Research on speeded-up robust features with RANSAC

KONG Jun; JIANG Min; Alimujiang Yiming
April 2013
International Journal of Advancements in Computing Technology;Apr2013, Vol. 5 Issue 8, p777
Academic Journal
SURF (Speeded-Up Robust Features) algorithm well solves the problems of calculation time and operation speed in image registration. But it has such shortcomings as accuracy and reliability. Especially, with the increase of matching threshold, the error-matched will turn more serious. In order to solve it, this paper proposes a novel registration algorithm R-SURF. Firstly, use integral images, Hessian matrix, scale-space construction, and descriptor vector to generate and detect feature points efficiently. Secondly, feature point matching based on the City-block distance is introduced into image registration so to further improve algorithm reliability. Finally, RANSAC (Random Sample Consensus) method is applied to remove the outlier set and eliminate the extra error-matched feature points to further improve algorithm accuracy. Experimental results prove that the R-SURF algorithm doesn't only retain existed advantages such as low computational cost, high real-time performance, but also improves matching accuracy and reliability.


Related Articles

  • A fully automatic registration approach based on contour and SIFT for HJ-1 images. Ni, XiLiang; Cao, ChunXiang; Ding, Lin; Jiang, Tao; Zhang, Hao; Jia, HuiCong; Li, GuangHe; Zhao, Jian; Chen, Wei; Ji, Wei; Xu, Min; Gao, MengXu; Zheng, Sheng; Tian, Rong; Liu, Cheng; Li, Sha // SCIENCE CHINA Earth Sciences;Oct2012, Vol. 55 Issue 10, p1679 

    To achieve a fully automatic registration between HJ-1 CCD images and HJ-1 infrared images is a difficult task as it must deal with the varying illuminations and resolutions of the images, different perspectives, and the local deformations within the images. In this paper, aimed at those...

  • Illumination Processing Recognition of Face Images Based on Improved Retinex Algorithm. Yang Jie; Wan Li; Qu Changqing // Journal of Multimedia;Oct2013, Vol. 8 Issue 5, p541 

    In order to change the defects of the similar traditional Retinex algorithm that it is easy to appear the "Halo" phenomenon in the illumination image acquisition process, we proposed a study on the face images recognition under the illumination condition based on the improved Retinex Algorithm,...

  • Robust Cephalometric Landmark Identification on Cephalometric Downs Analysis. Ningrum, Ika Purwanti; Harjoko, Agus; Mudjosemedi, Munakhir // International Journal of Computer & Electrical Engineering;Apr2014, Vol. 6 Issue 2, p172 

    Cephalometric landmark identification on cephalometric analysis Downs has been developed. Here we identify a 10 point landmarks used in cephalometric Downs analysis: Gnation, Gonion, Menton, Nation, Orbital, Porion, Point A, Point B, Pogonion, and Sella. The research was conducted in three...

  • Maximum Entropy Threshold Segmentation for Target Matching Using Speeded-Up Robust Features. Mu Zhou; Xia Hong; Zengshan Tian; Huining Dong; Mingchun Wang; Kunjie Xu // Journal of Electrical & Computer Engineering;2014, p1 

    This paper proposes a 2-dimensional (2D) maximumentropy 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...

  • Hausdorff Distance Image Registration based on Features of Harris and SIFT. Liu Jicheng; Wu Linlin; Sun Huilin // Information Technology Journal;2013, Vol. 12 Issue 8, p1571 

    Harris detection and SIFT(Scale-invariant feature transform) are frequently used to image registration, but they have the disadvantages of not adapting the variety of scale and low efficiency, respectively. Hausdorff distance method based on the feature of Harris and SIFT is discussed here....

  • Image Matching Based on Improved Harris Criterion Algorithm. Shyi-Ching Liang; Yen-Chun Lee; LunHao Liao // Journal of Multimedia;Jan2014, Vol. 9 Issue 1, p145 

    This paper proposes a local invariant feature for image matching based on Harris threshold criterion. Based on the extraction of SIFT invariant features, this algorithm chooses the effective features from the extracted invariant features utilizing Harris threshold criterion, which removes lots...

  • A New Zero-Watermarking Scheme Based on Features Extraction for Authentication of Text. Qiaoyan Kuang; Xiaoming Xu // Journal of Convergence Information Technology;Nov2011, Vol. 6 Issue 11, p155 

    Text is the most frequently used medium traveling over the internet besides image, audio, and video. The copyright protection of plain text is the most important issue. In this paper, we propose a robust zero-watermarking algorithm, which integrates the robust features extraction method and...

  • A High-performance Information Hiding Algorithm Based on CL Multi-Wavelet Transform and DCT. Shuai Ren; Tao Zhang // International Journal of Advancements in Computing Technology;May2012, Vol. 4 Issue 8, p137 

    Taking advantage of the feature that the energy of the image would gather and spread on four components (LL2, LH2, HL2 and HH2) in the sub-image after first-order CL multi-wavelet transform, and Using the advantage of Discrete Cosine Transform in application of information hiding, propose an...

  • View Synthesizing for a Large-Scale Object in a Scene. Thein, Thin Lai Lai; Sein, Myint Myint // Telkomnika;2012, Vol. 10 Issue 4, p795 

    A robust method for panorama view reconstruction of a scene is presented. The images of a scene are acquired by moving a camera to multiple viewpoints. We present a robust method of panorama synthesizing based on image mosaicing approach. The edge detection and feature points extraction are...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics