # visualize by MeTRAbs demo method visualize( image.numpy(), pred['boxes'].numpy(), pred['poses3d'].numpy(), pred['poses2d'].numpy(), model.per_skeleton_joint_edges['smpl_24'].numpy()) ࠲Ґͷίϯτϥϙετ΋ਪఆՄɻ ݕग़ͨ͠ίϯτϥϙετΛɺ ੺࿮ͷCCPYͰғΉɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃɿίϯτϥϙετ

Slide 38

Slide 38 text

ίϯτϥϙετ͸ελΠϧͷྑ͍ਓ෺ʹ༗རͳఆੴɻ࣍͸ɺผͷ࣋ͪຯ΋׆͖ΔʮੑઓུʯΛ঺հ͢Δɻ ΋ͪΖΜɺ೑ମඒ͚͕ͩ޷·ΕΔ৚݅Ͱ͸ͳ͍ ɾͨͩɺΩϟϥΫλʔશͯͷϓϩϙʔγϣϯ͕ ɹ༏Ε͍ͯΔΘ͚Ͱ͸ͳ͍ɻ ɾڝ͏ͳɺ࣋ͪຯΛΠΧͤɻ ɾϓϩϙʔγϣϯͷྑ͞΋ؚΊͯɺ ɹશਓྨ͕ऒ͔ΕΔΩϟϥΫλʔͷ࣋ͪຯΛ ɹ͍͔ͭ͘঺հ͢Δɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶃˠᶄ ͙͵͵

Slide 39

Slide 39 text

Ҩ఻ࢠϨϕϧͰ޷·ΕΔಛ௃͸ɺஉঁผʹɺҟੑɾಉੑɾࢠڙͱ͍͏ଐੑʹ෼͚Δͱ੔ཧ͠΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlΑΓ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃ ࢲͨͪͷҨ఻ࢠͷϓϩάϥϜ͞Εͨɺऒ͔ΕΔΩϟϥΫλʔͷಛ௃ͱ͸ʜʁ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ରɾҟੑ ରɾಉੑ ରɾࢠڙ ʁ ʁ ʁ ʁ ʁ ʁ

Slide 40

Slide 40 text

Slide 41

Slide 41 text

·ͣ͸உੑ͕޷Ήঁੑͷಛ௃ɻஉੑ͸ɺ׬શʹݟͨ໨͚ͩͰए݈͘߁Ͱ͋Δ͜ͱ͕൑ผͰ͖Δಛ௃Λ޷Ήɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ͘ͼΕͨࡉ͍΢ΤετɺԒͷ͋Δ௕͍൅ɺ ๛ຬͰϋϦͷ͋Δόετɺؙ͘ઑֺͬͨɺ γϫͷͳ͍៉ྷͳटݩɺ෯ͷ޿͍ࠎ൫ɺ ϋϦͷ͋Δ៉ྷͳखɺ೑෇͖ͷྑ͍٭FUD ˠ ए݈͘߁Ͱ ൟ৩Ձ͕ߴ͍ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<உੑˠҟੑ> உੑ͸جຊతʹൟ৩Ձ͕ߴ͍ʢ೛৷͕੒ޭ͠΍͍͢ʣঁੑΛ޷Ήɻ ೛৷͸ɺ݈߁Ͱए͍ঁੑ΄Ͳ੒ޭ཰্͕͕ΔͷͰɺݟͨ໨ͷ݈߁͞ͱए͕͞γάφϧɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ঁੑΩϟϥʹඳ͔ΕΔϑΣνͷଟ͕͘ʮए͞ʯͱʮ݈߁ʯͷσϑΥϧϝ FUD Ԓͷ͋Δ௕͍൅ ๛ຬͰϋϦͷ͋Δόετ ؙ͘ઑֺͬͨ ͘ͼΕͨࡉ͍΢Τετ ෯ͷ޿͍ࠎ൫ γϫͷͳ͍៉ྷͳख ೑෇͖ͷྑ͍٭ γϫͷͳ͍៉ྷͳटݩ ੒ख़͠ɺ࿝͚͍ͯͳ͍ ੒ख़͠ɺ͔ͭ҆࢈͕ݟࠐΊΔ ੒ख़͠ɺ࿝͚͍ͯͳ͍ ੒ख़͠ɺ݈߁తͰ͋Δ පؾͰͳ͘ɺ೛৷͍ͯ͠ͳ͍ ੒ख़͠ɺਨΕΔ೥ྸͰ͸ͳ͍ ൅Λ৳͹͢ظؒɺ݈߁Ͱए͍ ೕࣃ͕ແ͍೥ྸͰɺଠͬͯͳ͍

Slide 42

Slide 42 text

ঁੑ͸உੑʹൺ΂ɺҟੑʹର͠௕ظతͳؔ܎Λ๬Ήɻ·ͨɺൺֱతࢿ࢈͕ଟ͘஍Ґͷߴ͍೥্Λ޷Έ΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ʁʁʁ ೥্ɺଞʁ ˠ ˠ ڧ݈͘߁Ͱੜଘ͠ଓ͚Δ ࣋ଓతʹՈఉΛࢧԉͰ͖Δ ঁੑ͸࣋ଓతʹࣗ෼΍࣮ࢠΛࢧԉͰ͖ΔɺͣͬͱຯํͰ͍ͯ͘ΕΔڧ͍உੑΛ޷Ήɻ ݈߁Ͱࢿ࢈͕ଟ͘ɺͦΕΒ͕ࣗ෼΍࣮ࢠͷͨΊʹ࢖ΘΕΔͱ͍͏҆৺ײ΋େࣄɻ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<ঁੑˠҟੑ> ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 43

