| AndreBeinrucker |
simple_edgedetector/5 |
44 |
1 |
This is a very crude edge detector, looking at the differences between pixel values. |
Jan. 23, 2012, 3:51 p.m. |
| AndreBeinrucker |
simple_pixel_difference |
37 |
1 |
Checks whether the difference of a pixel value to the value of the neighbor pixel is higher than a threshold. |
May 8, 2011, 8:57 p.m. |
| bedrorom |
mass_center/1 |
40 |
1 |
Counts coordinates of center of mass of each layer (r, g, b, white, black) of an input image. |
March 28, 2012, 12:14 p.m. |
| cdubout |
hough/3 |
19 |
1 |
Computes the linear Hough transform of the region of interest to detect lines. |
April 20, 2010, 12:35 p.m. |
| cdubout |
fourier/4 |
33 |
2 |
Fourier transform heuristic. Computes the 2D FFT of the region of interest to convert it to the frequency domain. |
March 14, 2011, 4 p.m. |
| cdubout |
haar |
36 |
1 |
Haar transform heuristic. Computes the 2D haar transform of the region of interest (all levels). |
April 20, 2010, 8:18 p.m. |
| cdubout |
identity |
29 |
1 |
Same as the mash/identity heuristic except that it returns RGB values instead of grayscale. |
April 20, 2010, 8:24 p.m. |
| cdubout |
hog/6 |
2 |
2 |
Histogram of oriented gradients (orientation discretized in 12 bins) taken at random positions and scales.
Strongly inspired from francoisfleuret/zk_v2. |
Sept. 28, 2010, 12:49 p.m. |
| cdubout |
hog_daisy/2 |
11 |
1 |
|
Nov. 15, 2011, 10:47 a.m. |
| cdubout |
segmentation2 |
46 |
1 |
Segment the gray-scale image pixels into 2 categories, the ones above the average intensity, and the ones below. |
Sept. 26, 2010, 11:57 p.m. |
| cdubout |
segmentation8 |
43 |
1 |
Segment the gray-scale image intensities into 8 bins with equal number of pixels in each.
Returns the index of the bins in which a new pixel falls. |
Sept. 27, 2010, 10:29 a.m. |
| cdubout |
hogblurred/4 |
3 |
1 |
Strongly blurred gradient magnitude images for 8 different gradient orientations (also rescales the image to 25% to save on features).
|
Sept. 28, 2010, 12:48 p.m. |
| cdubout |
mb_ilbp/4 |
8 |
2 |
Pyramid of histograms of multi-block improved local binary patterns.
Inspired from ftarsett/ilbp and created with the help of Cosmin Atanasoei. |
May 3, 2011, 7:32 p.m. |
| cdubout |
patches/3 |
12 |
2 |
Histogram of the (maximum and minimum) correlation with a dictionary of patches. |
June 30, 2011, 3:21 p.m. |
| cdubout |
v1plus |
5 |
1 |
|
June 15, 2011, 12:30 a.m. |
| cdubout |
hog_felzenszwalb/23 |
6 |
6 |
Histogram of oriented gradients, as described in the paper 'Object Detection with Discriminatively Trained Part Based Models' by Felzenszwalb et al. |
Jan. 6, 2012, 2:42 p.m. |
| cdubout |
viola_jones/4 |
20 |
2 |
The rectangle features used by Viola and Jones in their famous IJCV paper "Robust Real-time Object Detection". |
July 6, 2011, 11:15 a.m. |
| dubecmar |
normalization |
39 |
1 |
Heuristic to stretch the range of intensities include intensity normalization |
Oct. 21, 2010, 2:01 p.m. |
| FrancoisFleuret |
average |
59 |
1 |
Return the average level of the pixel gray levels. |
Oct. 2, 2009, 8:08 a.m. |
| FrancoisFleuret |
boxedaverages/3 |
26 |
3 |
Computes the average gray level over rectangular windows picked at random.
|
Feb. 23, 2011, 8:53 a.m. |
| FrancoisFleuret |
chamferzk/4 |
22 |
3 |
For each pixel, computes 8 Chamfer distances to as many edge orientations. |
Feb. 24, 2011, 11:27 a.m. |
| FrancoisFleuret |
zk/4 |
9 |
4 |
Computes proportion of edges over rectangles picked at random.
