Identification of Animal Fibers with Wavelet Texture Analysis

1. Identification of Animal Fibers with Wavelet Texture Analysis Dr Junmin Zhang Dr Stuart Palmer Professor Xungai Wang Centre for Material and Fibre Innovation Deakin University Australia

2. Introduction - Cashmere Source: http://en.wikipedia.org/wiki/ File:Old_O102_cropped_small.jpg As cashmere processing capacity outstrips available supplies of cashmere, some processors use superfine merino wool to blend with cashmere Cashmere wool blends provide the high quality worsted suiting fabric and produces a lower cost product while exploiting the positive market perceptions associated with the luxury cashmere content

3. Introduction - blends Source: http://commons.wikimedia.org/wiki/ File:Australian_Cashmere_Goats.jpg Current standard test methods for analysing blends of specialty fibres with sheep’s wool are based on scanning electron microscopy The current operator-based methods are tedious and subjective It is desirable to develop an objective, automatic method to identify and subsequently classify animal fibres

4. Introduction – fibre classification

5. Introduction – fibre classification

6. Sample image preparation Cashmere Merino wool

7. Sample image preparation Cashmere Merino wool

8. The 2D dual-tree complex wavelet transform

9. Fibre surface feature extraction Detail images represent the content of successive frequency bands The final approximation image contains the low frequency variations in background illumination

10. In this work, the analysis object is the fibre surface, and the texture feature is defined as: Where M×N is the size of the fibre surface image, and are the pixel grey-scale values of fibre surface image in scale s and direction k. Fibre surface feature extraction

11. Fibre surface feature extraction From the Cashmere Fiber Distinction Atlas, 13 cashmere fibre images and 15 merino fibre images were prepared From each of the 28 fibre images a texture feature vector consisting of 24 (6 orientations x 4 scales) energy features was developed Principal component analysis was used to reduce the dimension of the texture feature vector

12. Principal components analysis

13. Discriminant analysis

14. Allied work – automatic pilling classification

15. Future work non-linear neural network classification; testing of the performance of the wavelet texture analysis method of fibre identification on a larger set of real cashmere and other fibre samples; and the application of the wavelet texture analysis method to the of task analysing/assaying blends of specialty fibres

16. Thank you for your time