Slide 43 text

ҟੑʹରͯ͠إͷඒ͠͞ΛٻΊΔͷ͸ɺஉঁڞ௨ɻࠨӈରশͳإ͸ɺ༏ΕͨҨ఻ࢠΛड͚ܧ͙৅௃Ͱ΋͋Δɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlଞΑΓ lݱ୅ϚϯΨʹ͓͚Δʮ͔Θ͍͍ΩϟϥΫλʔʯͷ෼ੳͱ૑࡞ཥӱ௒cژ౎ਫ਼՚େֶʢʣlΑΓҾ༻ average() ݟͨ໨ͰΘ͔Δಛ௃ ࠨӈରশ පؾͳͲͰࠨӈͷ࿪Έ͕ͳ͍ ଟ༷ͳҨ఻ࢠΛड͚ܧ͍Ͱܗ੒͞Εͨإ ฏۉإ ˠ ˠ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<உঁˠҟੑ> உঁͱ΋ʹɺإ͕ඒ͍͠ҟੑΛٻΊΔɻ ࠨӈରশͰฏۉతͳإ͕ඒ͍͠ͱ͞Ε͍ͯΔɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 44

Slide 44 text

·ͨɺஉঁͱ΋ʹࣗ෼Λ޷͍ͨҟੑΛ޷Ήɻஉੑͷ޷Ήൟ৩ɺঁੑͷ޷Ή௕ظతͳؔ܎ɺ྆ํʹ༗ޮͳͨΊɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlଞΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ࣗ෼ʹإΛ޲͚Δɺಏ޸͕։͘ সإ ˠ ˠ ࣗ෼ʹڵຯ͕͋Δ ࣗ෼ʹ޷ײΛ࣋ͭ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<உঁˠҟੑ> உঁͱ΋ʹɺࣗ෼ʹڵຯ΍޷ײΛ࣋ͭҟੑʹ΋ऒ͔ΕΔɻ ࢹઢ΍ಏ޸ͱ͍͕ͬͨ໨ͷ༷ࢠ͔Βਪଌ͢Δ͜ͱ͕ଟ͍ɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 45

Slide 45 text

࣍ʹಉੑʹରͯ͠ɻஉঁͱ΋ʹࣗ෼ͷརӹ࠷େԽͷͨΊɺ਎಺΍͓खຊʹͳΔಉੑΛ޷Ήʢ಺ूஂόΠΞεʣ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ʁʁʁ ʁʁʁ ˠ ˠ ݟฦΓ͕ظ଴Ͱ͖Δ ༏ΕͨೳྗΛࢀߟʹͰ͖Δ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<உঁˠಉੑ> ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ ಉੑʹରͯ͠͸உঁͱ΋ʹɺ ࣗ෼ͷੑઓུͷো֐ͱͳΒͳ͍ڠྗؔ܎ʹ͋ΔಉੑΛ޷Ήɻ

Slide 46

Slide 46 text

࠷ޙʹɺࢠڙʹରͯ͠ɻஉঁͱ΋ʹϕϏʔεΩʔϚΛ࣋ͭ΋ͷʹ͸ɺਓͰ΋ಈ෺Ͱ΋ѪΒ͘͠ײ͡Δɻ l%JFBOHFCPSFOFO'PSNFONÖHMJDIFS&SGBISVOH-PSFO[ ,c;FJUTDISJGU'ÛS5JFSQTZDIPMPHJFʢʣlΑΓ ݟͨ໨ͰΘ͔Δಛ௃ ϕϏʔεΩʔϚ <େ͖ͳ໨ɺ๲ΒΜͩ๹ɺؙ͍͓Ͱ͜ɺ େ͖ͳ಄ɺ஄ྗ͋Δഽɺ୹͍ख଍FUD> ˠ อޢͨ͘͠ͳΔ ༊͞ΕΔ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<உঁˠࢠڙ> ࢠڙʹରͯ͠͸உঁͱ΋ʹɺ ʮϕϏʔεΩʔϚʯͰఆٛ͞ΕΔࢠڙΒ͍͠਎ମతಛ௃ΛѪΒ͘͠ࢥ͏ɻ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 47

Slide 47 text

Slide 48

Slide 48 text

Ҏ্͕ɺੑઓུΛ΋ͱʹ੔ཧͨ͠޷·ΕΔಛ௃ɻ֎ݟ͔ΒಡΈऔΓ΍͍͢ԫ৭͸ɺΠϥετʹԠ༻͠΍͍͢ɻ lਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯεҰສ೥มԽ͠ͳ͍Ձ஋؍Ξϥϯɾ4ɾϛϥʔcύϯϩʔϦϯάגࣜձࣾʢʣlଞΑΓ உঁͷੑઓུʹجͮ͘޷·ΕΔಛ௃<·ͱΊ> ରɾҟੑ ରɾಉੑ ରɾࢠڙ ए͞ ݈߁͞ʗإͷྑ͞ʗࣗ෼ʹؔ৺͕͋Δ ࣗ෼ʹརӹΛ΋ͨΒ͢ ࢠڙΒ͍͠਎ମతಛ௃Λ࣋ͭ ࣋ଓతͳڧ͍ຯํʹͳΔ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 49

Slide 49 text

ͨͩ͠ɺແܭըʹҰ෦ͷײੑΛܹࢗ͢ΔΑ͏ͳΠϥετΛඳ͘ͷ͸ةݥɻཁ݅ʹݟ߹͏ൣғͰ׆༻͠Α͏ɻ lʮӺ೫Έ͔ͪʯεέεέεΧʔτ͕େ෺ٞɹ౦ژϝτϩɺ൷൑ड͚ඍົʹʮमਖ਼ʯʢʣc+$"45χϡʔεzΑΓ ͨͩ͠ɺੑઓུͷσϑΥϧϝ͸৻ॏʹ ΩϟϥΫλʔΛັྗతʹݟͤΔͷ΋େࣄ͕ͩɺ ڧௐ͢Δͷ͸ΩϟϥΫλʔͷཁ݅ʹ߹ͬͨັྗʹߜΔඞཁ͕͋Δɻ ʮެڞަ௨ػؔͷΩϟϥΫλʔͱͯ͠;͞Θ͘͠ͳ͍ʯ “ ” ͱͯ͠෺ٞΛৢ͠ɺʮӺ೫Έ͔ͪʯͷσβΠϯ͸मਖ਼͞Εͨɻ मਖ਼ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 50

