From 2a1b884e841efe562e0c84885a404819433b3405 Mon Sep 17 00:00:00 2001 From: Jules Laplace Date: Wed, 5 Dec 2018 16:19:50 +0100 Subject: styling images --- .../research/01_from_1_to_100_pixels/index.html | 101 +++++++++++++++++++++ 1 file changed, 101 insertions(+) create mode 100644 site/public/research/01_from_1_to_100_pixels/index.html (limited to 'site/public/research/01_from_1_to_100_pixels') diff --git a/site/public/research/01_from_1_to_100_pixels/index.html b/site/public/research/01_from_1_to_100_pixels/index.html new file mode 100644 index 00000000..90f142e9 --- /dev/null +++ b/site/public/research/01_from_1_to_100_pixels/index.html @@ -0,0 +1,101 @@ + + + + MegaPixels + + + + + + + + + +
+ + +
MegaPixels
+ The Darkside of Datasets +
+ +
+
+ +
+

From 1 to 100 Pixels

+
+
+
Posted
+
2018-12-04
+
+
+
By
+
Adam Harvey
+
+ +
+
+ +

High resolution insights from low resolution data

+

This post will be about the meaning of "face". How do people define it? How to biometrics researchers define it? How has it changed during the last decade.

+

What can you know from a very small amount of information?

+
    +
  • 1 pixel grayscale
  • +
  • 2x2 pixels grayscale, font example
  • +
  • 4x4 pixels
  • +
  • 8x8 yotta yotta
  • +
  • 5x7 face recognition
  • +
  • 12x16 activity recognition
  • +
  • 6/5 (up to 124/106) pixels in height/width, and the average is 24/20 for QMUL SurvFace
  • +
  • 20x16 tiny faces paper
  • +
  • 20x20 MNIST handwritten images http://yann.lecun.com/exdb/mnist/
  • +
  • 24x24 haarcascade detector idealized images
  • +
  • 32x32 CIFAR image dataset
  • +
  • 40x40 can do emotion detection, face recognition at scale, 3d modeling of the face. include datasets with faces at this resolution including pedestrian.
  • +
  • need more material from 60-100
  • +
  • 60x60 show how texture emerges and pupils, eye color, higher resolution of features and compare to lower resolution faces
  • +
  • 100x100 0.5% of one Instagram photo
  • +
+

Find specific cases of facial resolution being used in legal cases, forensic investigations, or military footage

+

Research

+
    +
  • NIST report on sres states several resolutions
  • +
  • "Results show that the tested face recognition systems yielded similar performance for query sets with eye-to-eye distance from 60 pixels to 30 pixels" 1
  • +
+
+
+
  1. NIST 906932. Performance Assessment of Face Recognition Using Super-Resolution. Shuowen Hu, Robert Maschal, S. Susan Young, Tsai Hong Hong, Jonathon P. Phillips

  2. +
+
+
+ +
+

MORE RESEARCH

+
+ +
+
+ +
+ + + + \ No newline at end of file -- cgit v1.2.3-70-g09d2