The project developed using TensorFlow to recognize the License Plate from a car and to detect the charcters from it.

Python 65.12% Jupyter Notebook 34.88%

python tensorflow deep-learning machine-learning license-plate-recognition

tensorflow-license-plate-detection's Introduction

TensorFlow-ALPR

The project developed using TensorFlow to detect the License Plate from a car and uses the Tesseract Engine to recognize the charactes from the detected plate.

Software Packs Needed

Anaconda 3 (Tool comes with most of the required python packages along with python3 & spyder IDE)
Tesseract Engine (Must need to be installed)

Python Packages Needed

ABOUT PROJECT

TensorFlow is an open-source software library (Deep learning) for dataflow programming across a range of tasks. It is a symbolic math library, and also used for machine learning applications such as neural networks. So we have planned to use it for number plate detection.

TRAINING PHASE -- IMAGE LABELING

Collected the set of 100 images (Cars along with number plate) from the sources such as Google Images and Flickr. Then annotated the set of images by drawing the boundary box over the number plates to send it for the training phase.
- The Annoation gives the co-ordinates of license plates such as (xmin, ymin, xmax, ymax)
- Then the co-ordinates are saved into a XML file
- All the XML files are grouped and the Co-ordinates are saved in CSV file.
- Then the CSV file is converted into TensorFlow record format.
The set of other separate 10 images also gone through the above steps and saved as Test Record file

GPU TRAINING

By using the Tensorflow-gpu version, the set of annotated images were sent into the Convolutional neural network called as ssd-mobilenet where the metrics such as model learning rate, batch of images sent into the network and evaluation configurations were set. The training phase of the model took several days. At last the model came around with the positive result and detected the number plate over the input images.

OCR PART

Then the detected number plate is cropped using Tensorflow, By using the Google Tesseract-OCR (Package originally developed to scan hard copy documents to filter out the characters from it) the picture undergoes some coversions using computer vision package then the charcters are filtered out.

CROP

CONVERSION

MOTION DETECTION PART

The basic motion capturing has been implemented to capture the picture of moving vehicle by using the openCV where the threshold of the camera is fixed (threshold value changes in according to frame's boundary area). If the vehicle touches the boundary the picture is captured. (In progress)

tensorflow-license-plate-detection's People

Contributors

Stargazers

Watchers

Forkers

andrinethomas itzhp chamamme santoshi055 ngadhvi eleenchang norberto-enomoto faical-yannick-congo maxprog kanghanbich handsomeboy mmua lchia bharath5673 sante85 shwetashettar thamizh-sterio pingbixupt arieframasyarif nattita chappie74 vonholst dheeraj-thedev faizan1041 ajaykannuri abhisheik1289 willvin313 lucaskuan alex-delacruz haneetgh hckdk24 devasivakanth maik900 gandrei95 mkzirncz1 thecyberkibbutz pluketic xing710 caolusg adrianhust farmers-tan tiravata sherwinterunez amarsaikhanb sharan-sundar flavio58it mao-example badmusanu sasauz xiaolaozai pooja2509 mick0622 iamraqeeb edenshin rashikyou issifuabdulmajeed keyochali cleristondantas djordjedot antonizhubar biranchi2018 alexjonas yashwant43 anusolanki pai-chai-university ngoluuduythai bernaldani vaibhavbiturwar cagrigungor deepikabrown fengsterooni hassanmajidi worl6088 deepdriving aashishpt drastraios akniloy6 vegebir sameedahmedkhan dharanya-subramanian rysias likith1206 cecethea rsingh2083 sundaram81200 ammartahircheema plasmadev-sudo gachen95 amardimiaty esttelle umeshsati54 yafaa gaurav82692 tweikiang ahmadnaghibi loganzi aagrandaz momodevlop vramana36 sudeep25022000

tensorflow-license-plate-detection's Issues

GUI

I have no GUI, how can I run this without GUI

I have a license plate detection project, how can I crop the image after the detection object?

how to add the code?

cannot import name 'label_map_util' from 'utils'

python .\numplate_recognition_detection.py
2021-02-01 15:07:20.916974: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2021-02-01 15:07:20.917460: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
File ".\numplate_recognition_detection.py", line 18, in
from utils import label_map_util
ImportError: cannot import name 'label_map_util' from 'utils' (C:\Program Files (x86)\Python 3.8\lib\site-packages\utils_init_.py)

Training for new Country

Thanks for this repository, can I use this to train my own model, for example I have two model for our country and train it using this?

Will this program be able to make it real time using IP Camera?

No such file / folder training\object-detection.pbtxt

Line 34 in your code : label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
No such file / folder training\object-detection.pbtxt ?
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: training\object-detection.pbtxt : The system cannot find the file specified.
; No such file or directory

NameError: name 'get_ipython' is not defined

/Tensorflow-License-Plate-Detection-master/numplate_recognition_detection.py", line 13, in
get_ipython().magic('matplotlib inline')

where can get_ipython be defined?
the file has not been changed, I just installed the packages.
greetings!

