• Dr. K.K.Tripathi
• Santosh Vitthal Bhosale
• Pritam Ramdas Dhumal
• Pradip Devidas Kayande

This project introduces an Android-based mobile application aimed at fulfilling the crucial need for precise mango variety identification. Understanding the significance of mango varieties in both agriculture and consumer preferences, the app employs Deep learning algorithms such as Convolutional Neural Networks (CNN) to revolutionize the accuracy and efficiency of this process. Traditional methods, primarily reliant on manual assessments and basic image recognition, suffer from limitations such as time consumption and reduced accuracy. This project overcomes these challenges by harnessing CNN technology, facilitating automated and accurate mango variety identification. The CNN model, trained on an extensive dataset of mango varieties, evaluates visual attributes from input images, resulting in a significant enhancement in accuracy. Users can capture a mango image for quick and reliable variety identification. Additionally, real-time access to a comprehensive mango variety database enriches the user experience, providing valuable information on taste, appearance, and cultivation practices for each recognized variety. In conclusion, the Android-based Mango Variety Identification Using CNN app offers an efficient and highly accurate solution, benefiting farmers, vendors, and consumers alike, facilitating informed decisions, and fostering appreciation for this beloved fruit.

CNN, Mango Classification, Deep Learning.

"ANDROID-BASED CLASSIFICATION MODEL ON MANGO FRUIT DATASET USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.189-198, July-2024, Available :http://www.jetir.org/papers/JETIRGK06025.pdf

"ANDROID-BASED CLASSIFICATION MODEL ON MANGO FRUIT DATASET USING DEEP LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. pp189-198, July-2024, Available at : http://www.jetir.org/papers/JETIRGK06025.pdf