Jiafeng Xu

With the increase in cross-border mobility, passports, as critical identity documents, require robust anti-counterfeiting security. While existing deep learning-based automatic detection methods achieve high accuracy, they lack interpretability. This paper introduces the Concept Bottleneck Model (CBM) to construct a transparent passport printing method detection framework. By defining interpretable intermediate concepts and integrating linear reasoning, the model significantly enhances reliability and debugging efficiency. The article systematically analyzes the advantages, challenges, and future directions of this approach.

Passport background texture classification has always been an important task in border checks. Current manual methods struggle to achieve satisfactory results in terms of consistency and stability for weakly textured background images. For this reason, this study designs and develops a CNN and Transformer complementary network (PBNet) for passport background texture image classification. We first design two encoders by Transformer and CNN to produce complementary features in the Transformer and CNN domains, respectively. Then, we cross-wisely concatenate these complementary features to propose a feature enhancement module (FEM) for effectively blending them. In addition, we introduce focal loss to relieve the overfitting problem caused by data imbalance. Experimental results show that our PBNet significantly surpasses the state-of-the-art image segmentation models based on CNNs, Transformers, and even Transformer and CNN combined models designed for passport background texture image classification.

Genome editing tools based on SpCas9 and FnCpf1 have facilitated strain improvements for natural product production and novel drug discovery in Streptomyces. However, due to high toxicity, their editing requires high DNA transformation efficiency, which is unavailable in most streptomycetes. The transformation efficiency of an all-in-one editing tool based on miniature Cas nuclease AsCas12f1 was significantly higher than those of SpCas9 and FnCpf1 in tested streptomycetes, which is due to its small size and weak DNA cleavage activity. Using this tool, in Streptomyces coelicolor, we achieved 100% efficiency for single gene or gene cluster deletion and 46.7 and 40% efficiency for simultaneous deletion of two genes and two gene clusters, respectively. AsCas12f1 was successfully extended to Streptomyces hygroscopicus SIPI-054 for efficient genome editing, in which SpCas9/FnCpf1 does not work well. Collectively, this work offers a low-toxicity, high-efficiency genome editing tool for streptomycetes, particularly those with low DNA transformation efficiency.