ImportError: No module named 'utils'

I think you have not uploaded utils file.

EMPTY PACKAGE OR MODULE

HI, I am a new student researcher in python, I downloaded your projects and installed all the dependables but on running your code I got error "ModuleNotFoundError: No module named 'object_detection.utils'". I went and pip install utils and tried again but same error. i checked in your project and saw object_detedtion as a folder (more like a package) and it is literally empty. please guide me on how to fix this.

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb2 in position 12: invalid start byte

Traceback (most recent call last):
File "numplate_recognition_detection.py", line 81, in
text = pytesseract.image_to_string(Image.open(filename),lang=None)
File "D:\Anaconda3\envs\tensorflow_gpu\lib\site-packages\pytesseract\pytesseract.py", line 294, in image_to_string
return run_and_get_output(*args)
File "D:\Anaconda3\envs\tensorflow_gpu\lib\site-packages\pytesseract\pytesseract.py", line 202, in run_and_get_output
run_tesseract(**kwargs)
File "D:\Anaconda3\envs\tensorflow_gpu\lib\site-packages\pytesseract\pytesseract.py", line 178, in run_tesseract
raise TesseractError(status_code, get_errors(error_string))
File "D:\Anaconda3\envs\tensorflow_gpu\lib\site-packages\pytesseract\pytesseract.py", line 79, in get_errors
line for line in error_string.decode('utf-8').splitlines()

Excuse me！ I meet this problem when I run the code. Do you know how to solve it?

No 'training\object-detection.pbtxt' file in repository

Hello,
Thanks for this repository, can you add 'training\object-detection.pbtxt' file to this repository.
This file is required to run this project, and file is missing from repository.

Need Requirement File

Hello, I hope you are doing well. I want to train your repo. I want to know the requirements for this.

Missing utils

Hi Dharun,

I am trying to run your code for car plate recognition but get an error for missing utils. Could you also share you utils file?

ModuleNotFoundError: No module named 'object_detection

Hi, I downloaded repository and tried to run numplate_recognition_detection, I'm running it with anaconda IPython 7.8.0. First I got error message: "UnknownBackend: No event loop integration for 'inline'. Supported event loops are: qt, qt4, qt5, gtk, gtk2, gtk3, tk, wx, pyglet, glut, osx". According to tensorflow discussion I replaced matplotlib inline for matplotlib tk. but then I got error message: ModuleNotFoundError: No module named 'utils'. I downloaded utils file from previous issue but than this showed up: ModuleNotFoundError: No module named 'object_detection_evaluation'. Any idea on what am I doing wrong? (note, first time using IPython O:) )

Can I recognitize two layer car plate using these project?

object-detection.pbtxt can not be found.

Do i have to train the model again to obtain object-detection.pbtxt? This error occured when i run numberplate_recognition_detection.py:

Traceback (most recent call last):
  File "C:\Users\DELL\Downloads\Tensorflow-License-Plate-Detection-master\Tensorflow-License-Plate-Detection-master\numplate_recognition_detection.py", line 34, in <module>
    label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
  File "C:\Users\DELL\Downloads\Tensorflow-License-Plate-Detection-master\Tensorflow-License-Plate-Detection-master\object_detection\utils\label_map_util.py", line 117, in load_labelmap
    label_map_string = fid.read()
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36-32\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 120, in read
    self._preread_check()
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36-32\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 80, in _preread_check
    compat.as_bytes(self.__name), 1024 * 512, status)
  File "C:\Users\DELL\AppData\Local\Programs\Python\Python36-32\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 519, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: NewRandomAccessFile failed to Create/Open: training\object-detection.pbtxt : The system cannot find the path specified.

; No such process

Tesseract model

pytesseract.tesseract_cmd = '/home/tensorflow-cuda/dharun_custom/models/research/object_detection/tessdata/'

I don't find this folder inside this repository, maybe you can refactor this repository to make it more understandable? thank you!

Missing file in Proto or Util

ImportError Traceback (most recent call last)
in
2 sys.path.append("/Users/jivira/Tensorflow-License-Plate-Detection-master/object_detection")
3
----> 4 from utils import label_map_util
5 from utils import visualization_utils as vis_util
6

~/Tensorflow-License-Plate-Detection-master/object_detection/utils/label_map_util.py in
24 import tensorflow as tf
25 from google.protobuf import text_format
---> 26 from object_detection.protos import string_int_label_map_pb2
27
28

ImportError: cannot import name 'string_int_label_map_pb2'

Can you please help me in this....

dharun / tensorflow-license-plate-detection Goto Github PK