Computer Vision: Difference between revisions

(2 intermediate revisions by the same user not shown)

Line 1:

Notes from the [https://www.udacity.com/course/introduction-to-computer-vision--ud810 Udacity Computer Vision Course] taught by Georgia Tech professors.

==Hough Transform==

The Hough transform is a voting technique used to find things in images such as lines, circles, and arbitrary shapes.

==Image Features==

===Histogram of Gradients (HOG)===

See [https://www.youtube.com/watch?v=28xk5i1_7Zc].

For each image, HoG generates a feature vector for overlapping 16x16 patchs of the image.

* For each 8x8 patch, compute the gradients for each pixel. Gradients will have a norm and direction.

* Then bin the gradients by direction using bilinear binning (weighted voting) such that each angle will have a sum of norm (e.g. <math>\{0: x_0, 20: x_1, ..., 160: x_8\}</math>. For your 8x8 patch, <math>(x_0, ..., x_8)</math> is your feature vector or ''histogram''. This is called ''orientation binning''.

* For each overlapping 16x16 patch, you have 4 8x8 patches, each with a feature vector. Concatenate all to form a 36-dim feature vector. This feature vector is then normalized with L2-norm.

===SIFT===

Scale Invariant Feature Transform

==Segmentation==

Line 10:

Line 26:

;Pros

* Automatically finds ~~basin~~ of attraction.

* Automatically finds basins of attraction.

* Only one parameter: Window size for region of interest.

* Does not assume any shape on cluster.

@@ Line 1: / Line 1: @@
 Notes from the [https://www.udacity.com/course/introduction-to-computer-vision--ud810 Udacity Computer Vision Course] taught by Georgia Tech professors.
+==Hough Transform==
+The Hough transform is a voting technique used to find things in images such as lines, circles, and arbitrary shapes.
+==Image Features==
+===Histogram of Gradients (HOG)===
+See [https://www.youtube.com/watch?v=28xk5i1_7Zc].
+For each image, HoG generates a feature vector for overlapping 16x16 patchs of the image.
+* For each 8x8 patch, compute the gradients for each pixel. Gradients will have a norm and direction.
+* Then bin the gradients by direction using bilinear binning (weighted voting) such that each angle will have a sum of norm (e.g. <math>\{0: x_0, 20: x_1, ..., 160: x_8\}</math>. For your 8x8 patch, <math>(x_0, ..., x_8)</math> is your feature vector or ''histogram''. This is called ''orientation binning''.
+* For each overlapping 16x16 patch, you have 4 8x8 patches, each with a feature vector. Concatenate all to form a 36-dim feature vector. This feature vector is then normalized with L2-norm.
+===SIFT===
+{{main | SIFT features}}
+Scale Invariant Feature Transform
 ==Segmentation==
@@ Line 10: / Line 26: @@
 ;Pros
-* Automatically finds basin of attraction.
+* Automatically finds basins of attraction.
 * Only one parameter: Window size for region of interest.
 * Does not assume any shape on cluster.