Slide 50 text

Ͱ͸ੑઓུʹجͮ͘ಛ௃Λڧௐ͠ա͍͗ͯͳ͍͔ɺ࿐ࠎͳදݱΛ1ZUIPOͰݕग़ͯ͠ΈΔɻ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFC%G@.GVB@8NRWO.I/::Y[.%6 ࿐ࠎͳදݱΛݕग़͢Δ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 51

Slide 51 text

਺ߦͰݕग़͢Δྫɻ/4'8'JMUFS͸4/4΍ݕࡧͳͲͷࣄྫ͕ଟ͘ɺ044΋ଟ͍ɻϑϦʔϥΠυ͠΍͍͢ɻ ࿐ࠎͳදݱΛݕग़͢Δʢ/VEFOFUͷֶशࡁΈϞσϧʗ൑ผثΛར༻ʣ # import library import nudenet as NudeDetector # load input image and put local (omitted) # initialize detector (adjusted NudeDetector in nudenet) detector = NudeDetector() # run censor method # -> detect nudity & set bbox & display image detector.censor(img_name) ݕग़࣌ʹ ܯࠂʁ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴᶄɿੑઓུ

Slide 52

Slide 52 text

લ൒·ͱΊɻΩϟϥΫλʔͷັྗΛදݱ͢Δࣗ༝౓͕ߴ͍͜ͱΛ౿·͑ͯɺશਓྨʹ༗ޮͳఆੴΛࣔͨ͠ɻ ΩϟϥΫλʔͷ৺ཧઓུɿ·ͱΊ ϙʔζ ද৘ Ͳ͏ັྗΛ఻͑Δ͔ ίϯτϥϙετ ఆੴ ੑઓུ ʜ ΩϟϥΫλʔੑͱ ೑ମඒ ʜ உ͸ൟ৩ɺ ঁ͸Ϧιʔε ಛ௃ᶃ ಛ௃ᶇ ಛ௃ᶄ ಛ௃ᶆ ಛ௃ᶅ ϙʔζʗද৘ΛܾΊΔ ΩϟϥΫλʔͷັྗΛ఻͑Δ ετʔϦʔ΍৔໘Λ఻͑Δ Ωϟϥֆͷझࢫ

Slide 53

Slide 53 text

ίϯτϥϙετ ఆੴ ੑઓུ ʜ ΩϟϥΫλʔੑͱ ೑ମඒ ʜ உ͸ൟ৩ɺ ঁ͸Ϧιʔε ಛ௃ᶃ ಛ௃ᶇ ಛ௃ᶄ ಛ௃ᶆ ಛ௃ᶅ ϙʔζʗද৘ΛܾΊΔ ʁʁʁ ʁʁʁ ϙʔζ ද৘ Ͳ͏ັྗΛ఻͑Δ͔ ΩϟϥΫλʔͷັྗΛ఻͑Δ ετʔϦʔ΍৔໘Λ఻͑Δ Ωϟϥֆͷझࢫ ࠓճ঺հͨ͠ఆੴ͸σϞͰࣔͨ͠௨Γɺ1ZUIPO΍"*Ͱ΋ཧղ͠΍͍͢ɻֆࢣ͕஫ྗ͢΂͖͸ଞͷཁૉ͔΋ɻ ΩϟϥΫλʔͷ৺ཧઓུɿΫϦΤΠλʔ͕஫ྗ͢΂͖͸…ʁ

Slide 54

Slide 54 text

̎ ޫͱ৭ͷ৺ཧઓུ

Slide 55

Slide 55 text

l৭ృΓνϡʔτϦΞϧσδλϧ࠼৭ͷجຊύΫɾϦϊcϚʔϧࣾʢʣlΑΓ લఏ஌ࣝͱͯ͠ɺޫ͸෺ཧݱ৅Ͱɺ৭͸৺ཧݱ৅Ͱ͋Δ͜ͱɻͦͯ͠৭͸ޫʹґଘ͍ͯ͠Δɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ന৭ޫ ੺͍ޫ ੺ʂ

Slide 56

Slide 56 text

΋͠΋ޫݯ͕ϒϧʔϥΠτ͔͠ͳ͔ͬͨΒɺࢲͨͪ͸੨͔ࠇ͔͠ೝࣝ͢Δ͜ͱ͕Ͱ͖ͳ͍ɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ϒϧʔϥΠτ ൓ࣹޫ ࠇʁ ੨ʁ l৭ృΓνϡʔτϦΞϧσδλϧ࠼৭ͷجຊύΫɾϦϊcϚʔϧࣾʢʣlΑΓ

Slide 57

Slide 57 text

΋͠΋ޫݯ͕ϒϧʔϥΠτ͔͠ͳ͔ͬͨΒɺࢲͨͪ͸੨͔ࠇ͔͠ೝࣝ͢Δ͜ͱ͕Ͱ͖ͳ͍ɻ ޫͱ৭ ৭͸ޫʹґଘ͢Δ ϒϧʔϥΠτ ൓ࣹޫ ࠇʁ ੨ʁ l৭ృΓνϡʔτϦΞϧσδλϧ࠼৭ͷجຊύΫɾϦϊcϚʔϧࣾʢʣlΑΓ %B[4UVEJP *SBZ ʹͯ࡞੒ lըͮ͘ΓͷͨΊͷޫͷतۀϦνϟʔυɾϤοτc#//৽ࣾʢʣlΑΓ ༦ํͷଠཅޫ ۭ৭ͷఱۭޫ ೔ৗੜ׆Ͱ΋ɺ৭͕ภΔޫܠ͸Α͘ݟΒΕΔ

