Identification of Wool and Cashmere Based on Texture Analysis

Yuan, Sen; Lü, Kai; Zhong, Yan

doi:10.4028/www.scientific.net/kem.671.385

Cited by 18 publications

(14 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xing et al used the GMRF method to extract the wool and cashmere fiber texture features and the final identification accuracy was 90.07% [15] Jiao et al used the co-occurrence matrix for the texture analysis of fibers and the final identification accuracy was 91.93% [16]. Yuan et al used the Tamura texture analysis method to describe the fiber surface texture feature and the final identification accuracy was 81.17% [17]. Although some algorithms can achieve high recognition rate compared with the method proposed in this paper, they require a large number of sample data sets.…”

Section: B Comparison With the Existing Methods For Fiber Features Ementioning

confidence: 99%

See 1 more Smart Citation

Identification of Extremely Similar Animal Fibers Based on Matched Filter and HOG-SVM

et al. 2019

View full text Add to dashboard Cite

Identification of extremely similar animal fibers has always been one of the challenging research topics in the textile field. In this paper, an improved image-based recognition method was proposed for the identification of extremely similar animal fibers including cashmere and wool. A total of 100 groups of wool and 100 groups of cashmere fiber images were collected using the self-developed microscope image analysis system. The contrast of original fiber micro images usually was not high enough and some impurities always existed during the slicing process, so the matched filters were first applied for these images to extract the enhanced fiber binary texture, which only needs to set reasonable segment length and the threshold for different fiber images to eliminate impurities and background. Then, the high-dimensional texture features of the original color images, gray images, and the images processed by matched filter were extracted by calculating and analyzing the histogram of oriented gradient (HOG). The 200 sets of original color images, gray images, and processed images were divided into the training set and testing set according to different proportions, and the recognition expert system based on the support vector machine (SVM) could be trained and validated accordingly. The experimental results show that the recognition accuracy of the fiber images processed by matched filter was obviously improved compared with that of the other two data sets, and the recognition rate reaches the highest with 92.5%. It also proves that the proposed algorithm in this paper can classify and identify extremely similar wool and cashmere fibers more quickly and effectively compared with other texture feature extraction and identification algorithms. INDEX TERMS Extremely similar fibers, image identification, matched filter, HOG, SVM.

show abstract

Section: B Comparison With the Existing Methods For Fiber Features Ementioning

confidence: 99%

“…Then these texture features would be used as input parameters of support vector machine to realize the recognition of wool and cashmere [16]. Yuan et al used the improved Tamura texture feature to analysis the final texture images and identify the cashmere and wool fibers by neural network [17].…”

Section: Introductionmentioning

confidence: 99%

Identification of Extremely Similar Animal Fibers Based on Matched Filter and HOG-SVM

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Some techniques, which use the microscopy with human eye, separate these fibres from the samples of their circular scales and others from their chemical and physical characteristics. However, the characteristic features of these samples are still the most useful proof for the capable microscopy to characterize animal fibres such as wool, merino, mohair and cashmere [1–5]. From this perspective, classification of animal fibres is actually a distinctive task of classification and pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

Identification of wool and mohair fibres with texture feature extraction and deep learning

Yildiz

2020

IET Image Processing

View full text Add to dashboard Cite

“…Instead of calculating the measurement parameters of fiber surface geometry, some scholars extract visible features from fiber images to describe the difference in scale patterns between wool and cashmere fibers. Yuan et al 11 employed Tamura texture features to describe fiber images and a back propagation (BP) neural network to classify wool and cashmere fibers. Zhong et al 12 transferred a fiber image into texture blocks, and a projection curve was created based on these texture blocks.…”

Section: Introductionmentioning

confidence: 99%

Identification of wool and cashmere SEM images based on SURF features

Lü

Jun-li

Zhong

et al. 2019

Journal of Engineered Fibers and Fabrics

Self Cite

View full text Add to dashboard Cite

Pattern recognition and feature extraction methods are applied to identify cashmere and wool fibers, which are two kinds of very similar animal fibers. In this article, we proposed a new identification method based on Speed Up Robust Features of fiber images. The images of wool and cashmere fibers are obtained by scanning electron microscopy. Speed Up Robust Features of fiber images are extracted, and each fiber image is regarded as a collection of feature vectors in our logic. The vectors are fed into a support vector machine for supervised learning. The findings from scanning electron microscope images indicate that this method is effective; the recognition rate is higher than 93% for a broad range of blend proportions of the two fibers.

show abstract

Identification of Wool and Cashmere Based on Texture Analysis

Cited by 18 publications

References 2 publications

Identification of Extremely Similar Animal Fibers Based on Matched Filter and HOG-SVM

Identification of Extremely Similar Animal Fibers Based on Matched Filter and HOG-SVM

Identification of wool and mohair fibres with texture feature extraction and deep learning

Identification of wool and cashmere SEM images based on SURF features

Contact Info

Product

Resources

About