|
Feb. 16, 2011, 4:23 p.m. |
| ftarsett |
lbp |
56 |
1 |
This heuristics computes a Local Binary Pattern (LBP) |
July 10, 2009, 6:47 p.m. |
| ftarsett |
ilbp |
50 |
1 |
This heuristics computes an Improved Local Binary Pattern (LBP). compare pixels to it's mean value |
July 14, 2009, 11:02 a.m. |
| GillesBlanchard |
blockwise |
30 |
1 |
Differences of blockwise averages at different scales on the ROI
(Haar wavelets à la Viola and Jones) |
March 24, 2010, 2:53 p.m. |
| GillesBlanchard |
blockwise2 |
25 |
1 |
|
May 23, 2011, 2:20 p.m. |
| jena |
radialedgesstats/4 |
23 |
1 |
Computes several edge-based statistics along the radial directions. |
May 12, 2011, 5:18 p.m. |
| jena |
randomprojections |
57 |
1 |
Computes a set of random projections of the gray-scale ROI. |
May 19, 2011, 10:27 a.m. |
| johndoe |
average |
60 |
1 |
|
Sept. 27, 2010, 5:04 p.m. |
| Kanma |
closerpixel |
52 |
1 |
This heuristic looks at 9x9 blocks of grayscale pixels and returns the index of the one which is the closer (intensity-wise) of the center one. |
July 13, 2009, 3:32 p.m. |
| Kanma |
fartherpixel |
61 |
1 |
This heuristic looks at 9x9 blocks of grayscale pixels and returns the index of the one which is the farther (intensity-wise) of the center one. |
July 13, 2009, 3:33 p.m. |
| Kanma |
grayscalehistogram |
41 |
1 |
This heuristic computes the histogram of the region of interest, in grayscale format |
July 13, 2009, 3:33 p.m. |
| Kanma |
rgbhistogram |
27 |
1 |
This heuristic computes the histogram of the region of interest, in RGB format. The RGB color-space is segmented in 512 parts (8 per channel). |
July 13, 2009, 3:34 p.m. |
| Kanma |
blobs |
31 |
1 |
This heuristic produces a 'blobbed' version of the (RGB) region of interest. |
April 29, 2010, 11:20 a.m. |
| kaslzden |
detect_color_regions_red/3 |
48 |
1 |
This heuristics is used to compute position of the most significant red region. |
May 15, 2012, 7:10 p.m. |
| kaslzden |
detect_color_regions_green/1 |
55 |
0 |
This heuristics is used to compute position of the most significant green region. |
May 15, 2012, 7:26 p.m. |
| kaslzden |
detect_color_regions_blue/1 |
62 |
0 |
This heuristics is used to compute position of the most significant blue region. |
May 15, 2012, 7:27 p.m. |
| kaslzden |
detect_color_regions_wooden |
53 |
1 |
This heuristics is used to compute position of the most significant wooden region. |
May 15, 2012, 7:49 p.m. |
| kaslzden |
detect_color_regions_yellow |
51 |
1 |
This heuristics is used to compute position of the most significant yellow region. |
May 15, 2012, 7:50 p.m. |
| leonidas |
dt_hogs10 |
10 |
1 |
Same heuristic different parameters |
Oct. 14, 2010, 6:18 p.m. |
| leonidas |
rgb_hogsplushist2/2 |
1 |
2 |
|
Dec. 27, 2011, 8:50 p.m. |
| leonidas |
dt_hogs6 |
7 |
1 |
Histograms of Oriented Gradients (Dalal and Triggs) |
July 27, 2010, 12:25 p.m. |
| leonidas |
rgb_hogs/2 |
4 |
2 |
With color |
Dec. 27, 2011, 8:33 p.m. |
| leonidas |
simple_color_hist |
35 |
1 |
Average RGB values |
Nov. 4, 2010, 5:09 p.m. |
| leonidas |
lopd/13 |
13 |
1 |
Pooled gradients taken at positions on a circular grid (Daisy-like). |
May 26, 2011, 11:46 p.m. |
| leonidas |
laws/2 |
34 |
1 |
A texture descriptor using 3x3 Laws masks |
June 7, 2011, 12:17 p.m. |
| leonidas |
scratches/4 |
14 |
3 |
Yet another codebook descriptor. |
July 8, 2011, 9:34 a.m. |
| leonidas |
catches/4 |
16 |
3 |
Another codebook based descriptor |
July 8, 2011, 9:48 a.m. |
| leonidas |
corner_catches256/2 |
21 |
2 |
|
July 8, 2011, 9:44 a.m. |
| leonidas |
corner_scratches256/2 |
15 |
2 |
|
July 8, 2011, 9:16 a.m. |
