No abstract

In the textile and apparel industry, it remains a challenging task to evaluate the fabric smoothness objectively. In existing studies, the objective fabric smoothness assessment is defined as a typical image classification problem. However, the fabric smoothness labels contain sequence information, and the problem shall be defined as an ordinal classification problem. This article presents an effective method including an image preprocessing algorithm, a compact convolutional neural network(CNN) model, and a label smoothing process. Compared with the commonly used CNN frameworks, the proposed compact CNN model is more suitable for this small-sample and low-abstraction problem. The image processing algorithm can improve the model's illumination adaptability, and the label smoothing process can modify the model to satisfy the ordinal classification problems better. In the experiments, the method is tested on a fabric image set including 385 graded fabric specimens. Within a 10-fold cross validation, the proposed method achieves 84.00%, 95.38%, and 100% average accuracies under errors of 0 degree, 0.5 degree, and 1 degree respectively. Implementation discussions on preprocessing and label smoothing verify their effectiveness in improving model performance in assessment accuracies and illumination stability. The proposed method outperforms the state-of-the-art methods for fabric smoothness assessment and a series of widely used deep learning methods. Promisingly, the proposed method can provide novel research ideas for the image-based fabric smoothness assessment.INDEX TERMS Fabric smoothness, textile testing, convolutional neural network, label smoothing.

For the poor adaptability of the two-dimensional image based fabric smoothness assessment methods for multi-color fabrics, three-dimensional imaging technologies were widely concerned in the area. In this paper, we suggest that the multi-color fabric smoothness assessment can be solved by the twodimensional image based methods with the help of the proposed multi-color fabric decoloration method. The decoloration problem was solved by a paired image-to-image translation model built by conditional generative adversarial networks that was widely discussed in recent years. To train such model, we proposed a multi-color and white fabric image pairs generation method with a physically based fabric shading model. The experiment results show good performance of the proposed method on both generated image pairs and real multi-color fabric images. To quantitatively evaluate the performance of the decolored fabric images, a set of metrics was established based on the pixel wise image difference, fabric smoothness classification consistency, and manually fabric smoothness evaluation difference. The quantitative evaluation results demonstrated that the proposed method can achieve reasonable results for the multi-color fabric image decoloration.

Fabric smoothness appearance assessment plays an important role in the textile and apparel industry. To evaluate fabric smoothness objectively, different methods have been proposed based on computer vision technology. To further improve the performance and promote the application of the assessment methods, this paper reports a hybrid computer vision system for objective assessment of fabric smoothness appearance with an ensemble classifier to integrate the advantages of the different image feature sets, which are extracted based on different image processing technologies. The image acquisition environment is established in this system with the selection of illumination parameters—intensity, position angle and altitudinal angle—by a designed strategy. The main steps of the strategy include determination of priority by information gain analysis and parameter selection by classifier performance analysis. The support vector machine classifiers trained by each feature sets are grouped into an ensemble by a self-adapting weighted voting method and the redundant feature sets are eliminated based on the weights of the feature sets. The final result shows evaluation accuracies with 82.86% under 0-degree error, 97.14% under 0.5-degree error and 100% under 1-degree error, which outperforms the other methods in the same environment and verifies the applicability of the proposed system.

No abstract