This paper proposes a 2-dimensional (2D) maximum entropy threshold segmentation (2DMETS) based speeded-up robust features (SURF) approach for image target matching. First of all, based on the gray level of each pixel and the average gray level of its neighboring pixels, we construct a 2D gray histogram. Second, by the target and background segmentation, we localize the feature points at the interest points which have the local extremum of box filter responses. Third, from the 2D Haar wavelet responses, we generate the 64-dimensional (64D) feature point descriptor vectors. Finally, we perform the target matching according to the comparisons of the 64D feature point descriptor vectors. Experimental results show that our proposed approach can effectively enhance the target matching performance, as well as preserving the real-time capacity.
In recent decades, the image target matching not only plays a significant role in many research fields, like the computer vision and digital image processing [
The basic motivation of addressing 2DMETS based SURF in this paper is to improve the cost efficiency and matching accuracy further. In concrete terms, due to the smaller sizes of descriptors in integral images (e.g., each descriptor in SURF only contains 64 bins which is half the size of the descriptor in SIFT), 2DMETS based SURF requires lower computation cost for the detecting and matching of feature points compared to the conventional SIFT [
The rest of this paper is structured as follows. In Section
As the first representative work on image target matching, the authors in [
In recent decades, many institutes and universities proposed a variety of enhanced approaches for image target matching, like the principle component analysis-based SIFT (PCA-SIFT), Harris-SIFT, affine SIFT (ASIFT), shape SIFT (SSIFT), and speeded-up robust features (SURF). The descriptors in PCA-SIFT can effectively reduce the number and dimensions of feature points. In concrete terms, the descriptors in PCA-SIFT encode salient aspect of image gradients into the neighborhood of feature points and then normalize the gradient patches by using the PCA approach [
The abovementioned algorithms fail to carefully consider the interference of background noise and edge pixels on image target matching. To fix this problem, we propose the 2DMETS based SURF in this paper. 2DMETS based SURF can be simply recognized as an integration of 2DMETS and SURF.
In 2DMETS based SURF, we first construct a 2D gray histogram based on the gray level of each pixel and the average gray level of its 8 neighboring pixels (or
Flow chart of 2DMETS based SURF.
For each raw image
If we set the maximum entropy threshold at gray level pair
The total entropy (
We select the pair
The three main steps involved in the determination of feature points are as follows: integral image construction, interest point detection, and Gaussian scale approximation.
After the Gaussian scales have been approximated, all the interested points can be detected. As the final step of the feature point determination, we compare each interested point with its 26 neighboring pixels in a
To guarantee the rotation invariance, each feature point is assigned by a reproducible orientation. By assuming that a feature point is found at scale
We adopt the Euclidean distance to evaluate the similarity of every two normalized SURF descriptors (
There are four groups of images selected for the testing: (i) group 1 (in Figure
(a) Otsu segmentation on images in group 1. (b) 2DMETS on images in group 1.
(a) Otsu segmentation on images in group 2. (b) 2DMETS on images in group 2.
(a) Otsu segmentation on images in group 3. (b) 2DMETS on images in group 3.
(a) Otsu segmentation on images in group 4. (b) 2DMETS on images in group 4.
First of all, we apply Otsu segmentation and 2DMETS to transform the raw images into black-and-white images in a uniform gray scale to mitigate the interference from background noise and edge pixels, as shown in Figures
Second, Figures
Matching performance for images in group 1.
Parameters | SIFT | SURF | Otsu based SIFT | Otsu based SURF | 2DMETS based SIFT | 2DMETS based SURF |
---|---|---|---|---|---|---|
Number of feature points (left/right images) | 84/88 | 60/69 | 223/169 | 82/83 | 698/321 | 116/89 |
Number of correct matches | 10 | 18 | 21 | 25 | 21 | 22 |
Number of incorrect matches | 1 | 3 | 3 | 2 | 1 | 1 |
Matching performance for images in group 2.
Parameters | SIFT | SURF | Otsu based SIFT | Otsu based SURF | 2DMETS based SIFT | 2DMETS based SURF |
---|---|---|---|---|---|---|
Number of feature points (left/right images) | 151/86 | 210/161 | 152/169 | 175/144 | 478/508 | 221/189 |
Number of correct matches | 56 | 99 | 46 | 80 | 136 | 144 |
Number of incorrect matches | 2 | 2 | 5 | 2 | 1 | 0 |
Matching performance for images in group 3.
Parameters | SIFT | SURF | Otsu based SIFT | Otsu based SURF | 2DMETS based SIFT | 2DMETS based SURF |
---|---|---|---|---|---|---|
Number of feature points (left/right images) | 827/796 | 406/429 | 1570/1211 | 418/430 | 1756/1522 | 378/414 |
Number of correct matches | 2 | 4 | 6 | 8 | 4 | 11 |
Number of incorrect matches | 0 | 0 | 2 | 3 | 0 | 0 |
Matching performance for images in group 4.
Parameters | SIFT | SURF | Otsu based SIFT | Otsu based SURF | 2DMETS based SIFT | 2DMETS based SURF |
---|---|---|---|---|---|---|
Number of feature points (left/right images) | 342/182 | 316/296 | 339/458 | 328/269 | 355/407 | 296/322 |
Number of correct matches | 11 | 56 | 1 | 40 | 8 | 62 |
Number of incorrect matches | 3 | 0 | 0 | 4 | 0 | 0 |
Target matching for images in group 1.
SIFT
SURF
Otsu based SIFT
Otsu based SURF
2DMETS based SIFT
2DMETS based SURF
Target matching for images in group 2.
SIFT
SURF
Otsu based SIFT
Otsu based SURF
2DMETS based SIFT
2DMETS based SURF
Target matching for images in group 3.
SIFT
SURF
Otsu based SIFT
Otsu based SURF
2DMETS based SIFT
2DMETS based SURF
Target matching for images in group 4.
SIFT
SURF
Otsu based SIFT
Otsu based SURF
2DMETS based SIFT
2DMETS based SURF
After the affine transformation, if there is a pair of feature points located at the same target in the two different images, a
We use
The matching time determines the real-time capacity of our proposed approach. We define it as the time cost for feature point searching and target matching. The
Repeatability,
Repeatability
Match Score
Correct Matching Rate
Matching time
As can be seen from Figure
A novel 2DMETS based SURF proposed in this paper is proved to perform well in accuracy and computation cost for image target matching. Compared to the conventional SIFT, SURF, Otsu based SIFT, Otsu based SURF, and the enhanced 2DMETS based SIFT, an effective improvement of
The authors declare that there is no conflict of interests regarding the publication of this paper.
The authors wish to thank the editor and all the reviewers for the careful review and the effort in processing this paper. This work was supported in part by the Program for Changjiang Scholars and Innovative Research Team in University (IRT1299), National Natural Science Foundation of China (61301126), Special Fund of Chongqing Key Laboratory (CSTC), Fundamental and Frontier Research Project of Chongqing (cstc2013jcyjA40041, cstc2013jcyjA40032, and cstc2013jcyjA40034), Scientific and Technological Research Program of Chongqing Municipal Education Commission (KJ130528, KJ1400413), Startup Foundation for Doctors of CQUPT (A2012-33), Science Foundation for Young Scientists of CQUPT (A2012-77), and Student Research Training Program of CQUPT (A2013-64).