nsankethreddy/DiabolicalBaggage

The project contains the files related to dataset creation and then training the dataset for flagging the knives and guns in an automatic baggage scanning system.

DiabolicalBaggage: Baggage scanning using ML

Datasets:

Two datasets were experimented with.

• SIXray
• GDXray

Refernces:

https://machinelearningmastery.com/how-to-use-transfer-learning-when-developing-convolutional-neural-network-models/
https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-to-classify-photos-of-dogs-and-cats/

Execution:

• Model.py: Sets up the model with the mobilenet image classification architecuture.
• Training.py: Trains the model, with specified dataset.

Parts

• Firearm classifier
• Other objects such as knives, laptops, shurikens, razor blades,etc

Final Dataset

*Firearm classifier : Cropped out images of guns vs empty bag space