Comparison of Sift,surf,orb,fast,brisk feature extraction algorithms

Original: http://blog.csdn.net/vonzhoufz/article/details/46594369

Image processing is based on the extraction of feature points, feature (interest points) Detect method is also in continuous progress, edge detection, corner detection, line detection, round detection, SIFT feature point detection, while the descriptor is also in the development, in order to match the efficient, Gradually from high-dimensional eigenvectors to binary vectors ... Below do a simple list and call the OpenCV API to see the effects!
To undertake the previous article.

Feature Detection Methods List:

• Canny Edge Detect, A computational approach to Edge Detection, 1986. The Canny edge detector is an edge detection operator, uses a multi-stage algorithm to detect a wide range of edges in Images.
• Harris, A combined corner and Edge detector, 1988. Considering the differential of the corner score with respect to direction directly.
• Gftt,good Features to track,1994, determines strong corners in an image.
• Matas-2000, robust Detection of Lines Using the Progressiveprobabilistic Hough Transform. The Hough transform detects straight lines.
• Sift,distinctive image Features from Scale-invariant keypoints,2004, invariant to Image translation, scaling, and rotation , partially invariant to illumination changes and robust to local geometric distortion. 128-dim (512B).
• SURF, speeded up robust features,2006, inspired by sift, faster than sift, robust. 64-dim (256B).
• FAST, machine learning for high-speed Corner Detection, 2006,wiki. Very fast, not robust to high level noise.
• ORB, Orb:an efficient alternative to SIFT or surf,2011, based on fast and brief, two orders of magnitude faster than SIFT, available as an alternative to SIFT (a fusion of fast KeyPoint Detector and BRIEF descriptor). 32B binary Descriptor.
• Brisk,brisk:binary robust Invariant Scalable keypoints, 2011. 64B binary Descriptor.
• Star,censure:center surround Extremas for realtime feature detection and matching,2008, the number of references is not high. scale-invariant Center-surround Detector (censure) that claims to outperform other detectors and is capable of real-time implementation.
• Mser,robust Wide Baseline Stereo from maximally Stable extremal regions, 2002, spot detection (BLOB detection).

Feature point extraction Algorithm comparison (image DataSet (Pictures)):

Imageno	SIFT	SURF	ORB	FAST	STAR	Brisk
0	2414	4126	500	11978	715	1538
1	4295	8129	500	16763	1166	1861
2	3404	4784	500	16191	816	1445
3	1639	2802	500	7166	203	699
4	1510	1484	497	29562	2383	3421
5	10572	8309	500	720	0	65
6	191	187	295	16125	825	1782
7	3352	4706	500	567	15	43
8	165	403	374	26701	1558	2762
9	4899	7523	500	12780	473	1299
10	1979	4212	500	10676	864	1498
11	3599	3294	500	36V	0	70
12	163	168	287	7923	661	953
13	1884	2413	500	11681	548	2683
14	2509	5055	500	18097	1671	2898
15	9177	4773	500	7224	842	888
16	3332	3217	500	20502	1381	2612
17	5446	6611	500	16553	683	1959
18	4592	6033	500	706	54	216
19	266	509	55X	9613	356	583
20	2087	2786	500	7459	223	607
21st	2582	3651	500	12147	720	1530
22	2509	4237	500	14890	507	1113
23	1236	4545	500	6473	410	718
24	1311	2606	500	4293	199	491
25	237	387	500	657	122	132
26	968	1418	488	6609	45	343
Time Cost	21.52	17.4	0.97	0.25	2.34	2.14

The above is the time of feature detect, which is measured by some pictures, and then a pair of images to see the total cost of time spent in feature detect and compute feature descriptor (in seconds):

Image pair	SIFT	SURF	ORB	FAST (SURF)
Eiffel-1,13.jpg	2.77	3.22	0.11	0.22

You can see the cost of calculating descriptor is still very large, here are only two pictures, so the main start is the calculation descriptor, extraction is very fast.

Below through two pictures to see these algorithms match the effect, 1639-1311-697 represents the picture 1, 2 respectively extracted 1639,1311 keypoints, which matched 697.

Image pair	SIFT	SURF	ORB	FAST (SURF)	Brisk
Eiffel-1,13.jpg	1639/1311/697	2802/2606/1243	500/500/251	1196/1105/586	607/491/287

Canny Edge Detection effect:

Find line segments by probabilistic Hough transform:

Harris Corner Detection:

SIFT match:

SURF match:

ORB match:

Brisk match:

Here's the code.

Reference:
Canny Edge Detector Example
Feature Detection-canny, Houghlinesp
Harris Corner Detector Example
BRIEF (Binary robust Independent elementary Features)
ORB (oriented FAST and rotated BRIEF)

Comparison of Sift,surf,orb,fast,brisk feature extraction algorithms