Outline - Feature Extraction

[johko]

Here is the outline for the Feature Extraction section:

• Feature Detection - feature_description.mdx - @blessondavis

  • What are features?
  • What makes a good feature?
  • Simple Feature Detection (e.g. Harris Corner Detection, Hough Transform, Shi-Tomasi)

• Feature Description - feature_description.mdx - @aman06012003

  • How can we represent features in data structures?
  • What makes a good descriptor (think of different image conditions, rotation, translation, etc.)
  • Example algorithm: SIFT & SURF

• Feature Matching - feature_matching.mdx - @kfahn22

  • How can we match detected features from image-to-image?
  • Examples (Brute Force, FLANN, maybe others)

• CNN Features + Visualization - feature_visualization.ipynb - @johko

  • How do ANN (especially CNNs) detect features?
  • What do the features “look like”?
  • Some nice visualizations, maybe some DeepDream for fun

• Feature Extraction Notebook - feature_extraction.ipynb - @BSophia

• Feature Visualization Notebook - feature_visualization.ipynb - @JavidanAbdullayev

Resources:
https://docs.opencv.org/4.8.0/db/d27/tutorial_py_table_of_contents_feature2d.html
https://towardsdatascience.com/image-feature-extraction-traditional-and-deep-learning-techniques-ccc059195d04
https://fpcv.cs.columbia.edu/

Working on this part are @kfahn22, @aman06012003, @blessondavis, @JavidanAbdullayev, @BSophia, @johko

[kfahn22]

I am trying to trouble-shoot something that showed up in the quality test. I didn't add a link to an actual image in feature-matching.mdx and I am guessing this is the issue. (At least the test failed at line 27):
img1 = cv.imread('image1.png',cv.IMREAD_GRAYSCALE)

Nevermind, I have fixed the issue.