Police sketch generator using generative adversarial networks.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Police sketch generator using generative adversarial networks.
Συγγραφείς: Poornima, Ediga, Tarang, Goggi Ruthvik, Numaan, Syed Khasim, Kashyap, Burra, Seshappa, Angadi, Ihassan, Mohammed, Saini, Manisha, Sehgal, Archana
Πηγή: AIP Conference Proceedings; 2025, Vol. 3263 Issue 1, p1-16, 16p
Θεματικοί όροι: Generative adversarial networks, Criminal investigation, Program generators (Computer programs), Pen drawing, Eyewitness accounts, Police, Artificial intelligence, Face perception
Περίληψη: Facial sketches drawn by a traditional artist have long occupied an exclusive place in the field of law enforcement as a quick-communicator for what somebody looks like based on eyewitness accounts when pursuing fugitives. Other studies have attempted to improve this method and compared it with all points bulletins 222 or composites. However, the creation of facial composites via applications has always been a time-consuming endeavor. This work showcases a novel use of GANs to devise an application that can morph police sketches in new way. The main purpose of this unbelievable tool, is to produce nearly natural however completely imaginary human faces with changeable sliders such as skin color, facial hair and head form. It quickly generates thousands of unique facial profiles that resemble real people. Using input from eyewitness descriptions, the generator network then improves that output accordingly to better fit with what was described verbally. As the GAN continues to train, it learns how to create detailed sketches with fine distinctions in facial features, expressions or other details. This is a major benefit for criminal investigations by speeding the process of creating an accurate suspect sketch, which could be key in identifying and catching someone wanted. [ABSTRACT FROM AUTHOR]
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Complementary Index
FullText Text:
  Availability: 0
Header DbId: edb
DbLabel: Complementary Index
An: 187395242
RelevancyScore: 1009
AccessLevel: 6
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 1008.54614257813
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Police sketch generator using generative adversarial networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Poornima%2C+Ediga%22">Poornima, Ediga</searchLink><br /><searchLink fieldCode="AR" term="%22Tarang%2C+Goggi+Ruthvik%22">Tarang, Goggi Ruthvik</searchLink><br /><searchLink fieldCode="AR" term="%22Numaan%2C+Syed+Khasim%22">Numaan, Syed Khasim</searchLink><br /><searchLink fieldCode="AR" term="%22Kashyap%2C+Burra%22">Kashyap, Burra</searchLink><br /><searchLink fieldCode="AR" term="%22Seshappa%2C+Angadi%22">Seshappa, Angadi</searchLink><br /><searchLink fieldCode="AR" term="%22Ihassan%2C+Mohammed%22">Ihassan, Mohammed</searchLink><br /><searchLink fieldCode="AR" term="%22Saini%2C+Manisha%22">Saini, Manisha</searchLink><br /><searchLink fieldCode="AR" term="%22Sehgal%2C+Archana%22">Sehgal, Archana</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: AIP Conference Proceedings; 2025, Vol. 3263 Issue 1, p1-16, 16p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Generative+adversarial+networks%22">Generative adversarial networks</searchLink><br /><searchLink fieldCode="DE" term="%22Criminal+investigation%22">Criminal investigation</searchLink><br /><searchLink fieldCode="DE" term="%22Program+generators+%28Computer+programs%29%22">Program generators (Computer programs)</searchLink><br /><searchLink fieldCode="DE" term="%22Pen+drawing%22">Pen drawing</searchLink><br /><searchLink fieldCode="DE" term="%22Eyewitness+accounts%22">Eyewitness accounts</searchLink><br /><searchLink fieldCode="DE" term="%22Police%22">Police</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Face+perception%22">Face perception</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Facial sketches drawn by a traditional artist have long occupied an exclusive place in the field of law enforcement as a quick-communicator for what somebody looks like based on eyewitness accounts when pursuing fugitives. Other studies have attempted to improve this method and compared it with all points bulletins 222 or composites. However, the creation of facial composites via applications has always been a time-consuming endeavor. This work showcases a novel use of GANs to devise an application that can morph police sketches in new way. The main purpose of this unbelievable tool, is to produce nearly natural however completely imaginary human faces with changeable sliders such as skin color, facial hair and head form. It quickly generates thousands of unique facial profiles that resemble real people. Using input from eyewitness descriptions, the generator network then improves that output accordingly to better fit with what was described verbally. As the GAN continues to train, it learns how to create detailed sketches with fine distinctions in facial features, expressions or other details. This is a major benefit for criminal investigations by speeding the process of creating an accurate suspect sketch, which could be key in identifying and catching someone wanted. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=187395242
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1063/5.0261372
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 1
    Subjects:
      – SubjectFull: Generative adversarial networks
        Type: general
      – SubjectFull: Criminal investigation
        Type: general
      – SubjectFull: Program generators (Computer programs)
        Type: general
      – SubjectFull: Pen drawing
        Type: general
      – SubjectFull: Eyewitness accounts
        Type: general
      – SubjectFull: Police
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Face perception
        Type: general
    Titles:
      – TitleFull: Police sketch generator using generative adversarial networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Poornima, Ediga
      – PersonEntity:
          Name:
            NameFull: Tarang, Goggi Ruthvik
      – PersonEntity:
          Name:
            NameFull: Numaan, Syed Khasim
      – PersonEntity:
          Name:
            NameFull: Kashyap, Burra
      – PersonEntity:
          Name:
            NameFull: Seshappa, Angadi
      – PersonEntity:
          Name:
            NameFull: Ihassan, Mohammed
      – PersonEntity:
          Name:
            NameFull: Saini, Manisha
      – PersonEntity:
          Name:
            NameFull: Sehgal, Archana
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 16
              M: 04
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 0094243X
          Numbering:
            – Type: volume
              Value: 3263
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: AIP Conference Proceedings
              Type: main
ResultId 1