guiltyneuron / anpr Goto Github PK

Hello bro how are you? good night,

i have a problem testing ur code of recognition area

maybe u can check and help me ?

Hi thank you for yor greate work .
Would you please share some images (at least 2 images) for training plate recognition ?
I'l like to know the structure of dataset .
Thank you

Hey KhazriAchraf , i want to detect Morrocan plate it's like this : file:///root/Desktop/marokko38.jpg how can i modify your code to detect the plate in real time ,

Hi
Why the accuracy is very low with plates (tunisian) from this link ? (plate recognition)

https://drive.google.com/open?id=1CTLo2BYaThPiGkasMPY8lkJkinSe5Jez

Bonjour,
pour la reconnaissance des plaques d'immatriculations administratives,
pouvez vous nous proposer une solution ?

hi
this error

Tunisian_plates/main.py", line 4, in <module>
    from sklearn.externals import joblib
ImportError: cannot import name 'joblib' from 'sklearn.externals'

If the lens is tilted, how would you adjust it?

when i start training this happend,please repond i have no idea ,
Loading weights from darknet53.conv.74...Done!
Learning Rate: 0.001, Momentum: 0.9, Decay: 0.0005
Resizing
480
Floating point exception (core dumped)

Can you provide the trained yolo weights file?

Thanks for sharing your code. I run the following script suggested by you:

python detector.py --video test.mp4

But, there is no test.mp4 file. How can i download it?

hello
thank you for your contribution, it's really good
but in the first part (license plate detection) is it a way to run it on GPU because it's really slow when we want to apply it on a video.

Hi,
I am interested in getting your dataset.zip and frozen graph to feed to our own model. Will be interested in giving out? What does it take?
please contact me at : [email protected]
Thanks.

i am trying to generate the data pickle file please helf me hoe to generate that file

hello im trying your code but i dont get good response from system

example

https://towardsdatascience.com/automatic-license-plate-detection-recognition-using-deep-learning-624def07eaaf

my only change its

contours, hierarchy = cv2.findContours(th3, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
to
_, contours, _ = cv2.findContours(th3, cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)

how you are find 700 photos , i search for Moroccan plate. please tell me how can i find it ? and how about the resolution and form of photos ?

Hi, Thank you for your great work

I wonder that how did you collect the digits of license plate recognition dataset in
"ANPR/Licence_plate_recognition/USA_plates/"

And also, Are there digit images before binarizing the images
which means cropped digits in license plates?

@KhazriAchraf
ValueError: Expected 2D array, got 1D array instead:
array=[].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

How to run licence plate detection?

if any one have have data .picke file taht is need because of the neural network train the iam struguling to generate that file .plese helf me

hi
i have this error

USA_plates/predict.py", line 39, in <module>
    ohe = OneHotEncoder(handle_unknown='ignore', categorical_features=None)
  File "F:\source\python\Digits-Classification-master\venv\lib\site-packages\sklearn\utils\validation.py", line 73, in inner_f
    return f(**kwargs)
TypeError: __init__() got an unexpected keyword argument 'categorical_features'

Hi @GuiltyNeuron, can you please add license to this repository?

I downloaded the dataset from kaggle
https://www.kaggle.com/achrafkhazri/anpr-dataset-tunisian-plates-and-digits

I am getting errors after running
$python3 main.py -mode train -d dataset

Traceback (most recent call last):
File "main.py", line 23, in
data, labels = load_dataset(args.d)
File "/Users/biranchi/Desktop/Vettons License Plate Recognition/ANPR/Licence_plate_recognition/tools.py", line 209, in load_dataset
gray = cv2.cvtColor(training_digit_image, cv2.COLOR_BGR2GRAY)
cv2.error: OpenCV(3.4.2) /Users/travis/build/skvark/opencv-python/opencv/modules/imgproc/src/color.hpp:253: error: (-215:Assertion failed) VScn::contains(scn) && VDcn::contains(dcn) && VDepth::contains(depth) in function 'CvtHelper'

The model file is overfitted, the model is not trained properly.

Hi, for the loadataset function, it says the function loads the image and the label for the image. The label for the image is the folder name. Is this correct? For example, my current dataset has 500 images, their labels are in a csv. In order to use this, does each image need to be in its own folder? And the folder name must be the Label?

File "C:\Users\Bilva Prasad\Anaconda3\lib\site-packages\sklearn\utils\validation.py", line 521, in check_array
"if it contains a single sample.".format(array))
ValueError: Expected 2D array, got 1D array instead:
array=[].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

how to fix this??

Hey KhazriAchraf, can you help me to solve this issue? Thank you

Hello,

Thanks for the awesome code.

However, I want data of number plate in one variable after capturing from an image.

Could you please help me out?

Hi,
After traning the Licence_plate_recognition model, runing python3 main.py -mode predict -i test.jpg -model mlp.pkl ended with the error :

Traceback (most recent call last):
  File "main.py", line 35, in <module>
    digits = histogram_of_pixel_projection(img)
  File "/Users/Projects/ml/ANPR/Licence_plate_recognition/tools.py", line 74, in histogram_of_pixel_projection
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
cv2.error: OpenCV(4.1.0) /Users/travis/build/skvark/opencv-python/opencv/modules/imgproc/src/color.simd_helpers.hpp:92: error: (-2:Unspecified error) in function 'cv::impl::(anonymous namespace)::CvtHelper<cv::impl::(anonymous namespace)::Set<3, 4, -1>, cv::impl::(anonymous namespace)::Set<1, -1, -1>, cv::impl::(anonymous namespace)::Set<0, 2, 5>, cv::impl::(anonymous namespace)::SizePolicy::NONE>::CvtHelper(InputArray, OutputArray, int) [VScn = cv::impl::(anonymous namespace)::Set<3, 4, -1>, VDcn = cv::impl::(anonymous namespace)::Set<1, -1, -1>, VDepth = cv::impl::(anonymous namespace)::Set<0, 2, 5>, sizePolicy = cv::impl::(anonymous namespace)::SizePolicy::NONE]'
> Invalid number of channels in input image:
>     'VScn::contains(scn)'
> where
>     'scn' is 1

Any thoughts ? thank you in advance.
/Y

Hi,

I want to ask how did you split each digit and alphabet from the license plate?

Thanks

sir plese hele me to to run the traing the neural network i need to again again i need data.pickel file.but here missing. that file how to generate it. how to generate data.pickel file.