Development of an Intelligent System for Fruit Detection and Cutting Using Computer Vision

In the food industry, process automa-tion is essential for improving efficiency, productivity, and ensuring product qua-lity. Computer vision has emerged as a powerful tool for the automated detec-tion, classification, and manipulation of fruits and other foods (Fan et al., 2024). This technology enables precise and ra-pid identification of characteristics such as type, ripeness, and quality, facilitating processes like classification, packaging, and quality control (Patil et al., 2023).Computer vision utilizes artificial intelligence and machine learning al-gorithms to analyze images and extract relevant information, allowing high-pre-cision classification of fruits based on shape, color, and texture (Del Castillo et al., 2021). Recent studies have highli-ghted the potential of this technology to enhance efficiency and quality in food production, such as defect detection in fruits and vegetables, grain and seed classification, and fish species identifi-cation (Kang & Chen, 2020).The relevance of computer vision and artificial intelligence algorithms for object detection has expanded across various fields, including industrial pro-cesses, quality control, and automation, proving indispensable in Industry 4.0. Applications extend beyond industry to scientific and security sectors, significantly improving processes in various companies (Sucari et al., 2020). Research has demonstrated substantial improvements in process quality through the implementation of computer vision systems. These include systems for recognizing Latin American tropical fruits, using advanced techniques to enhance precision and efficiency in object identification and classification (Fan et al., 2020). The integration of artificial intelligence with computer vision has further advanced industrial quality control, employing deep learning techniques for high-precision fruit detection and classification (Javaid et al., 2022). In smart agriculture, computer vision systems have optimized crop management, resource use, and yields (Sharma et al., 2022). Additionally, autonomous systems for fruit harvesting have shown remarkable advancements (Zhou et al., 2021). Computer vision techniques for inspecting agricultural product quality are replacing manual inspections, reducing errors, and improving economic efficiency (Da Costa et al., 2020). This project aims to identify the technical characteristics of a computer vision system for real-time image acquisition and electronic component evaluation, focusing on five types of fruits: watermelon, apple, pear, orange, and banana. The development will follow the Quality Function Deployment (QFD) methodology to prioritize technical characteristics and include designing printed circuits and arranging elements in the graphical interface (Ruiz García, 2020). Tests will be conducted to validate the system’s accuracy and improve detection algorithms (Amaral et al., 2023). The rest of this article is organized as follows. In Section 2, the Methods a.