Optimal region growing segmentation and its effect on classification accuracy

Image segmentation is a preliminary and critical step in object-based image classification. Its proper evaluation ensures that the best segmentation is used in image classification. In this article, image segmentations with nine different parameter settings were carried out with a multi-spectral Landsat imagery and the segmentation results were evaluated with an objective function that aims at maximizing homogeneity within segments and separability between neighbouring segments. The segmented images were classified into eight land-cover classes and the classifications were evaluated with independent ground data comprising 600 randomly distributed points. The accuracy assessment results presented similar distribution as that of the objective function values, that is segmentations with the highest objective function values also resulted in the highest classification accuracies. This result shows that image segmentation has a direct effect on the classification accuracy; the objective function not only worked on a single band image as proved by (Espindola, G.M., Camara, G., Reis, I.A., Bins, L.S. and Monteiro, A.M., 2006, Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation. International Journal of Remote Sensing, 27, pp. 3035–3040.) but also on multi-spectral imagery as tested in this, and is indeed an effective way to determine the optimal segmentation parameters. McNemar's test (z 2  =  10.27) shows that with the optimal segmentation, object-based classification achieved accuracy significantly higher than that of the pixel-based classification, with 99% significance level.

[1]  Hugo Carrão,et al.  Contribution of multispectral and multitemporal information from MODIS images to land cover classification , 2008 .

[2]  Mark Berman,et al.  Segmenting multispectral Landsat TM images into field units , 2002, IEEE Trans. Geosci. Remote. Sens..

[3]  Kannan,et al.  ON IMAGE SEGMENTATION TECHNIQUES , 2022 .

[4]  Limin Yang,et al.  Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data , 2000 .

[5]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Guaraci J. Erthal,et al.  Satellite Imagery Segmentation: a region growing approach , 1996 .

[7]  Xie Yuan-dan,et al.  Survey on Image Segmentation , 2002 .

[8]  Robert A. Schowengerdt,et al.  Remote sensing, models, and methods for image processing , 1997 .

[9]  M. Wulder,et al.  Contextual classification of Landsat TM images to forest inventory cover types , 2004 .

[10]  Thomas Blaschke,et al.  OBIA Tutorial - Introduction to Object-based Image Analysis , 2006 .

[11]  Gilberto Câmara,et al.  Spring: integrating remote sensing and gis by object-oriented data modelling , 1996, Comput. Graph..

[12]  Robert A. Schowengerdt.  CHAPTER 9 – Thematic Classification , 2007 .

[13]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[14]  J. Dymond.  How accurately do image classifiers estimate area , 1992 .

[15]  Geoff Smith,et al.  An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities , 2003 .

[16]  Marvin E. Bauer,et al.  Integrating Contextual Information with per-Pixel Classification for Improved Land Cover Classification , 2000 .

[17]  P. Soille,et al.  Information extraction from very high resolution satellite imagery over Lukole refugee camp, Tanzania , 2003 .

[18]  D. Flanders,et al.  Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction , 2003 .

[19]  Pietro Alessandro Brivio,et al.  Pareto boundary: a useful tool in the accuracy assessment of low spatial resolution thematic products , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[20]  Tin Kam Ho,et al.  Complexity Measures of Supervised Classification Problems , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Antônio Miguel Vieira Monteiro,et al.  Parameter selection for region‐growing image segmentation algorithms using spatial autocorrelation , 2006 .

[22]  H. Egawa,et al.  Region Extraction in SPOT Data , 1988 .

[23]  D. Sloane,et al.  An Introduction to Categorical Data Analysis , 1996 .

[24]  David L. Verbyla,et al.  Optimistic bias in classification accuracy assessment , 1996 .

[25]  Ioannis Z. Gitas,et al.  Object-based image classification for burned area mapping of Creus Cape, Spain, using NOAA-AVHRR imagery , 2004 .

[26]  Giles M. Foody,et al.  Training set size requirements for the classification of a specific class , 2006 .

[27]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[28]  A. Agresti.  An introduction to categorical data analysis , 1997 .

[29]  John R. Jensen,et al.  Introductory Digital Image Processing: A Remote Sensing Perspective , 1986 .

[30]  J Richards,et al.  Computer processing of remotely-sensed images: An introduction , 1990 .

[31]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[32]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[33]  U. Benz,et al.  Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information , 2004 .

[34]  M. Neubert,et al.  A COMPARISON OF SEGMENTATION PROGRAMS FOR HIGH RESOLUTION REMOTE SENSING DATA , 2004 .

[35]  Sucharita Gopal,et al.  Fuzzy set theory and thematic maps: accuracy assessment and area estimation , 2000, Int. J. Geogr. Inf. Sci..