A Standardized Probability Comparison Approach for Evaluating and Combining Pixel-based Classification Procedures

In this paper, a standardized probability approach is presented to evaluate the pixel labeling confidence of each pixel and then combine the classification maps generated from different classification procedures for improving classification accuracy. This approach examines the posterior probability of the maximum-likelihood classifier or inverse-distance weight for the minimum-distance classifier for each pixel. It recommends that, for every classification, a standardized probability map should be outputted along with the classified map to show the pixel labeling confidence for all pixels. Tests based on different feature combinations and training strategies from Ikonos data show that the proposed approach was effective in improving the labeling confidence, as well as overall classification accuracy when classified maps from different classification procedures were combined. This standardized probability can be used to provide additional spatial information along with the traditional accuracy assessment.

• Publication year

  2008

• Venue

  Photogrammetric Engineering and Remote Sensing

• Publication date

  2008-05-01

• Fields of study

  Geography, Computer Science, Environmental Science

• Identifiers
  DOI 10.14358/PERS.74.5.601
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Assessing the Accuracy of Remotely Sensed Data: Principles and Practices

  2010cited by this paper
• Using Cluster Analysis to Improve the Selection of Training Statistics in Classifying Remotely Sensed Data

  2008cited by this paper
• The Use of Contextual Information in the Classification of Remotely Sensed Data Contextual methods

  2008cited by this paper
• Knowledge-Based Classification of an Urban Area Using Texture and Context Information in Landsat-TM Imagery

  2007cited by this paper
• Artificial Neural Network Classification Using a Minimal Training Set : Comparison to Conventional Supervised Classification

  2007cited by this paper
• Quantification Error Versus Location Error in Comparison of Categorical Maps

  2006cited by this paper
• Designing fuzzy rule based classifier using self‐organizing feature map for analysis of multispectral satellite images

  2005cited by this paper
• Maximum posterior probability estimators of map accuracy

  2005cited by this paper
• Examining the effect of spatial resolution and texture window size on classification accuracy: an urban environment case

  2004cited by this paper
• Contextual classification of Landsat TM images to forest inventory cover types

  2004cited by this paper
• Strategies for Integrating Information from Multiple Spatial Resolutions into Land-Use/Land-Cover Classification Routines

  2003cited by this paper
• Status of land cover classification accuracy assessment

  2002cited by this paper
• Hard and soft classifications by a neural network with a non-exhaustively defined set of classes

  2002cited by this paper
• THE EFFECT OF TRAINING STRATEGIES ON SUPERVISED CLASSIFICATION AT DIFFERENT SPATIAL RESOLUTIONS

  2002cited by this paper
• From Land Cover to Land Use: A Methodology for Efficient Land Use Mapping over Large Areas

  2001cited by this paper
• From Land Cover to Land Use: A Methodology for Efficient Land Use Mapping over Large Areas

  2001cited by this paper
• The potential of kernel classification techniques for land use mapping in urban areas using 5m-spatial resolution IRS-1C imagery

  2000cited by this paper
• QUANTIFICATION ERROR VERSUS LOCATION ERROR IN COMPARISON OF CATEGORICAL MAPS

  2000cited by this paper
• Combining Multiple Classifiers: An Application Using Spatial and Remotely Sensed Information for Land Cover Type Mapping

  2000cited by this paper
• Incorporating texture into classification of forest species composition from airborne multispectral images

  2000cited by this paper
• Using Correspondence Analysis to Combine Classifiers

  1999cited by this paper
• A Principal Components Approach to Combining Regression Estimates

  1999cited by this paper
• The use of census data in urban image classification

  1998cited by this paper
• A modified contextual classification technique for remote sensing data

  1998cited by this paper
• Assessing the accuracy of remotely sensed data : principles and practices

  1998cited by this paper
• Improving classical contextual classifications

  1998cited by this paper
• A comparison of contextual classification methods using Landsat TM

  1997cited by this paper
• Stacked Regressions

  1996cited by this paper
• A knowledge-based system for the computation of land cover mixing and the classification of multi-spectral satellite imagery

  1996cited by this paper
• INFERRING URBAN LAND USE FROM SATELLITE SENSOR IMAGES USING KERNEL-BASED SPATIAL RECLASSIFICATION

  1996cited by this paper
• Fuzzy classification of spatially degraded Thematic Mapper data for the estimation of sub-pixel components

  1996cited by this paper
• Combining Estimates in Regression and Classification

  1996cited by this paper
• THE INTEGRATION OF GEOGRAPHIC DATA WITH REMOTELY SENSED IMAGERY TO IMPROVE CLASSIFICATION IN AN URBAN AREA

  1995cited by this paper
• Classification of remotely sensed data by an artificial neural network: issues related to training data characteristics

  1995cited by this paper
• An evaluation of fuzzy and texture-based classification approaches for mapping regenerating tropical forest classes from Landsat-TM data

  1995cited by this paper
• Remote sensing and the measurement of geographical entities in a forested environment. 1. The scale and spatial aggregation problem

  1994cited by this paper
• THE HEURISTIC CLASSIFICATION OF FUNCTIONAL LAND USE: A KNOWLEDGE-BASED APPROACH.

  1994cited by this paper
• A Nagao-Matsuyama approach to high-resolution satellite image classification

  1994cited by this paper
• Artificial Neural Networks for Land-Cover Classification and Mapping

  1993cited by this paper
• Urban land use classification and modelling using cover-type frequencies

  1993cited by this paper
• Frequency-based contextual classification and gray-level vector reduction for land-use identification

  1992cited by this paper
• Nested-hierarchical scene models and image segmentation

  1992cited by this paper
• Derivation and applications of probabilistic measures of class membership from the maximum-likelihood classification

  1992cited by this paper
• Post-classification Processing For Thematic Mapping Based On Remotely Sensed Image Data

  1991cited by this paper
• Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

  1990cited by this paper
• The use of structural information for improving land-cover classification accuracies at the rural-urban fringe.

  1990cited by this paper
• A graphical approach for the evaluation of land-cover classification procedures

  1990cited by this paper
• Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery

  1990cited by this paper
• The factor of scale in remote sensing

  1987cited by this paper
• Introductory Digital Image Processing: A Remote Sensing Perspective

  1986influential reference
• Evaluation of several schemes for classification of remotely sensed data

  1980cited by this paper

• A filter-based post-processing technique for improving homogeneity of pixel-wise classification data

  2016cites this paper
• Assessing and Improving Methods for the Effective Use of Landsat Imagery for Classification and Change Detection in Remote Canadian Regions

  2016cites this paper
• Soft urban water cover extraction using mixed training samples and Support Vector Machines

  2015cites this paper
• A comparison of classification algorithms using Landsat-7 and Landsat-8 data for mapping lithology in Canada’s Arctic

  2015cites this paper
• Spectral and Spatial-Based Classification for Broad-Scale Land Cover Mapping Based on Logistic Regression

  2008cites this paper
• Wavelet-Based Classification of Remotely Sensed Images: A Comparative Study of Different Feature Sets in an Urban Environment

  2007cites this paper