A new method using the convolutional neural network with compressive sensing for fabric defect classification based on small sample sizes
Autor: | Yongsheng Ding, Bing Wei, Kuangrong Hao, Xue-song Tang |
---|---|
Rok vydání: | 2018 |
Předmět: |
010302 applied physics
Polymers and Plastics Computer science business.industry Pattern recognition Small sample 02 engineering and technology 021001 nanoscience & nanotechnology 01 natural sciences Convolutional neural network Texture (geology) Compressed sensing 0103 physical sciences Chemical Engineering (miscellaneous) Artificial intelligence 0210 nano-technology business |
Zdroj: | Textile Research Journal. 89:3539-3555 |
ISSN: | 1746-7748 0040-5175 |
Popis: | The convolutional neural network (CNN) has recently achieved great breakthroughs in many computer vision tasks. However, its application in fabric texture defects classification has not been thoroughly researched. To this end, this paper carries out a research on its application based on the CNN model. Meanwhile, since the CNN cannot achieve good classification accuracy in small sample sizes, a new method combining compressive sensing and the convolutional neural network (CS-CNN) is proposed. Specifically, this paper uses the compressive sampling theorem to compress and augment the data in small sample sizes; then the CNN can be employed to classify the data features directly from compressive sampling; finally, we use the test data to verify the classification performance of the method. The explanatory experimental results demonstrate that, in comparison with the state-of-the-art methods for running time, our CS-CNN approach can effectively improve the classification accuracy in fabric defect samples, even with a small number of defect samples. |
Databáze: | OpenAIRE |
Externí odkaz: |