Objective Evaluation of Fabric Wrinkles Based on 2-D Gabor Transform
- PDF / 1,729,029 Bytes
- 9 Pages / 609 x 794 pts Page_size
- 23 Downloads / 195 Views
ISSN 1229-9197 (print version) ISSN 1875-0052 (electronic version)
Objective Evaluation of Fabric Wrinkles Based on 2-D Gabor Transform Kangjun Shi†, Jingan Wang†, Lei Wang, Ruru Pan, and Weidong Gao* Key Laboratory of Eco-textiles, Ministry of Education, Jiangnan University, Wuxi, Jiangsu 214122, China (Received July 4, 2019; Revised October 2, 2019; Accepted December 19, 2019) Abstract: In order to establish an objective, stable and efficient wrinkle evaluation system for fabric wrinkle evaluation, a method based on 2-D Gabor transform was proposed. Among this system, the directions of Gabor filter were determined according to the range of amplitude response. Then a set of Gabor filters were obtained by selecting and optimizing the central frequency, the half peak bandwidth and the shape factor of the Gaussian surface. After Gabor transform by such filter bank, the amplitudes of different response spectrums were extracted, constructing a multi-dimensional feature vector. Finally, the feature vectors of the fabric image samples, whose wrinkle degrees were evaluated manually in advance, were extracted and used to train a support vector machine (SVM), which achieved 81.82 % evaluation accuracy on the 345 samples. The trained SVM was applied to evaluate the wrinkle degree of the fabric samples acquired in different illumination directions, and verified the stability of the proposed method to illumination environment. Compared with the existing method, the proposed method has higher classification accuracy. The comparison results indicate the Gabor amplitude feature proposed by this research has a high correlation with the fabric wrinkle grades. Keywords: Gabor transform, Amplitude total, Support vector machine, Wrinkle evaluation, Fabric
and subjective evaluation by establishing non-linear regression model [3]. Na and Pourdeyhimi used CCD camera to acquire 2-D images of AATCC replicas, and proposed indicators including gray level and surface statistics, co-occurrence analysis and power spectral density to measure fabric wrinkles [4]. Mori and Komiyama extracted entropy, contrast, correlation, angular second moment and fractal dimension as the feature vector based on the Gray level co-occurrence matrix (GLCM) of the gray images to train the neural network as final classification model [5]. Based on the frequency domain analysis, Choi et al. transformed images from spatial domain to frequency domain by 2-D Fourier transform, and calculated the spectrum amplitudes of part frequency to characterize the change of wrinkles [1]. Since objective evaluation of fabric wrinkles uses 2-D images based on gray values and position information, the evaluation results is easily affected by the illumination environment and surface color of fabrics. Consequently, researchers apply 3D depth maps to objectively evaluate the fabric wrinkles. Kang et al. had done a lot of works in this field. They used laser scanning and stereo vision technology to acquire 3-D depth maps of AATCC replicas, and calculated fractal dimension based on depth
Data Loading...
