A Method for the Evaluation of Image Quality According to the Recognition Effectiveness of Objects in the Optical Remote Sensing Image Using Machine Learning Algorithm

Tao Yuan,Wei Zhou,Xinqi Zheng,Xuan Hu,Wei Wang,Denis G Pelli

doi:10.1371/journal.pone.0086528

Tao Yuan, Wei Zhou + Show 4 more

Open Access

https://doi.org/10.1371/journal.pone.0086528

Copy DOI

Abstract

Objective and effective image quality assessment (IQA) is directly related to the application of optical remote sensing images (ORSI). In this study, a new IQA method of standardizing the target object recognition rate (ORR) is presented to reflect quality. First, several quality degradation treatments with high-resolution ORSIs are implemented to model the ORSIs obtained in different imaging conditions; then, a machine learning algorithm is adopted for recognition experiments on a chosen target object to obtain ORRs; finally, a comparison with commonly used IQA indicators was performed to reveal their applicability and limitations. The results showed that the ORR of the original ORSI was calculated to be up to 81.95%, whereas the ORR ratios of the quality-degraded images to the original images were 65.52%, 64.58%, 71.21%, and 73.11%. The results show that these data can more accurately reflect the advantages and disadvantages of different images in object identification and information extraction when compared with conventional digital image assessment indexes. By recognizing the difference in image quality from the application effect perspective, using a machine learning algorithm to extract regional gray scale features of typical objects in the image for analysis, and quantitatively assessing quality of ORSI according to the difference, this method provides a new approach for objective ORSI assessment.

Highlights

Remote sensing image data, mainly optical remote sensing image (ORSI) data, are a major data source to obtain spatial information
The error statistical method considers a digital image as a collection of isolated image pixels, ignores the statistical correlation among local pixels, and identifies signal errors in the visual perception leading to quality aberration, which do not conform to human visual characteristics
This study proposes to conduct target object recognition on Haar-like features of typical objects by a machine learning algorithm and evaluate image quality by identifying effects

Summary

Introduction

Remote sensing image data, mainly optical remote sensing image (ORSI) data, are a major data source to obtain spatial information. Based on current study results, the quantitative assessment indexes of image quality reflect some aspects of the ORSI quality under certain conditions For these indicators of digital image processing, the calculation results are often significantly different from the practical application effects of object identification and information extraction of remote sensing data, or even completely opposite. With the focus on the practical application of ORSI data, we evaluated the image quality given the ability of optical remote sensing data to recognize target objects, revealed the relationship between the commonly used objective assessment indexes and the practical application effects of RS data, and analyzed the applicability and limitations of these indexes used to represent the image data quality On this basis, we used a machine learning algorithm, selected sample training classifiers, and automatically identified and labeled typical objects in ORSI by programming in the Microsoft Visual C++2008 and OpenCV 2.1 environment. We propose an application-oriented ORSI quality assessment method that provides a new perspective from which to assess ORSI quality

Materials and Methods

Conclusions

Assessment Method of Remote Sensing Image Quality

Findings

Discussion