Fabric defect detection is a necessary and essential step of quality control in the textile manufacturing industry. Traditional fabric inspections are usually performed by manual visual methods, which are low in efficiency and poor in precision for long-term industrial applications. In this paper, we propose an unsupervised learning-based automated approach to detect and localize fabric defects without any manual intervention. This approach is used to reconstruct image patches with a convolutional denoising autoencoder network at multiple Gaussian pyramid levels and to synthesize detection results from the corresponding resolution channels. The reconstruction residual of each image patch is used as the indicator for direct pixel-wise prediction. By segmenting and synthesizing the reconstruction residual map at each resolution level, the final inspection result can be generated. This newly developed method has several prominent advantages for fabric defect detection. First, it can be trained with only a small amount of defect-free samples. This is especially important for situations in which collecting large amounts of defective samples is difficult and impracticable. Second, owing to the multi-modal integration strategy, it is relatively more robust and accurate compared to general inspection methods (the results at each resolution level can be viewed as a modality). Third, according to our results, it can address multiple types of textile fabrics, from simple to more complex. Experimental results demonstrate that the proposed model is robust and yields good overall performance with high precision and acceptable recall rates.

No abstract

We use a green sputtering technique to deposit a Pt/Cu alloy target on liquid polyethylene glycol (PEG) to obtain well-dispersed and stable Pt29Cu71 alloy nanoparticles (NPs). The effects of sputtering current, rotation speed of the stirrer, sputtering time, sputtering period, and temperature of PEG on the particle size are studied systematically. Our key results demonstrate that the aggregation and growth of Pt/Cu alloy NPs occurred at the surface as well as inside the liquid polymer after the particles landed on the liquid surface. According to particle size analysis, a low sputtering current, high rotation speed for the stirrer, short sputtering period, and short sputtering time are found to be favorable for producing small-sized single crystalline alloy NPs. On the other hand, varying the temperature of the liquid PEG does not have any significant impact on the particle size. Thus, our findings shed light on controlling NP growth using the newly developed green sputtering deposition technique.

Metal−organic frameworks (MOFs) for in situ enzyme encapsulation commonly possess weak metal−ligand coordination bonds and rather small pores, which are instable in aqueous solution and present rather high diffusion resistance of reactants. Herein, we prepare a type of hierarchically porous and water-tolerant MOFs through a facile polyphenol treatment method for enzyme encapsulation. In brief, enzymes are first in situ encapsulated in a zeolitic imidazolate framework-8 (ZIF-8) through coprecipitation of enzymes, zinc ions (Zn 2+ ), and 2-imidazole molecules (2-MI). Then, tannic acid (TA, a typical polyphenol) is introduced to functionalize the surface and etch the void of ZIF-8, acquiring the biocatalyst termed as E@ZIF-8@ZnTA. The hierarchically porous structure would accelerate the diffusion process of reactants, whereas the Zn-O bond in a TA-Zn nanocoating would improve the structural stability against water corrosion compared to ZIF-8. Taking glucose oxidase (GOD) as a model enzyme for the catalytic conversion of β-D-glucose, the