Classification of scaled texture patterns with transfer learning. (15th April 2019)

• Record Type: Journal Article
• Authors: Anam, Asaad M.; Rushdi, Muhammad A.
• Is Part Of: Expert systems with applications. Volume 120(2019)
• Page Start: 448
• Page End: 460
• Publication Date: 2019-04-15
• Subjects: Texture classification -- Texture scaling -- Transfer learning -- Partial least-square regression -- Coupled dictionary learning -- Local binary patterns; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.11.033
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We seek to classify texture when few scale variations are available for training. Existing methods use a pure-learning approach with all scales present for training. We use transfer learning to learn the map from atypical to typical texture scales. Classifiers equipped with learned maps may use few scale variations for training. As training scales increase, the gap between transfer and pure learning approaches diminishes. Abstract: Classification of texture patterns with large scale variations poses a great challenge for expert and intelligent systems. A pure learning approach addresses this issue by including texture patterns at all scales in the training dataset. This approach makes the construction of an expert system quite costly and unrealistic given the large variations in real-world texture scales and patterns. We propose a transfer learning approach where the full range of texture scales is available only for a small subset of the texture classes. Such a subset is used to learn the scaling map through partial least-square regression or coupled dictionary learning. Experimental results on classifiers equipped with the learned maps show promising reduction in training data scale variability with improved classification accuracy compared to the data-intensive pure learning approach. The proposed approach can be followed to build image-based expert systems of reasonable accuracy and limited data requirements.