Anew approach to evaluate the accuracy of image classification result -R'

Precision evaluation is an important step in remote sensing classification. The Kappa is widely used to evaluate the overall accuracy of classification result, but it cannot reflect the classification effect of a certain class. A new precision evaluation index R can apply to evaluate the accuracy of a certain category in classification image. In this paper, we extracted building damage information based on objectoriented method, and discussed the effect and robust of index R and Kappa when different categories of the classification result were involved in precision evaluation. The study shows that the standardized index R can reflect the efficiency of the classification result more stably and it has certain advantages in classification evaluation.

show abstract

“…The index i R of i th class in remote sensing classification (i = 1, 2...K) will be defined as following [4] [5]:…”

Section: Index R For Classification Precision Evaluationmentioning

confidence: 99%

“…Index R can evaluate the efficiency of a certain type of the categories in the classification image. Dou (2004) and Wang (2012) successfully applied the index R to accuracy assessment of remote sensing classification images [4] [5]. Object-oriented method is widely used to the classification of high-resolution remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

Study on the precision evaluation index in building seismic damage information extraction from remote sensing image

Dou

Wang

2014

2014 IEEE Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

show abstract

“…The effectiveness of earthquake prediction can be improved through optimization of the forecast model to maximize R-value . R-value is successfully used in the performance evaluation of earthquake forecast and the forecast method optimization (Ding et Dou and Wang (2004) defined the R-value through the tools of collection and probability, and applied it to the evaluation of remote sensing image classification. Based on the confusion matrix, this paper launches a further probe of the definition of R-value from a new point of view, discusses the characteristics of R-value, and especially, focuses on the application of R-value to the evaluation of the classification efficiency for a certain type of category in classification based on remote sensing image.…”

Section: Introductionmentioning

confidence: 99%

Study on the precision evaluation method for a specific category in the classification of remote sensing image

Wang

Dou

2012

2012 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

The kappa value mainly reflects the overall classification accuracy, but it is hard to evaluate whether a specific classification is optimal or not. In earthquake forecast, an indicator, R-value, is widely used to evaluate the predicting effect of a forecasting method. This paper introduces the Rvalue to evaluate the classifying accuracy of a specific category in image classification. The range and implication of R-value for a specific category are described and compared. As an example, analyses are performed to determine the R-value of classified building damage grade extracted from RS image, compared with building damage grade determined according to ground survey in order to get the best corresponding relationship between them. The results demonstrate that the best corresponding scheme with maximum R-values is consistent with the subjective understanding. It indicates that the R-value method gives richer classification accuracy assessment information than the Kappa method. It is expected to be applied to the evaluation of classifying accuracy of a particular category and the determination of the best scheme in image classification.

show abstract

Anew approach to evaluate the accuracy of image classification result -R'

Cited by 2 publications

References 0 publications

Study on the precision evaluation index in building seismic damage information extraction from remote sensing image

Study on the precision evaluation index in building seismic damage information extraction from remote sensing image

Study on the precision evaluation method for a specific category in the classification of remote sensing image

Contact Info

Product

Resources

About