Deep-learning models have achieved state-of-the-art performances in a wide range of defect detection tasks. However, an inescapable criticism of one-stage fully supervised models is the lack of interpretability, which not only reduces the reliability of fabric defect detection systems but also limits the scope of their applications in production environments. To tackle the data imbalance and low interpretability of defect samples, we proposed a spatial cloze strategy for fabric defect detection, which reconstructs a local normal image and then feeds it into the detection model with the original image simultaneously. Specifically, we formulate the defect detection task as a novel image completion problem. Firstly, an end-to-end deep neural network is trained to finely restore the defect image by completing each image slice removed in sequence. Next, the progressive attention mechanism fuses the repaired normal image with the raw image, replacing the input layer of the cascade region-based convolutional neural network. Eventually, accurate instance-level defect segmentation can be obtained by comparing the repaired defect-free and the raw images. On the Tianchi dataset, the proposed method displays superior accuracy in 92% of defect classes, with a breakthrough in various categories that have hardly ever been detected. Extensive experiments on various complex fabric defect samples demonstrate that our strategy outperforms existing advanced methods.

Wine has an indispensable position in the ancient national food culture. Among them, wine vessels, as material carriers, are the core of ancient national wine culture, reflecting social functions, plastic arts, craft production, customs, habits, etc., and therefore are also the concrete expression of spiritual and institutional culture. Ancient ethnic traditional drinking vessels are not only a comprehensive manifestation of the precious material cultural heritage but also of the ancient spiritual culture of the nation. Through the study of the representational design and cultural characteristics of ancient ethnic traditional drinking vessels and the aesthetic tendencies they reflect, we can see the unique philosophy of life and the spiritual reverence of ancient peoples. Although these traditional ancient ethnic drinking vessels are now gradually marginalized and some have completely withdrawn from the historical stage, their spiritual and cultural value has increased rather than decreased. This paper explores the representational design and cultural characteristics of ancient traditional drinking vessels and the aesthetic tendencies they reflect and analyzes the correlation between them using ML methods and semiotic theory, to get a glimpse of the unique talent and wisdom of the ancients in aesthetic creation and gain new design inspiration from them.

No abstract

The indiscriminate discharge of industrial and domestic wastewater leads to the pollution of production, living, and landscape waters with heavy metals, including Pb2+. To protect people working in environments with risk of water pollution by Pb2+, the Pb2+ chemosensor based on fluorescent carbon dots (CDs) was designed in this study. Based on quenching of the fluorescence of CDs via electron or energy transfer between Pb2+ and CDs, the sensor induces a significant “dark blue to light blue” fluorescence burst color change under the naked eye. Results suggest that the fluorescence intensity of CDs positively correlated with the concentrations of Pb2+ (R2 = 0.823–0.986), which is conducive to the detection of Pb2+-containing wastewater by CDs. On this basis, we integrated CD fluorescent sensors into wearable gloves via a mediated coating method. With no additional burden (off-site, long lead times, high cost, etc.), the designed wearable gloves enable front loading of the detection window for Pb2+-contaminated water to protect the wearer from poisoning. Eight watershed environmental occupants reported a 57.42% reduction in occupational anxiety after using our safety gloves. We believe that the proposed flexible and stable wearable sensing system will not only have great potential applications in Pb2+ field detection but also stimulate the development of other environmental pollution sensing devices.