Home / Case Studies / Fruits Recognition

The solution created by APRO is able to detect strawberries on the image taken by camera on a daily basis and recognize different states of each berry starting from flower and till a ripe berry. This solution can be adapted to detection and recognition of any type of berry. The solution uses artificial intelligence (AI) technologies and utilizes modern neural networks.

Aim of the Project

● Create an AI model to detect and recognize strawberries on an image from a camera
● Develop a web service & API for the AI model integration and usage

Results Achieved

● Accuracy 84%
● Image processing time <0.5 sec

Main Technologies

● AI Architecture: Faster RCNN (backbone resnet 50)
● For ML: TensorFlow, Keras, Python.
● For Backend: Flask, Python.
● For Environment: Docker.

The development was made from scratch using 2500 marked up images with defined 6 states of berries. During R&D phase we have compared Deeplabv3+ Gaussian and Faster RCNN (backbone resnet 50), the last approach gave a bit better results.

Model Features

The model is able to work with the following defects on images:
– partly blurred images
– bright glares from the sun

The model can detect 6 states of a berry:
– flower
– small green berry
– green berry
– white berry
– start colouring berry
– ripe berry

Initial model accuracy was increased by increasing the number of learning dataset and quality of markup.