A Seamless Image-Stitching Method Based on Human Visual Discrimination and Attention

Stitching gaps and misalignments in mosaic images can severely degrade the human visual perception of mosaic effects. Image stitching plays a key role in eliminating these unpleasant defects. In this paper, an image-stitching method for mosaic images with invisible seams is proposed, according to the research on the human visual system (HVS). By quantifying the human visual attention of images and visual discrimination about luminance difference and fine dislocations, each pixel in the stitching region is given a priority value for tracing a stitching line. Coupled with the processing of an optimal stitching line locating method and the multi-band blending algorithm, the pixels of discontinuous items in mosaic images decrease significantly and the stitching line is almost invisible. This study provides a new insight into the image-stitching field, and the experiments show that the results of the proposed method are more consistent with the human visual system in creating high-quality image mosaics.

[1]  Miaomiao Yu,et al.  Full-Reference Image Quality Assessment by Combining Features in Spatial and Frequency Domains , 2019, IEEE Transactions on Broadcasting.

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[4]  S. Goodhew,et al.  Understanding recovery from object substitution masking , 2012, Cognition.

[5]  Martin Kerschner,et al.  Seamline detection in colour orthoimage mosaicking by use of twin snakes , 2001 .

[6]  Stanislas Dehaene,et al.  The neural basis of the Weber–Fechner law: a logarithmic mental number line , 2003, Trends in Cognitive Sciences.

[7]  David L. Milgram,et al.  Computer Methods for Creating Photomosaics , 1975, IEEE Transactions on Computers.

[8]  Haluk Ogmen,et al.  A statistical perspective to visual masking , 2015, Vision Research.

[9]  Chun-Shin Lin,et al.  Seam-line determination for image mosaicking: A technique minimizing the maximum local mismatch and the global cost , 2010 .

[10]  Li Li,et al.  Optimal Seamline Detection for Orthoimage Mosaicking by Combining Deep Convolutional Neural Network and Graph Cuts , 2017, Remote. Sens..

[11]  Li Li,et al.  Optimal seamline detection for multiple image mosaicking via graph cuts , 2016 .

[12]  Kenichi Kanatani,et al.  Image mosaicing by stratified matching , 2004, Image Vis. Comput..

[13]  Francisco J. Serón,et al.  Implementation of a method of curved ray tracing for inhomogeneous atmospheres , 2005, Comput. Graph..

[14]  Zaifeng Shi,et al.  Seam-based variable-step Bresenham blending method for real-time video mosaicking , 2016, J. Electronic Imaging.

[15]  Jinwhan Kim,et al.  Efficient image mosaicing for multi-robot visual underwater mapping , 2014, Pattern Recognit. Lett..

[16]  Le Yu,et al.  Towards the automatic selection of optimal seam line locations when merging optical remote-sensing images , 2012 .

[17]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[18]  Ming Li,et al.  Improved Seam-Line Searching Algorithm for UAV Image Mosaic with Optical Flow , 2018, Sensors.

[19]  Zaifeng Shi,et al.  A perceptual image quality index based on global and double-random window similarity , 2017, Digit. Signal Process..

[20]  Vivek K. Goyal,et al.  A framework for Bayesian optimality of psychophysical laws , 2012, Journal of Mathematical Psychology.

[21]  Guojun Lu,et al.  An Improved Curvature Scale-Space Corner Detector and a Robust Corner Matching Approach for Transformed Image Identification , 2008, IEEE Transactions on Image Processing.

[22]  Jinghong Liu,et al.  Automatic orthorectification and mosaicking of oblique images from a zoom lens aerial camera , 2015 .

[23]  Tao Luo,et al.  Robust and Efficient Corner Detector Using Non-Corners Exclusion , 2020, Applied Sciences.

[24]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[25]  Xin Yang,et al.  Image quality assessment using contourlet transform , 2009 .

[26]  Hongyu Li,et al.  VSI: A Visual Saliency-Induced Index for Perceptual Image Quality Assessment , 2014, IEEE Transactions on Image Processing.

[27]  Nan Li,et al.  Perception-based seam cutting for image stitching , 2018, Signal, Image and Video Processing.

[28]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[29]  Penglang Shui,et al.  Contour-based corner detection via angle difference of principal directions of anisotropic Gaussian directional derivatives , 2015, Pattern Recognit..

[30]  Xudong Jiang,et al.  Contrast Invariant Interest Point Detection by Zero-Norm LoG Filter , 2016, IEEE Transactions on Image Processing.

[31]  Harpreet S. Sawhney,et al.  True Multi-Image Alignment and Its Application to Mosaicing and Lens Distortion Correction , 1999, IEEE Trans. Pattern Anal. Mach. Intell..