• Sharada HP
• Dr. Sandeep Bhat

The assessment of fruit quality in markets is becoming more difficult as mainly due to the demanding physical labor it requires. "This work introduces a low-cost method for assessing fruit quality by combining camera-based image capture with AI-driven classification." The system is designed to operate effectively in real-world environments. Fruit detection is primarily carried out using the "You Only Look Once" (YOLO) V3 algorithm. Designated fruits are continuously tracked based on image characteristics such as size, height, fressness and width, with quality assessment occurring throughout the process. A switching gap mechanism is employed to distinguish between different quality grades of fruit. This is optimized for round fruits, including apples, bananas, cucumbers, oranges, and lemons, and incorporates a newly developed image processing approach. Additionally, a graphical user interface (GUI) is provided to facilitate control, data collection, model evaluation, and system monitoring, thereby enhancing the application's overall efficiency. Tests conducted on a dataset of 6,000 fruit images revealed that the system can reach an accuracy rate of 87%.

autoencoder,gateway control model, convolution layer

"FRUIT QUALITY CLASSIFICATION APPLICATION USING AN ARTIFICIAL INTELLIGENCE ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.925-932, July-2025, Available :http://www.jetir.org/papers/JETIRGX06173.pdf

"FRUIT QUALITY CLASSIFICATION APPLICATION USING AN ARTIFICIAL INTELLIGENCE ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp925-932, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06173.pdf