Kavach'23 - Team: 404_Found
P.S. Code : KVH-005
Phase 1 : Testing normal plate recogintion
- Successfully tested normal character recognition using
python scripts
andOpenCV
- Nope it all starts here
- we have also prepared the ground work for
Easy OCR
andTensorFlow Object Detection
- We are done setting up
Virtual env/Kernel
for our ANPR system (so while integratingFace Recognition System
there won't be any problem about over-writing of libraries)
Step - 1 :
python -m venv anprsys
Step - 2 : Activate your virtual environment
source tfod/bin/activate # Linux
.\arpysns\Scripts\activate # Windows
Step - 3 : Install dependencies and add virtual environment to the Python Kernel
python -m pip install --upgrade pip
pip install ipykernel
python -m ipykernel install --user --name=anprsys
-
We are also in middle of completion of integrating
TensorFlow API
for out project -
To train model we will be using
Transfer learning
method in initial phase
!. Initially we will be using kaggel dataset
and manually divided
the collected images into two folders
train and test so that all the images
and annotations will be split among
these two folders.
- We will be using
pre-trained state-of-the-art model
and just fine tuned it on our particular specific use case. We will begin the training process by opening Real Time Number Plate Detection and installed the Tensoflow Object Detection (TFOD) + API
- Opencv
- Easy OCR
- Tensorflow
- Jupyter Notebook/Jupyter Lab
- Python Libraries (more can be used depending upon the implementation*)
- Surya Pratap Singh Chauhan
- Ujjawal Tyagi
- Yash Vardhan Singh
- Shravya Vashishtha
- Suryansh Kapil
- Shreya Srivastava