Slide 58

Slide 58 text

Ͱ͸·ͣ͸ɺΠϥετ͔Βޫͱ৭Λ෼཭ͯٞ͠࿦͢ΔͨΊɺ1ZUIPOͰর໌ͷ৭Λ෼཭ͯ͠ΈΔɻ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFG0G5Y:OE30-DR['M*-23G),(D,0D' PythonͰΠϥετͷޫͷ৭Λ୳Δ Πϥετ͔Βর໌ͷ৭Λফ͢

Slide 59

Slide 59 text

# crone Deep_White_Balance !git clone https://github.com/mahmoudnafifi/Deep_White_Balance.git # run test script !python demo_single_image.py \ —input INPUT_IMAGE_PATH \ --output_dir OUTPUT_DIR \ --model_dir MODEL_DIR # crone mixedillWB !git clone https://github.com/mahmoudnafifi/mixedillWB.git # run test script !python test.py \ --wb-settings T F D C S \ --model-name WB_model_p_64_D_S_T_F_C \ —testing-dir INPUT_DIR --outdir OUTPUT_DIR ϗϫΠτόϥϯεͷ่ΕΛิਖ਼͠ɺෳ਺ͷর໌ͷ৭Λิਖ਼͢Δͱ͍͏̎ͭͷख๏Λ࠾༻ʢ঎༻ར༻ෆՄʣ র໌ͷ৭Λݕग़ʗന͘ิਖ਼͢Δʢ%FFQ8# NJYFEJMM8#Λར༻6/FUʣ ("'"ࣾһΒͷެ։͢ΔSFQPͷ αϯϓϧεΫϦϓτΛ࣮ߦ͢Δ͚ͩɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ

Slide 60

Slide 60 text

Slide 61

Slide 61 text

Πϥετͷޫͷදݱ͸ɺ෺ཧ๏ଇʹ४ڌ͸ͯ͠΋ɺ९क͸͞Εͳ͍ɻͦͷͨΊҰఆͷϧʔϧͷநग़͸ࠔ೉ɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ → Failed 2ΠϥετͷϗϫΠτόϥϯεɺԿނ͏·͍͔͘ͳ͍ͷ͔ έʔε̍ɹهԱ৭ʢయܕ৭ʣΛڧௐ έʔε̎ɹཱମදݱ͕লུ "ɹཧ༝͸ʮޫͷ෺ཧ๏ଇʹैΘͳ͍࠼৭ʯ͔ͩΒ ˠ ҰఆͷϧʔϧԽ͸ࠔ೉ ʜ l৭࠼ݕఆެࣜςΩετڃฤ ೥վగ൛ ʗ6$ڃ ೥վగ൛ ৭࠼ݕఆڠձc৭࠼ݕఆڠձlଞΑΓ ڧௐ লུ

Slide 62

Slide 62 text

Πϥετͷޫͷදݱ͸ɺ෺ཧ๏ଇʹ४ڌ͸ͯ͠΋ɺ९क͸͞Εͳ͍ɻͦͷͨΊҰఆͷϧʔϧͷநग़͸ࠔ೉ɻ PythonͰΠϥετͷޫͷ৭Λ୳Δ → Failed 2ΠϥετͷϗϫΠτόϥϯεɺԿނ͏·͍͔͘ͳ͍ͷ͔ έʔε̍ɹཱମදݱ͕লུ έʔε̎ɹهԱ৭ʢయܕ৭ʣΛڧௐ "ɹཧ༝͸ʮޫͷ෺ཧ๏ଇʹैΘͳ͍࠼৭ʯ͔ͩΒ ˠ ҰఆͷϧʔϧԽ͸ࠔ೉ লུ ڧௐ ʜ l৭࠼ݕఆެࣜςΩετڃฤ ೥վగ൛ ʗ6$ڃ ೥վగ൛ ৭࠼ݕఆڠձc৭࠼ݕఆڠձlଞΑΓ Πϥετσʔλͷ෼ੳͰ͸ ޫΛ௚઀ѻ͏ͷ͸೉͍͠ɺ৭ʹूத͢Δ 🥲 ઓུతఫୀ ͥ͟ΔΛಘͳ͍

Slide 63

Slide 63 text

৭ͷ໾໨͸ɺ੍࡞ϑϩʔͷஈ֊ʹΑͬͯେ͖̎ͭ͘ʹ෼͔ΕΔɻ a ੍ ࡞ ϑ ϩ Πϥετશମͷ৭ΛܾΊΔ ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ৭ͷ໾໨ͱ੍࡞ϑϩʔ

Slide 64

Slide 64 text

ҰൠʹɺґཔऀʹΠϥετΛൃ஫͞Εͨ৔߹ɺΠϥετΛ࢓্͛Δલʹ·ͣશମͷ഑৭Λ֬ೝͯ͠΋Β͏ɻ a Πϥετશମͷ৭ΛܾΊΔ ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ੍ ࡞ ϑ ϩ ৭ΛృΓ࢝ΊΔલʹ ৭ͷϥϑΛ͍͔ͭ͘ඳ͍ͯɺ ґཔओͱೝࣝΛ߹ΘͤΔɻ ˠίϯηϓτΛܾΊΔ ৭ͷ໾໨ͱ੍࡞ϑϩʔ

Slide 65

Slide 65 text

a ੍ ࡞ ϑ ϩ Πϥετશମͷ৭ΛܾΊΔ ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ܾ·ͬͨ഑৭Λϕʔεʹ ண৭͠ɺࡉ෦Λඳ͖ࠐΉɻ ˠΫΦϦςΟΛ্͛Δ ˠίϯηϓτΛܾΊΔ ഑৭Ͱґཔऀͱͷ߹ҙ͕औΕͨΒɺΫΦϦςΟʔΛ্͛ΔͨΊʹΠϥετʹ৭Λඳ͖ࠐΜͰ͍͘ɻ ৭ͷ໾໨ͱ੍࡞ϑϩʔ

