Editorial: Computer Vision and AI in Real-world Applications: Robustness, Generalization, and Engineering

Alessandro Bruno ^1* Pier Luigi Mazzeo ² Nicola Strisciuglio ³ Barbara Hammer ⁴ Mingliang Gao ⁵

• ¹ Università IULM, Milan, Italy
• ² Institute of Applied Sciences and Intelligent Systems, Department of Physical Sciences and Technologies of Matter, National Research Council (CNR), Pozzuoli, Italy
• ³ University of Twente, Enschede, Netherlands
• ⁴ Bielefeld University, Bielefeld, North Rhine-Westphalia, Germany
• ⁵ Shandong University, Jinan, Shandong Province, China

From a higher standpoint, the contribution lies within the broad AI-driven surveillance topic and enriches it by providing a new technique for more effective monitoring of public spaces. Detection is among the most featured keywords in AI and ML articles due to the excellent inference capabilities proven by several techniques and approaches. The contribution, "OSPS-MicroNet: a distilled knowledge micro-CNN network for detecting rice diseases", stands out as a lighweight deep learning approach to identifying rice plant diseases. OSPS-MicroNet is conceived to find a tradeoff between detection accuracy rates and computational resource constraints. The proposed approach relies on CNNs in a limited-resource setting. A teacher-student learning framework is used to work around the given challenge. The knowledge is transferred from a more sophisticated and bigger-sized 'teacher' model to the lighter-weighted OSPS-MicroNet 'student' model. Data labelling is a well-known challenge in AI and Computer Vision. The article "Automatic labeling of fish species using deep learning across different classification strategies" addresses the labelling of a dataset collecting images from 19 fish species. Pretrained CNNs represent the basis upon which stacking supervised classification layers. In greater detail, Transfer learning specifies pre-trained CNNs on features from the given dataset. Afterward, Support Vector Machines (SVMs) and Linear Discriminant Anaysis (LDA) are used as final classificators. The article "Deep learning-based classification of eye diseases using Convolutional Neural Network for OCT images" lays out a method to detect retinal disease from OCT (Optical Coherence Tomography) images. A preprocessing step based on Gaussian Blur Filtering is carried out before running OCT classification. A Convolutional Neural Network (CNN) runs OCT image classification into four categories: normal retina, Diabetic Macular Edema (DME), Choroidal Neovascular Membranes (CNM), and Agerelated Macular Degeneration (AMD). The article titled "EfficientNet Family U-Net Models for Deep Learning Semantic Segmentation of Kidney Tumors on CT Images" presents a novel biomedical image segmentation method. Kidney cancer segmentation from CT (Computed Tomography) scans is approached combining U-Net and EfficientNet. The latter is opted due to its capabilities in image details extraction. The features detected by EfficientNet are paramount in accurately detecting the region of interest contours. Integrating the two architectures (U-Net and EfficientNet) delivers a more accurate segmentation of the kidney regions and the corresponding suspicious areas. The method is tested over KiTS19, a dataset of CT scans.In summary, the collection of research topics hosts seven contributions presenting methods and techniques in optimisation, image classification, labelling, deep learning, and interdisciplinary applications. Compelling scenarios arise from the latest development oflarge multimodal language models (LMLs), which will probably lead to ripple effects on computer vision and AI applications. That might pave the way for new case studies and techniques to be developed and tested.