About this document
Scale and Texture in Image Classification by Nirmal is a document available to read on EtoBox.
This thesis investigates the impact of scale and texture on digital image classification, emphasizing the hierarchical nature of spatial information and the effects of class edges on classification accuracy. It demonstrates that while texture can enhance class separability, the window sizes required for stable texture measures often lead to significant edge effects that complicate classification results. The study combines theoretical frameworks with empirical data to explore optimal window sizes for effect
- Author
- Nirmal
- Language
- EN