Computer vision systems are often used in industrial quality control to offer fast, objective, non-destructive, and contactless evaluation of fruit. The senescence of fresh-cut apples is strongly related to the browning of the pulp rather than to the properties of the peel. This work addresses the identification and selection of pulp inside images of fresh-cut apples, both packaged and unpackaged; this is a critical step towards a computer vision system that is able to evaluate their quality and internal properties. A DeepLabV3+-based convolutional neural network model (CNN) has been developed for this semantic segmentation task. It has proved to be robust with respect to the similarity of colours between the peel and pulp. Its ability to separate the pulp from the peel and background has been verified on four varieties of apples: Granny Smith (greenish peel), Golden (yellowish peel), Fuji, and Pink Lady (reddish peel). The semantic segmentation achieved an accuracy greater than 99% on all these varieties. The developed approach was able to isolate regions significantly affected by the browning process on both packaged and unpackaged pieces: on these areas, the colour analysis will be studied to evaluate internal quality and senescence of packaged and unpackaged products.

The safety of railway infrastructure needs utmost attention as even minor faults can lead to catastrophic consequences. With recent advancements in deep learning and computer vision, the railway sector has seen significant innovations aimed at enhancing safety through more efficient anomaly detection and infrastructure inspection. This review systematically explores these advancements by analysing research articles published in Q1 journals between 2022 and 2024. Utilising the PRISMA protocol, the review categorises selected articles based on three major factors: 1) the application areas with the inspection and anomaly detection within railway infrastructure, 2) the sensing equipment utilised for data acquisition, and 3) the algorithms deployed to process the collected data. The review reveals a growing reliance on deep learning techniques, adopting convolutional neural networks to process complex and heterogeneous datasets. It highlights the widespread use of 1D and 2D sensors for data collection, with almost balanced usage of sequential data and independent and identically distributed data in safety-related applications. Still, significant challenges are posed by the requirements in terms of compliance for safety standards and explainability, along with the integration of several vertical systems into a coherent, holistic approach to railway safety. Therefore, the outcome of this review provides valuable insights into current trends in the railway sector and offers a comprehensive understanding of promising methodologies and technologies, along with their current limitations, that are essential for researchers, policymakers, and industry stakeholders aiming to enhance the safety and reliability of railway infrastructure.