Slide 66

Slide 66 text

a ੍ ࡞ ϑ ϩ ഑৭Ͱ ίϯηϓτܾఆ Πϥετશମͷ৭ΛܾΊΔ ˠίϯηϓτΛܾΊΔ ృΓͰ ΫΦϦςΟ61 ඃࣸମʢʴഎܠʣΛඳ͖ࠐΉ ˠΫΦϦςΟΛ্͛Δ ʜ⁞ ʜ  ͭ·Γɺ৭ʹ͸ʮ഑৭ͰίϯηϓτΛܾΊΔʯʮృΓͰΫΦϦςΟΛ্͛Δʯͱ͍͏̎ͭͷ໾໨͕͋Δɻ ৭ͷ໾໨ͱ੍࡞ϑϩʔ

Slide 67

Slide 67 text

⁞഑৭ͰίϯηϓτΛܾΊΔɿ఻͑Δҹ৅͕୯৭ or ෳ਺৭ l৭࠼ݕఆެࣜςΩετڃฤ ೥վగ൛ ʗ6$ڃ ೥վగ൛ ৭࠼ݕఆڠձc৭࠼ݕఆڠձlଞΑΓ Πϥετશମʹ࢖ΘΕΔ৭͸ྨࣅͯ͠Δʁ෼ࢄͯ͠Δʁ શମͷ৭͸ྨࣅ͔෼ࢄ͔ ྨࣅ ྨࣅ৭ͷதͰ ࠷΋໘ੵͷଟ͍৭ͷ ҹ৅·ͨ͸࿈૝Πϝʔδ ֆࢣ͕఻͍͑ͨײ৘ ෼ࢄ ෼ࢄͨ͠഑৭ͷ ૊Έ߹ΘͤʹΑΔ ҹ৅·ͨ͸࿈૝Πϝʔδ ֆࢣ͕఻͍͑ͨײ৘ Ұͭ໨ɺ഑৭ͰͲΜͳίϯηϓτΛܾΊΔ͔ɻ఻͍͑ͨΠϝʔδʹ߹Θͤͯɺશମͷ৭Λྨࣅʗ෼ࢄͤ͞Δɻ

Slide 68

Slide 68 text

ඃࣸମͱഎܠ͸ରൺ͔ಉԽ͔ ରൺ ಉԽ ඃࣸମͱഎܠͷ৭ͷ෼෍͕େ͖͘ҟͳΔʁࣅ͍ͯΔʁ ˠɹඃࣸମ͕࣋ͭײ৘ʹ஫໨͍ͤͨ͞ ˠɹΠϥετશମ͕࣋ͭײ৘ʹ஫໨͍ͤͨ͞ ⁞഑৭ͰίϯηϓτΛܾΊΔɿओ໾͕ඃࣸମ or શମ l৭࠼ݕఆެࣜςΩετڃฤ ೥վగ൛ ʗ6$ڃ ೥վగ൛ ৭࠼ݕఆڠձc৭࠼ݕఆڠձlଞΑΓ ͦͯ͠ඃࣸମʹ஫໨͍͔ͤͨ͞ɺഎܠʹೃછ·͍͔ͤͨɺͱ͍͏ૂ͍ʹ߹Θͤͯ৭ΛରൺʗಉԽͤ͞Δɻ

Slide 69

Slide 69 text

Ͱ͸࣮ࡍʹΠϥετͷ৭Λ1ZUIPOͰநग़ʗՄࢹԽͯ͠ɺ͜ΕΒͷํ਑Λ୳ͬͯΈΑ͏ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWF92H++YYC.N4SD&U[LZ"6X/@+9Y0U PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔ ʴ

Slide 70

Slide 70 text

഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔ ʢશମ૾ΛϚϯηϧද৭ܥͰ೺Ѳʣ # import library from matplotlib.colors import ListedColormap import matplotlib.pyplot as plt # prepare dataset C = [[1032 1033 1034 ... 1072 1073 1074] [ 989 990 991 ... 1029 1030 1031] ... [ 43 44 45 ... 83 84 85] [ 0 1 2 ... 40 41 42]] masked_cc = ['#ba2237' ... ‘#ffffff', ‘#411434', '#ffffff'] cmap = ListedColormap(masked_cc) # draw pcolormesh ax = plt.pcolormesh(C, cmap=cmap) plt.colorbar(ax) ը૾ʹແ͍৭͸ ͰϚεΫ͢Δ #ffffff PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ Ϛϯηϧද৭ܥͷσʔλΛ༻ҙͰ͖Ε͹ɺNBUQMPUMJCͷϝογϡඳըͰ഑৭ͷશମ૾͕ϚοϐϯάͰ͖Δɻ

Slide 71

Slide 71 text

഑৭Λ၆ᛌ͢Δɿྨࣅ͔෼ࢄ͔ ʢ৭૬෼෍Λ৭૬؀ώετάϥϜͰ೺Ѳʣ # import library import cv2 import matplotlib.pyplot as plt # prepare dataset (omitted) Polar_df = pd.DataFrame({'Hue': ..., 'Count': …}) # plot polar axis ax = plt.subplot(polar=True) # draw bars bars = ax.bar( x=[element * width for element in Polar_df.index], height=Polar_df.Count, width=2*np.pi / len(Polar_df.index), bottom=Polar_df[‘Count'].max()/3) ෼ࢄʁ ྨࣅʁ PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ .BUQMPUMJCͷۃ࠲ඪάϥϑͰɺ৭૬؀Λ໛ͨ͠ώετάϥϜ΋දݱՄೳɻNBUQMPUMJC͸͍͍ͧɻ

