
Quail Egg Detection and Classification Through Egg Candling and Image Processing
Software as a Service
NoCategory
Thesis DesignClients
Mapua University
Techstack
PythonTensorFlowOpenCVPyQt5Raspberry Pi
Purpose
Automate quail egg fertility inspection by combining a candling rig with image classification, replacing slow manual candling with a device that grades each egg as fertile, infertile, or not a quail egg.
Description
A Raspberry Pi candling prototype captures backlit egg images with its camera and classifies them using a convolutional neural network trained in TensorFlow/Keras on a fertile-versus-infertile dataset, then deployed on-device as a TensorFlow Lite model. A PyQt5 touchscreen interface handles capture and displays results, and model performance was validated with accuracy metrics and a confusion matrix.




