Low Quality Vehicle License Plate Recognition Using Deep Learning Approach
- 0 Collaborators
-> Built a Novel Neural Network architecture, which helps in recognizing Arbitrary Length, Multi-Style and Noisy Images in Segmentation Free Manner. -> Achieved State of the Art Accuracy on license Plate Dataset with Improvement of more than 1.9% in Accuracy. ...learn more
Project status: Published/In Market
Overview / Usage
Identifying License Plates using Convolutional Recurrent Neural Network.
Compared with previous systems for scene text recognition, the proposed architecture possesses the following distinctive properties:
(1) It is an end-to-end trainable. in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It generates an effective yet much smaller model, which is more practical for real-world application scenarios.
Methodology / Approach
In this project, I am investigating the problem of license plate recognition, which is among the most important and challenging tasks in image-based sequence recognition. I am using A novel neural network architecture, which integrates feature extraction, sequence modeling, and transcription into a unified framework. I am using a novel neural network architecture, called Convolutional Recurrent Neural Network (CRNN), which integrates the advantages of both Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). CRNN is able to take input images of varying dimensions and produces predictions with different lengths. It directly runs on coarse level labels requiring no detailed annotations for each individual element in the training phase. Moreover, as CRNN abandons fully connected layers used in conventional neural networks, it results in a much more compact and efficient model. All these properties make CRNN an excellent approach for image-based sequence recognition.
Technologies Used
Deep learning: CNN, RNN, Bidirectional LSTM, CTC Loss function
OpenCV: For generating a different type of Synthetic license plates.
Keras, Tensorflow