Slide 72

Slide 72 text

Slide 73

Slide 73 text

Slide 74

Slide 74 text

Slide 75

Slide 75 text

ଓ͍ͯɺඃࣸମͱഎܠΛ෼͚ͯɺͦΕͧΕͷ৭ͷؔ܎ੑΛ୳ͬͯΈΑ͏ɻ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWFC$*3'GV)TV)/R)XWE%*6H768F*N PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔

Slide 76

Slide 76 text

# import library import torch from carvekit.api.high import HiInterface # create CarveKit interface interface = HiInterface(batch_size_seg=5, batch_size_matting=1, device='cuda' if torch.cuda.is_available() else 'cpu', seg_mask_size=320, matting_mask_size=2048) images_without_background = interface([img_name]) # save object only image cat_wo_bg = images_without_background[0] cat_wo_bg.save(‘object_only.png') PythonͰΠϥετ͔Β৭ͷํ਑Λ୳Δ ඃࣸମͱഎܠͷؔ܎Λ୳Δɿରൺ͔ಉԽ͔ʢ$BSWF,JUͰ෼཭ʣ ඃࣸମͱഎܠͷ෼཭͸ɺڊਓͷݞʢ4FHNFOUBUJPOʣ͕୔ࢁɻࠓճ͸$BSWF,JUͱ͍͏'8Λར༻ͨ͠ɻ

Slide 77

Slide 77 text

Slide 78

Slide 78 text

Slide 79

Slide 79 text

Slide 80

Slide 80 text

l/PWJDF4USBUFHJFTGPS6OEFSTUBOEJOH1BJOUJOHT+"4DINJEUΒc"QQMJFE$PHOJUJWF1TZDIPMPHZʢʣlΑΓ  ృΓͰΫΦϦςΟΛ্͛Δ ࣮ࣸੑΛߴΊΔృΓ͸ɺֆࢣͷͩ͜ΘΓϙΠϯτ ৭Λඳ͖ࠐΉ͜ͱͰɺ࣭ײ΍Ԟߦ͖͕දݱͰ͖ɺ࣮ࣸੑ͕૿͢ɻ ༠໨ੑΛߴΊɺ຅ೖײ͕༩͑ΔͨΊɺඃࣸମͷڧௐʹΑ͘࢖ΘΕΔɻ ഑৭ʹଓ͘ɺ΋͏Ұͭͷ৭ͷ໾ׂ͕ʮృΓʯɻֆࢣ͸ͩ͜ΘΓ͍ͨ෦෼͸ಛʹ೤৺ʹඳ͖ࠐΉɻ

Slide 81

Slide 81 text

ͪͳΈʹృΓͰඳ͖ࠐΈྔ͕ଟ͍ྖҬ͸ɺ1ZUIPOͰ؆୯ʹਪఆͰ͖Δɻ %&.063-   IUUQTDPMBCSFTFBSDIHPPHMFDPNESJWF@XM47U:+)H2G#CS6UYC#ESY[33@) PythonͰΠϥετ͔ΒృΓͷͩ͜ΘΓΛ୳Δ ඳ͖ࠐΈ͕ଟ͍ྖҬΛਪఆ͢Δ

Slide 82

Slide 82 text

ྫ͑͹ಡΈࠐΜͩΠϥετΛ/෼ׂͯ͠ɺ֤ྖҬͷΤϯτϩϐʔΛܭࢉɻృΓͰ૿͑ͨ৘ใྔ͕ਪఆͰ͖Δɻ # import library (omitted) # load image (omitted) # divide gray scale image x0, y0, n, h, w = ... divided = [gray_image[x0*x:x0*(x+1), y0*y:y0*(y+1)] for x in range(n) for y in range(n)] # calculate entropy for each division entropies = [] for img in divided: img = np.array(img) e = calcEntropy_method(img) entropies.append(e) # visualize (omitted) ͋ʂ؈ͷඳ͖ࠐΈ͕ଟ͍ʂ ͳͲɺͩ͜ΘΓʹؾ෇͚Δ ඳ͖ࠐΈ͕ଟ͍ྖҬΛਪఆ͢ΔʢΤϯτϩϐʔͰܭࢉʣ PythonͰΠϥετ͔ΒృΓͷͩ͜ΘΓΛ୳Δ

Slide 83

Slide 83 text

ޙ൒·ͱΊɻ৭ͷ໾໨Λ഑৭ͱృΓʹ෼͚ɺಛʹ഑৭ʹΑΔίϯηϓτͷಡΈํΛ࣮ફΛ௨ͯ͠ղઆͨ͠ɻ ޫͱ৭ͷ৺ཧઓུɿ·ͱΊ ৭ ഑৭Ͱίϯηϓτ શମͷ৭ ྨࣅ ෼ࢄ ରൺ ಉԽ ඃࣸମͱഎܠ ޫ ʜ ʜ ඳ͖ࠐΈྔʹͩ͜ΘΓ͕දΕΔ ʜ ৭୯ମͷΠϝʔδΛ׆༻ ʜ ʜ ʜ ৭ͷ૊Έ߹ΘͤΠϝʔδΛ׆༻ ඃࣸମΛ஫໨ͤ͞Δ Πϥετશମʹ໨Λ޲͚ͤ͞Δ ৭͸ޫʹґଘ͢Δʢͨͩ͠ɺޫΛΠϥετ͔Β෼཭͢Δͷ͸ࠔ೉ʣ ృΓͰΫΦϦςΟ

