Comparison and fusion of co-occurrence, Gabor and MRF texture features for classification of SAR sea-ice imagery
ABSTRACT Image texture interpretation is an important aspect of the computer-assisted discrimination of Synthetic Aperture Radar (SAR) sea-ice imagery. Co-occurrence probabilities are the most common approach used to solve this problem. However, other texture feature extraction methods exist that ha...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Text |
| Language: | English |
| Published: |
2000
|
| Subjects: | |
| Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.3140 http://www.eng.uwaterloo.ca/~dclausi/Papers/comparison of texture methods AO 2001.pdf |
| Summary: | ABSTRACT Image texture interpretation is an important aspect of the computer-assisted discrimination of Synthetic Aperture Radar (SAR) sea-ice imagery. Co-occurrence probabilities are the most common approach used to solve this problem. However, other texture feature extraction methods exist that have not been fully studied for their ability to interpret SAR sea-ice imagery. Gabor filters and Markov random fields (MRF) are two such methods considered here. Classification and significance level testing shows that co-occurrence probabilities classify the data with the highest accuracy, with Gabor filters a close second. MRF results significantly lag Gabor and co-occurrence results. However, the MRF features are uncorrelated with respect to co-occurrence and Gabor features. The fused co-occurrence/MRF feature set achieves higher performance. In addition, it is demonstrated that uniform quantization is a preferred quantization method compared to histogram equalization. RÉSUMÉ [Traduit par la rédaction] L’interprétation de la texture des images est un aspect important de la discrimination assistée par ordinateur des images de la glace de mer produites par le radar à antenne synthétique (RAS). Les probabilités de cooccurrence sont l’approche la plus courante utilisée pour résoudre ce problème. Il existe cependant d’autres méthodes d’extraction des caractéristiques de texture qui n’ont pas encore été complètement explorées du point de vue de leur aptitude à interpréter les images de la glace de mer du RAS. Les filtres de Gabor et les champs aléatoires de Markov (CAM) sont deux de ces méthodes examinées ici. Les tests de |
|---|