Can I read Texture Algorithms for Urban Classification on EtoBox?

Texture Algorithms for Urban Classification by Yudho Indardjo is a document available to read on EtoBox.

What is Texture Algorithms for Urban Classification about?

This paper compares the effectiveness of various texture feature extraction algorithms for classifying different types of urban settlements using QuickBird satellite imagery of Soweto, South Africa. It finds that Local Binary Patterns achieved the best classification accuracy at 94%, followed by granulometrics at 85%, for distinguishing formal townships, informal squatter settlements, and other classes. The Local Binary Patterns algorithm captures relevant small-scale edge patterns while granulometrics desc

Author

Yudho Indardjo

Language

EN