View Code? Open in Web Editor
NEW
This repo contains my bachelor thesis project which is a conveyor belt system that detects and separates rotten fruits using machine learning.
License: GNU General Public License v3.0
Python 90.54%
Jupyter Notebook 9.46%
bachelor-thesis-project-ml-based-conveyor-belt-for-detecting-separating-rotten-fruits's People
Contributors
Watchers
bachelor-thesis-project-ml-based-conveyor-belt-for-detecting-separating-rotten-fruits's Issues
In this step, the camera must be set according to a convenient position.
Set the position of the camera for a clear view.
Draw a couple of lines for the fruit passed.
There should be 2 lines (for now) one of which is for opening the flapper, other one is closing the flapper.
In this section, a function or a class structure must be defined for contour detection. It will be working with the object detection algorithm. When the object (fruit) is detected, this algorithm will detect and draw the object's contours.
Define a function or class structure
Use morphological operations
Find and Draw the contours
Set a text label above the rectangle drawn, it is a place for the label of the fruit (e.g. rotten Apple, fresh Banana, etc.)
This is the final part, put all those algorithms together!
Inside the GUI script, implement object detection, and contour detection algorithms.
Set motor opening and closing times by updating the **FireBase Realtime Database".
The counter of the GUI must be updated according to the fruits.
Train a Neural Network model by using the Transfer Learning method.
Create a class structure for this.
The class must have a train function . It must be controlled by argparser in the terminal.
argparser must take
the path of the dataset,
number of epochs and batch size
path of the model for saving
Save the model.
This part will take place in Raspberry Pi for coding motor control algorithms.
Create two Config Files for both OS (Windows and Raspberry Pi).
One of the Config Files will contain the KEYS of FireBase Realtime Database
Another one will contain Parameters of Motor Controlling Algorithms inside the Raspberry Pi.
The main idea of Config Files is that control the Motor inside of Windows OS remotely without controlling in Raspberry Pi.
Create two FireBase Realtime Database
One of the Database will be about controlling the opening and closing time of the Motor
Another one of the Database is about Motor Control Parameters