Food safety is a pressing concern for human society, as it directly impacts people’s lives, while food freshness serves as one of the most crucial indicators in ensuring food safety. There exist diverse techniques for monitoring food freshness, among which intelligent packaging based on artificial intelligence technology boasts the advantages of low cost, high efficiency, fast speed and wide applicability; however, it is currently underutilized. By analyzing the current research status of intelligent packaging both domestically and internationally, this paper provides a clear classification of intelligent packaging technology. Additionally, it outlines the advantages and disadvantages of using intelligent packaging technology for food freshness detection methods, while summarizing the latest research progress in applying artificial intelligence-based technologies to food freshness detection through intelligent packaging. Finally, the author points out the limitations of the current research, and anticipates future developments in artificial intelligence technology for assisting freshness detection in intelligent packaging. This will provide valuable insights for the future development of intelligent packaging in the field of food freshness detection.

This study reported the production of pH-responsive films based on 8 wt% polyvinyl alcohol solution/0.2 wt% agar solution incorporated with cochineal-loaded starch particles (CSN) (2, 4, 6 and 8 wt% on agar basis) by a casting process. Results revealed that CSN presented obvious color changes over the pH range of 2–12. FTIR, XRD spectra and SEM micrographs presented that the incorporation of CSN formed new hydrogen bonds with a matrix and a tighter network structure. A certain improvement was observed in the color stability, swelling index and functional properties (antimicrobial and antioxidant activities) but water solubility, water vapor permeability and water contact angle of the pH-responsive films were decreased by the addition of CSN. The release of cochineal was a rate-limiting step following the Korsmeyer-Peppas model. The agar/polyvinyl alcohol film containing 6% CSN (PVA/GG-6) exhibited the best sensitivity for ammonia detection and its limit of detection was 35.4 ppm (part per million) for ammonia. The application trials showed that the PVA/GG-6 film presented different color changes for pork freshness. Hence, these pH-responsive films can be used as potential packaging materials for tracking the freshness of protein-rich fresh food in a non-destructive way.

The layout analysis of elements is indispensable in graphic design, as effective layout design not only facilitates the delivery of visual information but also enhances the overall esthetic appeal to the audience. The combination of deep learning and graphic design has gradually turned into a popular research direction in graphic design in recent years. However, in the era of rapid development of artificial intelligence, the analysis of layout still requires manual participation. To address this problem, this paper proposes a method for analyzing the layout of complex layout image elements based on the improved DeepLabv3++ model. The method reduces the number of model parameters and training time by replacing the backbone network. To improve the effect of multi-scale semantic feature extraction, the null rate of ASPP is fine-tuned, and the model is trained by self-constructed movie poster dataset. The experimental results show that the improved DeepLabv3+ model achieves a better segmentation effect on the self-constructed poster dataset, with MIoU reaching 75.60%. Compared with the classical models such as FCN, PSPNet, and DeepLabv3, the improved model in this paper effectively reduces the number of model parameters and training time while also ensuring the accuracy of the model.

Layout analysis of elements is indispensable in graphic design, and layout design can make the audience receive visual information as well as more attractive. The combination of deep learning and graphic design has gradually turned into a popular research direction in graphic design in recent years. However, in the era of rapid development of artificial intelligence, the analysis of layout still requires manual participation. To address this problem, this paper proposes a method for analyzing the layout of complex layout image elements based on the improved deeplabv3+ model. The method reduces the number of model parameters and training time by replacing the backbone network, and in order to improve the effect of multi-scale semantic feature extraction, the null rate of ASPP is fine-tuned, and the model is trained by self-constructed movie poster dataset. The experimental results show that the improved DeepLabv3+ model achieves a better segmentation effect on the self-constructed poster dataset, with MIoU reaching 75.60%. Compared with the classical models such as FCN, PSPNet and DeepLabv3, the improved model in this paper effectively reduces the number of model parameters and training time while also ensuring the accuracy of the model.