A multi-scale supervised orientational invariant neural architecture for natural texture classification

作者：Diaz Pernas F J; Anton Rodriguez M^*; Perozo Rondon F J; Gonzalez Ortega D

来源：Neurocomputing, 2011, 74(18): 3729-3740.

DOI：10.1016/j.neucom.2011.06.028

• Texture classification
• Supervised neural network
• Multi-scale processing
• Orientational invariance
• Gabor filtering
• Brodatz database
• Fuzzy ART

A multi-scale supervised neural architecture, called Multi-Scale SOON, is proposed for natural texture classification. This architecture recognizes the input textured image through a hierarchical categorization structure in multiple scales. This process consists of three sequential phases: a multi-scale feature extraction, a scale prototype pattern generation, and a multi-scale prototype fusion pattern classification. First phase extracts scale textural features using the Gabor filtering. Then, a hierarchical categorization shapes the classification. First categorization level generates the scale prototypes and an upper level categorizes the prototypes fusion. Three increasing complexity tests over the well-known Brodatz database are performed in order to quantify the Multi-Scale SOON behavior. The comparison to other standout methods proves Multi-Scale SOON behavior to be satisfactory. The tests, including the entire texture album, show the stability and robustness of the Multi-Scale SOON response.

• 出版日期2011-11