1 / 19

Building text features for object image classification

Building text features for object image classification. Group 1 : Eddie Sun, Youngbum Kim, Yulong Wang. Which object is presented ?. Why we need text features?. Main idea & Insights. Main idea

saburo
Télécharger la présentation

Building text features for object image classification

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. Building text features for object image classification Group 1: Eddie Sun, Youngbum Kim, Yulong Wang

  2. Which object is presented?

  3. Why we need text features?

  4. Main idea & Insights • Main idea • Determine which objects are present in an image based on the text that surrounds similar images. • Insights • First, it is often easier to determine the image content using surrounding text than with currently available image features. • Given a large enough dataset, we are bound to find very similar images to an input image, even when matching with simple image features.

  5. Illustration for building text features Internet Images with text Text Features

  6. Framework of the approach Texts of These Similar Images Training Process K Most Similar Images Visual Features: SIFT, Gist, Color, Gradient and Unified of all previous one

  7. Experiment • Dataset • The PASCAL Visual Object Classes Challenge

  8. Experiment • Features • SIFT • Gist • an abstract representation of the scene that spontaneously activates memory representations of scene categories (a city, a mountain, etc.) • Color • Color Features in the RGB space • Gradient • Unified • a concatenation of the above four features

  9. Experiment

  10. Experiment

  11. Experiment

  12. Experiment

  13. Experiment

  14. Summary How it works Results

  15. How it works? Return most similar images with their labels Internet images dataset with text • SIFT • Gist • Color • Gradient • Unified Get similar images based on visual features Construct text features from labels Extract visual features Cute, puppy, canine Dog cool dogs, boxer Input Image 1. Training images 2. Test images Visual features Dog Visual Classifier Puppy Dog, pet, animal Text features Text Classifier Learn parameters on training images Merge • Notes • Unified Feature – weighted average of the above 4 features • Text features – normalized histogram of tags counts Fusion Classifier Dog Final Output

  16. Results • Text features are built from visual features. Better visual features -> better text features • Combining visual and text classifiers Visual and text classifiers correct each other • Number of training images Small number of training images -> text classifiers outperform visual classifiers Combine -> always better • Number of Internet images in dataset 200,000 -> 600,000 : Big improvement 600,000 -> 1 million : very small improvement

  17. Questions?

  18. Thank you!

More Related