Abstract




 
   

IJE TRANSACTIONS B: Applications Vol. 31, No. 11 (November 2018) 1862-1869    Article in Press

PDF URL: http://www.ije.ir/Vol31/No11/B/9-2933.pdf  
downloaded Downloaded: 25   viewed Viewed: 255

  DPML-RISK: AN EFFICIENT ALGORITHM FOR IMAGE REGISTRATION
 
S. Kazemi and M. R. Ahmadzadeh
 
( Received: March 16, 2018 – Accepted in Revised Form: October 26, 2018 )
 
 

Abstract    Targets and objects registration and tracking in a sequence of images play an important role in various areas. One of the methods in image registration is feature-based algorithm which is accomplished in two steps. The first step includes finding features of sensed and reference images. In this step, a scale space is used to reduce the sensitivity of detected features to the scale changes. Afterward, we attribute feature points that obtained in the first step, descriptions using brightness value around the feature points. In this paper, a new algorithm is proposed based on Binary Robust Invariant Scalable Keypoints (BRISK) and Scale Invariant Feature Transform (SIFT) algorithms. The proposed algorithm uses the directional pattern to describe the edges which are around the keypoints. This pattern is perpendicular to the direction of keypoints which shows the direction of the edge and provides more useful information regarding brightness around the feature point to make descriptor vector. Furthermore, in the proposed algorithm, the output vector consists of multilevel values instead of binary values which means further useful information is involved in the descriptor vector. Also, levels of output vectors can be adjusted using a single parameter so that the processor with low computing ability can tune the output to a binary vector. Experimental results show that the proposed algorithm is more robust than the BRISK algorithm and the efficiency of the algorithm is about the same as BRISK algorithm.

 

Keywords    Feature Detection; Binary Descriptor; Image Registration; Scale Invariant Feature Transform

 

چکیده   

تطبیق و ره‌گیری اهداف در تصاویر نقش عمده‌ای را در صنعت‌ ایفا می‌کنند. یکی از روش‌های تطبیق استفاده از الگوریتم‌های مبتنی بر ویژگی است که به‌طورمعمول در دو مرحله صورت می‌گیرد. در اولین مرحله‌ی این الگوریتم‌ها، ویژگی‌هایی در تصویر دریافتی و تصویر هدف با استفاده از فضای مقیاسی استخراج می‌شود. سپس برای هر نقطه کلیدی به‌دست‌آمده در مرحله اول بر اساس شدت روشنایی اطراف آن یک بردار توصیفگر ساخته می‌شود. در این مقاله الگوریتم جدیدی با الهام از دو الگوریتم BRISK و SIFT، پیشنهادشده است. این الگوریتم از الگوی جهتی برای توصیف ویژگی استفاده می‌کند. جهت این الگو در جهت عمود بر زاویه ویژگی قرار می‌گیرد که این امر باعث می‌شود که اطلاعات مفیدتری از روشنایی‌های اطراف نقاط کلیدی در ساخت بردار توصیفگر استفاده شود. علاوه بر این بردار خروجی در الگوریتم پیشنهادی به‌صورت یک بردار چند سطحی است که باعث قدرت تمایز بیشتری می‌شود. نتایج این پژوهش نشان می‌دهد که قدرت تمایز و پایداری الگوریتم‌ پیشنهادی نسبت به الگوریتم BRISK قوی‌تر شده است و از نظر کارآمدی الگوریتم تا حدود زیادی با الگوریتم BRISK برابر است.

References   

1. Oliveira, F.P., Tavares, J.M.R.J.C.m.i.b. and engineering, b., "Medical image registration: A review",  Vol. 17, No. 2, (2014), 73-93.

2. Patel, Paresh M., and Vishal M. Shah. "Image registration techniques: a comprehensive survey." International Journal of Innovative Research and Development, Vol. 3, No. 3, (2014), 68-78.

3. Zitova, B., Flusser, J.J.I. and computing, v., "Image registration methods: A survey",  Vol. 21, No. 11, (2003), 977-1000.

4. Karimi, M., A. Sadeghi Niaraki, and A. Hosseininaveh Ahmadabadian. "Automatic Recognition of Coded Targets Using Feature Based Matching Algorithms in a Ubiquitous GIS." Journal of Geomatics Science and Technology 7, No. 1 (2017): 1-13.

5. Hassaballah, M., Aly Amin Abdelmgeid, and Hammam A. Alshazly. "Image features detection, description and matching." In Image Feature Detectors and Descriptors, pp. 11-45. Springer, Cham, 2016.

6. Lowe, D.G.J.I.j.o.c.v., "Distinctive image features from scale-invariant keypoints",  Vol. 60, No. 2, (2004), 91-110.

7. Lowe, David G. "Object recognition from local scale-invariant features." In Computer vision, 1999. The proceedings of the seventh IEEE international conference on, vol. 2, pp. 1150-1157. IEEE, 1999.

8. Bay, Herbert, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool. "Speeded-up robust features (SURF)." Computer vision and image understanding, Vol. 110, No. 3 (2008): 346-359.

9. Khatami, A., Babaie, M., Tizhoosh, H., Nazari, A., Khosravi, A. and Nahavandi, S.J.I.J.o.E.-T.C.A., "A radon-based convolutional neural network for medical image retrieval",  Vol. 31, No. 6, (2018), 910-915.

10. Leutenegger, S., Chli, M. and Siegwart, R.Y., "Brisk: Binary robust invariant scalable keypoints", in Computer Vision (ICCV), 2011 IEEE International Conference on, IEEE. Vol., No. Issue, (2011), 2548-2555.

11. Mair, E., Hager, G.D., Burschka, D., Suppa, M. and Hirzinger, G., "Adaptive and generic corner detection based on the accelerated segment test", in European conference on Computer vision, Springer. Vol., No. Issue, (2010), 183-196.

12. Alahi, A., Ortiz, R. and Vandergheynst, P., "Freak: Fast retina keypoint", in 2012 IEEE Conference on Computer Vision and Pattern Recognition, Ieee. Vol., No. Issue, (2012), 510-517.

13. Lindeberg, T.J.E.o.M., "Scale-space theory",  Vol., No., (2001).

14. Mikolajczyk, K., Schmid, C.J.I.t.o.p.a. and intelligence, m., "A performance evaluation of local descriptors",  Vol. 27, No. 10, (2005), 1615-1630.


Download PDF 



International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir