Image Stitching Based on Improved SURF Algorithm

In order to solve the problem of uneven distribution of picture features and stitching of images, an improved SURF feature extraction method is proposed. Image feature extraction and image registration are the core of image stitching, which is directly related to stitching quality. In this paper, a comprehensive and in-depth study of feature-based image registration is carried out, and an improved algorithm is proposed. Firstly, the Heisen detection operator in the SURF algorithm is introduced to realize feature detection, and the features are extracted as much as possible. Secondly, the characteristics are described by BRIEF operator in the ORB algorithm to realize the invariance of the rotation change. Then, the European pull distance is used to complete the similarity calculation, and the KNN algorithm is used to realize the feature rough matching. Finally, the distance threshold is used to remove the matching pair with larger distance, and then the RANSAC algorithm is used to complete the purification. Experiments show that the proposed algorithm has good real-time performance, strong robustness and high accuracy.

[1]  Tae Moon Roh,et al.  Fixed Homography-Based Real-Time SW/HW Image Stitching Engine for Motor Vehicles , 2015 .

[2]  Richard L Mort,et al.  Quantitative analysis of patch patterns in mosaic tissues with ClonalTools software , 2009, Journal of anatomy.

[3]  Honghai Liu,et al.  An Interactive Image Segmentation Method in Hand Gesture Recognition , 2017, Sensors.

[4]  Gongfa Li,et al.  Human Lesion Detection Method Based on Image Information and Brain Signal , 2019, IEEE Access.

[5]  Bozenko F. Oreb,et al.  Stitching interferometric measurement data for inspection of large optical components , 2002 .

[6]  Honghai Liu,et al.  Gesture Recognition Based on Kinect and sEMG Signal Fusion , 2018, Mobile Networks and Applications.

[7]  Sean R. Anderson,et al.  PTH-185 Mapping the gastric mucosal surface: image mosaicking for capsule endoscopy , 2015 .

[8]  Somaya Adwan,et al.  A new approach for image stitching technique using Dynamic Time Warping (DTW) algorithm towards scoliosis X-ray diagnosis , 2016 .

[9]  Honghai Liu,et al.  Jointly network: a network based on CNN and RBM for gesture recognition , 2018, Neural Computing and Applications.

[10]  Hyoungkwan Kim,et al.  UAV-based automatic generation of high-resolution panorama at a construction site with a focus on preprocessing for image stitching , 2017 .

[11]  G. Bruce Berriman,et al.  The Application of the Montage Image Mosaic Engine to the Visualization of Astronomical Images , 2017, 1702.02593.

[12]  Hyenkyun Woo,et al.  Block Decomposition Methods for Total Variation by Primal–Dual Stitching , 2016, J. Sci. Comput..

[13]  Nam Ik Cho,et al.  Unified framework for automatic image stitching and rectification , 2015, J. Electronic Imaging.

[14]  Patricia Rodriguez-Tomé,et al.  Classification and characterization of human endogenous retroviruses; mosaic forms are common , 2016, Retrovirology.

[15]  Bradley G. Johnson.  Recommendations for a system to photograph core segments and create stitched images of complete cores , 2015, Journal of Paleolimnology.

[16]  Gordon Petrie,et al.  Using image-based modelling (SfM–MVS) to produce a 1935 ortho-mosaic of the Ethiopian highlands , 2015, Int. J. Digit. Earth.

[17]  Min-Yuan Cheng,et al.  Fuzzy adaptive teaching–learning-based optimization for global numerical optimization , 2016, Neural Computing and Applications.