• Dr. Rajini S
• Spoorthi S
• Suhas Gowda
• Tejas D
• Vidhisha Gowda

Abstract - Date fruits, being both nutritious and widely sought after in the global market, require consistent quality to meet the expectations of consumers and producers alike. Conventional sorting methods, such as manual inspection, are labor- intensive and susceptible to human errors. In addressing this challenge, deep learning has emerged as a robust technology for automating the sorting process. This research introduces an inventive approach to classifying date fruit varieties using deep learning techniques. The proposed system employs convolutional neural networks (CNN) and image analysis to categorize dates based on quality attributes like size, color, ripeness, and the presence of defects. The training and validation dataset incorporates diverse date images from various sources. The deep learning model's performance was assessed, demonstrating remarkable accuracy and efficiency in the classification task. These findings underscore the potential of deep learning to streamline the date fruit sorting process, leading to reduced labor costs and enhanced quality assurance throughout the date industry.

"Revolutionizing Date Fruit Processing: YOLOv5-Based Sorting Solutions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.i496-i503, June-2024, Available :http://www.jetir.org/papers/JETIR2406852.pdf

"Revolutionizing Date Fruit Processing: YOLOv5-Based Sorting Solutions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. ppi496-i503, June-2024, Available at : http://www.jetir.org/papers/JETIR2406852.pdf