Machine Learning
Support vector machines: hype or hallelujah?
ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
Digital Image Processing: PIKS Inside
Digital Image Processing: PIKS Inside
Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Computer and Robot Vision
Improved statistics estimation and feature extraction for hyperspectral data classification
Improved statistics estimation and feature extraction for hyperspectral data classification
Multispectral Image Analysis Using the Object-Oriented Paradigm
Multispectral Image Analysis Using the Object-Oriented Paradigm
Fuzzy Regions for Handling Uncertainty in Remote Sensing Image Segmentation
ICCSA '08 Proceeding sof the international conference on Computational Science and Its Applications, Part I
SVM-based segmentation and classification of remotely sensed data
International Journal of Remote Sensing
Hi-index | 0.00 |
The increasing availability of high spatial resolution images provides detailed and up-to-date representations of cities. However, ana-lysis of such digital imagery data using traditional pixel-wise approaches remains a challenge due to the spectral complexity of urban areas. Object-Based Image Analysis (OBIA) is emerging as an alternative method to produce landcover information. Standard OBIA approaches rely on ima-ge segmentation which partitions the image into a set of 'crisp' non-overlapping image-objects. This step regularly requires significant user-interaction to parameterise a functional segmentation model. This paper proposes fuzzy image segmentation which produces fully overlapping image-regions with indeterminate boundaries that serves as alternative framework for the subsequent image classification. The new method uses three stages: (i) fuzzy image segmentation, (ii) feature analysis, and (iii) defuzzification, that were implemented applying Support Vector Machine (SVM) techniques and using open source software. The new method was tested against a benchmark land-cover classification that applied standard crisp image segmentation. Results show that fuzzy image segmentation can produce good thematic accuracy with little user input. It therefore provides a new and automated technique for producing accurate urban land cover data from high spatial resolution imagery.