Education, Science, Technology, Innovation and Life
Open Access
Sign In

Objective Quality Evaluation of Stitched Images Based on Information Entropy

Download as PDF

DOI: 10.23977/jipta.2022.050106 | Downloads: 11 | Views: 723

Author(s)

Changchun Li 1

Affiliation(s)

1 Institute of Computer Application Technology, Changchun College of Electronic Technology, Changchun, Jilin, 130000, China

Corresponding Author

Changchun Li

ABSTRACT

In the process of image stitching, the image quality will decrease. In order to quantitatively analyze the stitching quality of stitched images, an objective quality evaluation algorithm based on information entropy is designed. Based on the structural similarity parameter analysis, this algorithm completes the parameter adjustment by comparing and analyzing the structural similarity between images. The experiment analyzes the image information entropy under different dislocation conditions. The results show that the algorithm can effectively suppress the information entropy after image stitching. In the objective evaluation, the gray mean and standard deviation are better than the traditional stitching algorithm, which verifies the superiority of the algorithm. 

KEYWORDS

Information entropy, Stitched images, Objective evaluation, Positional deviation, SSPA

CITE THIS PAPER

Changchun Li, Objective Quality Evaluation of Stitched Images Based on Information Entropy. Journal of Image Processing Theory and Applications (2022) Vol. 5: 35-40. DOI: http://dx.doi.org/10.23977/jipta.2022.050106.

REFERENCES

[1] Parihar A., Verma O P., Contrast Enhancement Using Entropy - based Dynamic Sub-histogram Equalization. Iet Image Processing, 2016, 10 (11): 799-802.
[2] Wharton E., Panetta K., Againan S., Human Vision System Based Multi-Histogram Equalization for Non-Uniform Illumination And Shadow Correctin, IEEE International Conference on Acoustic, Speech and Signal Processing, IEEE, 2015: 729-731.
[3] Chari S K., Gupta A., Gupta P., et al. Threshold Selection in Image Segmentation Using Parametric Entropy Measures, IEEE Fourth International Conference on Image Information Processing, 2017, 16 (3): 273-277.
[4] Ioffe S., Szegedy C., Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Computer Science, 2015, 1 (3): 448- 456.
[5] Krizhevsky A., Sutskever I., Hinton G E., Image. Net classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems, Curran Associates Inc., 2012, 2 (4): 1097-1105.
[6] Qureshi H S., et al. Quantitative quality assessment of stitched panoramic images. let Image Processing, 2012, 6 (9): 1348-1358.
[7] Alexander N., Gorban, et al. Uniqueness of thermodynamic projector and kinetic basis of molecular individualism. Physica A Statistical Mechanics & Its Applications, 2004.
[8] Sun L., Wang L., Qian Y., et al. Feature selection using Lebesgue and entropy measures for incomplete neighborhood decision systems. Knowledge-Based Systems, 2019, 186: 104942.
[9] Yan L., Peng J., Gao D., et al. A hybrid method with cascaded structure for early-stage remaining useful life prediction of lithium-ion battery. Energy, 2022, 12 (3): 243-246.
[10] Kinney P L., Roman H A., Walker K D., et al. On the use of expert judgment to characterize uncertainties in the health benefits of regulatory controls of particulate matter. Environmental Science & Policy, 2010, 13 (5): 434-443.
[11] Teslyk M V., Teslyk O M., Zadorozhna L V., et al. Unruh effect and information entropy approach. 2021, 5 (2): 157-170.

Downloads: 1137
Visits: 98997

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.