Slide 84

Slide 84 text

͜ͷதͰֆࢣ͕஫ྗ͢΂͖͸ɺ΍͸Γ఻͑ΔΠϝʔδΛܾΊΔίϯηϓτઃܭͳͷͰ͸ͳ͍͔ͱ૝૾͢Δɻ ޫͱ৭ͷ৺ཧઓུɿΫϦΤΠλʔ͕஫ྗ͢΂͖͸…ʁ ৭ ഑৭Ͱίϯηϓτ શମͷ৭ ྨࣅ ෼ࢄ ରൺ ಉԽ ඃࣸମͱഎܠ ޫ ʜ ʜ ඳ͖ࠐΈྔʹͩ͜ΘΓ͕දΕΔ ʜ ৭୯ମͷΠϝʔδΛ׆༻ ʜ ʜ ʜ ৭ͷ૊Έ߹ΘͤΠϝʔδΛ׆༻ ඃࣸମΛ஫໨ͤ͞Δ Πϥετશମʹ໨Λ޲͚ͤ͞Δ ৭͸ޫʹґଘ͢Δʢͨͩ͠ɺޫΛΠϥετ͔Β෼཭͢Δͷ͸ࠔ೉ʣ ృΓͰΫΦϦςΟ ˠࠓޙ͜͜͸"*ֆࢣʹ೚ͤΒΕΔ͔΋ʁ

Slide 85

Slide 85 text

·ͱΊ

Slide 86

Slide 86 text

࠷ޙʹɺϓϨθϯͷ·ͱΊɻࠓճ͸৺ཧઓུͷߏ଄Խʹ௅Έɺֆࢣ͕஫ྗ͢΂͖ϙΠϯτΛ໛ࡧͨ͠ɻ ·ͱΊ ΩϟϥΫλʔͱޫʗ৭ͷ৺ཧઓུΛߏ଄Խ͠ɺ   ͦͷ͍͔ͭ͘Λ1ZUIPOͰ࠶ݱͨ͠ ΩϟϥΫλʔͷັྗΛҾ͖ग़͢ఆੴͱ   ɹ഑৭ʹΑΔίϯηϓτઃܭΛॏ఺తʹղઆͨ͠

Slide 87

Slide 87 text

ͪͳΈʹɺॴʑͰొ৔ͨ͠ΠϥετͷҰ෦͸4UBCMF%J ff VTJPOϕʔεͷ"*ֆࢣ͕ඳ͍ͨ΋ͷͰͨ͠ɻ ऴΘΓʹɿ͜ͷࢿྉ͸AIֆࢣͷྗΛआΓͯ࡞Γ·ͨ͠ ϓϨθϯࢿྉˍσϞૉࡐͱͯ͠ɺ ֆฑֶश"*ͷੜ੒ΠϥετΛ׆༻͠·ͨ͠ 4QFDJBMUIBOLTUP ͍͔͢Έ͞Μʂ ʢ!L@JLBTVNJQPXEFSʣ

Slide 88

Slide 88 text

Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF ෺ཧ Thank you! ͨ͘͞Μͷٕ๏ॻͷ ΤοηϯεΛ٧ΊࠐΈ·ͨ͠

Slide 89

Slide 89 text

• ○×ͰΘ͔Δ෩ܠ࡞ը ਆٕ࡞ըγϦʔζ - ͚͞ϋϥε | KADOKAWAʢ2020ʣ • ΩϟϥΫλʔΠϥετͷҾ͖ग़͠Λ૿΍͢ϙʔζͱද৘ͷԋग़ςΫχοΫ - ΧϦϚϦΧ | ᠳӭࣾʢ2022ʣ • ιοΧͷඒज़ղ๤ֶϊʔτ - ιΫδϣϯώϣϯ | ΦʔϜࣾʢ2018ʣ • ΩϜɾϥοΩͷਓମυϩʔΠϯά - ΩϜɾϥοΩ | ΦʔϜࣾʢ2020ʣ • ඳ͖͍ͨ΋ͷΛཧ࿦Ͱ͔ͭΉ ϙʔζͷఆཧ - ࣰ๪࿡࿠ | KADOKAWAʢ2022ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • Die angeborenen Formen möglicher Erfahrung - Lorenz, K. | Zeitschrift Für Tierpsychologieʢ1943ʣ • ਐԽ৺ཧֶ͔Βߟ͑ΔϗϞαϐΤϯε Ұສ೥มԽ͠ͳ͍Ձ஋؍ - ΞϥϯɾSɾϛϥʔ | ύϯϩʔϦϯάʢ2019ʣ

Slide 90

Slide 90 text

• ৭ృΓνϡʔτϦΞϧ σδλϧ࠼৭ͷجຊ - ύΫɾϦϊ | Ϛʔϧࣾʢ2020ʣ • ޫͱ৭ͷνϡʔτϦΞϧ - ӄӨͱ৭࠼ΛࣗࡏʹૢΔʂ - ύΫɾϦϊ | Ϛʔϧࣾʢ2021ʣ • ৭࠼ݕఆ ެࣜςΩετ 1ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ • ৭࠼ݕఆ ެࣜςΩετ 3ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ • ৭࠼ݕఆ ެࣜςΩετ UCڃ (2022೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • Χϥʔ&ϥΠτ ϦΞϦζϜͷͨΊͷ৭࠼ͱޫͷඳ͖ํ - δΣʔϜεɾΨʔχʔ | Ϙʔϯσδλϧʢ2012ʣ • ৭࠼ݕఆ ެࣜςΩετ 2ڃฤ (2020೥վగ൛) - ৭࠼ݕఆڠձ | ৭࠼ݕఆڠձ

Slide 91

Slide 91 text

• ਓؾֆࢣͷ࡞඼͔ΒֶͿ഑৭ͷώϛπ - Ҵ༿ོ | ݰޫࣾʢ2022ʣ • ΠϥετɺອըͷͨΊͷ഑৭ڭࣨ - দԬ৳࣏ | MdNʢ2018ʣ • ഑৭ͷڭՊॻ - ৭࠼จԽݚڀձ | PIE Internationalʢ2018ʣ • The Art of GUWEIZ ά΢ΣΠζըू - GUWEIZ | ϗϏʔδϟύϯʢ2021ʣ • mignon͕͔ͬ͠Γڭ͑ΔʮഽృΓʯͷൿ݃ - mignon | SBΫϦΤΠςΟϒʢ2020ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • ཧܥ೴Ͱඳ͘๖͑ֆ - ݾଈੋۭʢ2017ʣ

