Automatic Number Plate Recognition Using CNN

Automatic Number Plate Recognition Using CNN

Project covers detecting of number number plate using Haar-Cascade,and then segmenting out individual digits and feeding them to trained CNN

Artificial Intelligence

  • 0 Collaborators



Achieving high accuracy(97%+) on data set MNIST (which contain binary images of handwritten digit) motivated us to train the CNN to classify the number plate letters.We used Haar-Cascade with russiannumberplate pretrained classifier to detect number plates.Then we used Open-CV to find contours and extracted individual number which lie in certain aspect ratio.Last step was to use Caffe by berkeleyvision to classify the detected digits. We achieved 97% accuracy using the above architecture. Note:Currently i don't have my lappy with me so i will upload the images soon. Note:To request source code drop us a mail.

Medium 23674745 538901773125884 7636566904215259396 o

Rima M. updated status

Medium 23674745 538901773125884 7636566904215259396 o

Rima Modak

I am currently working to develop a prototype of an device based on IoT. This device will be used to detect any kind of material. It will be used to detect both living and non-living things, and after detecting, it will display varies other things related to the detected object according to the tags provided by the user/customer.

Medium fb img 1503828642929

Aravindhan N. created project Automatic attendance management system using face detection

Medium 5ad5deff 1bd2 4f42 8706 11bcd0116743

Automatic attendance management system using face detection

Automatic attendance management system will replace the manual method, which takes a lot of time and is difficult to maintain.There are many bio metric processes ,in that face recognition is the best method. In our campus staff attendance is taken with the help of Gesture recognition /attendance sheet .We can take this to next level by implementing Artificial Intelligence based Face Recognition using Convolution Neural Network(CNN). We have to train our neural net using COCO (large Image dataset designed for object detection) and Staff Dataset (Several images of individual staffs). Since we don't have the photos of the staffs,we have trained our neural net using our own photos.Our Neural net consists of 20 neurons in the hidden layer which help us to diagnose the pixels of the image and compares the result with the trained dataset .By using our advanced system the staffs can use their own mobile/laptop [camera] for registering their presence in their own place which is possible only if they are connected to our college Network (WiFi).

See More

No users to show at the moment.