1 / 11

HawtOrNawt : Facial Analysis and Morphing

Manjot Pal and Mikhail Skobov. HawtOrNawt : Facial Analysis and Morphing. Problem: Its been ages that people have been arguing about someone being more attractive than the other. - Instagram, Facebook - Different types of beautification apps - Flickr, Tumblr, other blogs

venice
Download Presentation

HawtOrNawt : Facial Analysis and Morphing

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. Manjot Pal and Mikhail Skobov HawtOrNawt: Facial Analysis and Morphing

  2. Problem: Its been ages that people have been arguing about someone being more attractive than the other.

  3. - Instagram, Facebook - Different types of beautification apps - Flickr, Tumblr, other blogs - Tourism industry - Magazines Motivation

  4. - Detects key facial features - Rotates the face to align it with Cartesian coordinates - Assisted hairline and chin detection Facial Feature Detection

  5. 1. Function gets appropriate set of ratios 2. Each ratio is compared to the expected value and weighed appropriately 3. The weighed scores are averaged, and presented to user Calculating Scores Score: 7.6

  6. - Smoothsimages while preserving edges, by means of a nonlinear combination of nearby image values. - It combines gray levels or colors based on both their geometric closeness and their photometric similarity. - Prefers near values to distant values in both domain and range. Bilateral Filtering

  7. Wp – normalization factor • (p-q) - space weight • (|I(p) – I(q)|) – brightness weight • C. Tomasi and R. Manduchi : • Bilateral Filtering for Gray and Color Images. Algorithm

  8. Perfect

  9. Almost Perfect

  10. Not so good….

  11. - Come up with more smoothing filters - Efficient algorithms to perform smoothing - Measuring attractiveness with the help of different criterion other than just ratios Future

More Related