Slide 92

Slide 92 text

• Vision ετʔϦʔΛ఻͑Δɿ৭ɺޫɺߏਤ - ϋϯεɾPɾόοϋʔ | Ϙʔϯσδλϧʢ2019ʣ • ֆΛݟΔٕज़ ໊ըͷߏ଄ΛಡΈղ͘ - ळాຑૣࢠ | ே೔ग़൛ࣾʢ2019ʣ • ޫͱ৭࠼ ղମ৽ॻ - μςφΦτ | ϚΠφϏग़൛ʢ2018ʣ • ըͮ͘ΓͷͨΊͷޫͷतۀ - দԬ৳࣏ | ϏʔɾΤψɾΤψ৽ࣾ ʢ2019ʣ • ײ֮৘ใͷ஌֮ϝΧχζϜ - ਗ਼ਫ๛ | ણҡ੡඼ফඅՊֶʢ1987ʣ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • Novice Strategies for Understanding Paintings - JA SchmidtΒ | Applied Cognitive Psychology 3.1ʢ1989ʣ • ֆըؑ৆ʹ͓͚Δೝ஌త੍໿ͱͦͷ؇࿨ - ాத٢࢙, দຊ࠼ق | ೝ஌Պֶʢ2013ʣ

Slide 93

Slide 93 text

• MeTRAbs Absolute 3D Human Pose Estimator | Github • ࠲ඪܥΛ͋ΘͤΔ ઈର࠲ඪͱϩʔΧϧ࠲ඪ - ϓϩάϥϛϯά੔ܗ֎Պҩͷϖʔδ • PythonʹΑΔ࠲ඪม׵ͷϓϩάϥϜ - ϓϩάϥϛϯά੔ܗ֎Պҩͷϖʔδ • ̏࣍ݩ্ۭؒͷͶ͡Εͨ̎௚ઢͷ࠷઀ۙ఺ΛٻΊΔ - Vignette & Clarity • Hue&ToneγεςϜ | Χϥʔઓུͷઐ໳Ո | NCD-WEB Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • Color Scheme Analysis of Illustrations - Niti Wattanasirichaigoon • Guide to Creating Color Schemes - ART ROCKET

Slide 94

Slide 94 text

• Deep White-Balance Editing | Github • Auto White-Balance Correction for Mixed-Illuminant Scenes | Github • NudeNet | Github **NSFW** • CarveKit | Github • ʮΩϟϥֆඳ͖ΞϧΰϦζϜʯγϦʔζ - osakana.factory | ٕज़ॻయ Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • Munsell Resources - Paul Centore • Image Color Extraction with Python in 4 Steps - Boriharn K | Medium

Slide 95

Slide 95 text

• σΟʔϓϒϦβʔυ - σΟʔϓϒϦβʔυ | YouTube • Yaki Mayuru drawing channel - ম·͍Δ | YouTube • ֆ༿·͠ΖͷͪΌΜͶΔ - ֆ༿·͠Ζ | Youtube Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • ͋ͳͨΛԠԉͨ͘͠ͳΔ5ͭͷཁҼͱ͸ʁ ਐԽ৺ཧֶͰߟ࡯ - Ṗ෦͑Ή | Noteʢ2018ʣ  https://note.com/nasobem/n/n628306e0e6e5 • ϓϩ໺ٿϑΝϯʹؔ͢Δݚڀ(V) : ϑΝϯ৺ཧɺԠԉߦಈɺ͓Αͼूஂॴଐҙࣝͷߏ଄  - ޿୔ढ़फΒ | ؔ੢ࠃࡍେֶ஍Ҭݚڀॴ૓ॻʢ2006ʣ • ʮ͔Θ͍͍ʯͷ৺ཧֶ - ೝ஌৺ཧੜཧֶݚڀࣨʢ2022/10/12࣌఺ʣ

Slide 96

Slide 96 text

• ༷ʑͳݒ೦΍໰୊Λ๊͑ͭͭ΋ʮ͓ֆ͔͖AIʯͷਐԽ͸ࢭ·Βͣʢ2022/10/4ʣ| Yahoo!χϡʔε  https://news.yahoo.co.jp/articles/1cb8c63ee8fb7a3bbbb8412aeefcc2bf2217d033 • ΠϥετϨʔλʔͷݸੑΛֶΜͰֆΛ“ແݶੜ੒”͢ΔAIαʔϏεʢ2022/8/29ʣ | ITmedia  https://www.itmedia.co.jp/news/articles/2208/29/news133.html • AI͕ֆΛඳ͘ʁ ਐԽ͢Δը૾ੜ੒AIͷ࠷લઢʢ2022/10/8ʣ | NHK  https://www3.nhk.or.jp/news/html/20221008/k10013851401000.html Ҏ্ɺ͝੩ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ɻ SFGFSFODF Thank you! • ʮͱΜͰ΋ͳ͘ϋΠΫΦϦςΟʔʯ࿩୊ͷը૾AIʮNovel AIʯͰͻͨ͢Βೋ࣍ݩඒগঁͱඒগ೥Λੜ੒ͯ͠Έͨ | ITmedia  https://www.itmedia.co.jp/news/articles/2208/29/news133.html • ʮӺ೫Έ͔ͪʯεέεέεΧʔτ͕େ෺ٞɹ౦ژϝτϩɺ൷൑ड͚ඍົʹʮमਖ਼ʯʢ2016/10/18ʣ | JCASTχϡʔε  https://www.j-cast.com/2016/10/18280985.html