1 / 13

Identification of animal images based on DNA

Identification of animal images based on DNA. Lior Wolf and Yoni Donner The School of Computer Science Tel-Aviv University. Visual appearance is largely determined by genetics…. …and appearance affecting genes have been identified. Eye color Sturm & Frudakis (2004).

avye-pugh
Download Presentation

Identification of animal images based on DNA

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Identification of animal images based on DNA Lior Wolf and Yoni DonnerThe School of Computer ScienceTel-Aviv University

  2. Visual appearance is largely determined by genetics…

  3. …and appearance affecting genes have been identified • Eye colorSturm & Frudakis (2004). • Skeletel structureChase, et al. (2002). • Dog heightSutterm, (2007).

  4. Our work is unique in the following ways: High Dimensionalworking directly with images Using very short 500bp sequences Correlative linksNot causal ones

  5. We employ mtDNA • Has no causal link to appearance • Easy to collect • Good marker for evolutionary history

  6. Tasks 1. Image synthesis given DNA (!) 2. Identification of the correct image given DNA

  7. Image synthesis Originalimage Extracted contour Recovered contour The algorithm predicts the contour of an unseen species based on its mtDNA

  8. Identification Acanthopagrus Butcheri ? Epinephelus ongus Given mtDNA, the algorithm identifies the correct unseen image

  9. Data sets Fishes of Australia Birds of North America Head view Dorsal view Profile view Ants of Madagascar

  10. Methods Three technical questions: • How do we represent the genetic sequences? • How do we represent the images? • How do we learn the connections? Simple intuitive vector representation Well known techniques: Bag of SIFT or C1 Regularized CCA

  11. Results • 93 fish species, 82 for training, 11 for testing • Significantly better than chance or NN

  12. Results Fish: 90% correct Birds: 72% correct Head: 56% correct Dorsal: 59% correct Profile: 64% correct

  13. Conclusions • Visual identification and image synthesis based on DNA sequences is a reality • Employing the power of correlation rather than causality • Future applications? • Virtual line-ups • Personalized medication • Prediction of appearance of extinct animals

More Related