Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments.

Lancaster Environment Centre

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments. / Koukoulas, S.; Blackburn, George Alan.
In: Photogrammetric Engineering and Remote Sensing, Vol. 67, No. 4, 04.2001, p. 499-510.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Bibtex

@article{34b0980a1a604979a39e1fffb7910cdd,

title = "Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments.",

abstract = "A range of accuracy indices for determining the optimal outputs from the classification of multispectral remotely sensed data is evaluated. Airborne Thematic Mapper imagery of semi-natural woodland was used in conjunction with an in situ data set. Indices of classification accuracy were unable to distinguish substantial differences in classified images because they are based only on errors of omission, accounting for only a proportion of the errors in classification. The Classification Success Index (CSI) is introduced here to estimate the overall effectiveness of classification, considering all output classes and using both errors of omission and commission from the error matrix. The Individual Classification Success Index (ICSI) is introduced which accounts for the classification success of a specific class. Finally, the Group Classification Success Index (GCSI) measures classification success for the most important classes in the area of interest. These new indices were found to offer considerable improvement over existing approaches.",

author = "S. Koukoulas and Blackburn, {George Alan}",

year = "2001",

month = apr,

language = "English",

volume = "67",

pages = "499--510",

journal = "Photogrammetric Engineering and Remote Sensing",

issn = "0099-1112",

publisher = "American Society for Photogrammetry and Remote Sensing",

number = "4",

}

RIS

TY - JOUR

T1 - Introducing New Indices for Accuracy Evaluation of Classified Images Representing Semi-Natural Woodland Environments.

AU - Koukoulas, S.

AU - Blackburn, George Alan

PY - 2001/4

Y1 - 2001/4

N2 - A range of accuracy indices for determining the optimal outputs from the classification of multispectral remotely sensed data is evaluated. Airborne Thematic Mapper imagery of semi-natural woodland was used in conjunction with an in situ data set. Indices of classification accuracy were unable to distinguish substantial differences in classified images because they are based only on errors of omission, accounting for only a proportion of the errors in classification. The Classification Success Index (CSI) is introduced here to estimate the overall effectiveness of classification, considering all output classes and using both errors of omission and commission from the error matrix. The Individual Classification Success Index (ICSI) is introduced which accounts for the classification success of a specific class. Finally, the Group Classification Success Index (GCSI) measures classification success for the most important classes in the area of interest. These new indices were found to offer considerable improvement over existing approaches.

AB - A range of accuracy indices for determining the optimal outputs from the classification of multispectral remotely sensed data is evaluated. Airborne Thematic Mapper imagery of semi-natural woodland was used in conjunction with an in situ data set. Indices of classification accuracy were unable to distinguish substantial differences in classified images because they are based only on errors of omission, accounting for only a proportion of the errors in classification. The Classification Success Index (CSI) is introduced here to estimate the overall effectiveness of classification, considering all output classes and using both errors of omission and commission from the error matrix. The Individual Classification Success Index (ICSI) is introduced which accounts for the classification success of a specific class. Finally, the Group Classification Success Index (GCSI) measures classification success for the most important classes in the area of interest. These new indices were found to offer considerable improvement over existing approaches.

M3 - Journal article

VL - 67

SP - 499

EP - 510

JO - Photogrammetric Engineering and Remote Sensing

JF - Photogrammetric Engineering and Remote Sensing

SN - 0099-1112

IS - 4

ER -

Research