• Pragati Vilas Ayare
• Kishori Sudhakar Gaonkar
• Rohan Ramesh Kudtarkar

Abstract: In this work, we tackle the problem of Vehicle number plate detection in natural scene images. Inspiredby the success of deep neural networks (DNNs) in various vision applications, here we leverage DNNs to learn high- level features in a cascade framework, which lead to improved performance on detection. Firstly, we train a 37-class convolutional neural network (CNN) to detect all characters in an image, which results in a high recall, compared with conventional approaches such as training a binary text/non-text classifier. False positives are then eliminated by the second plate/non- plate CNN classifier. Bounding box refinement is then carried out based on the edge information of the number plates, in order to improve the intersection-over-union (IOU) ratio. The proposed cascade framework extracts number plates effectively with both high recall and precision. .

IndexTerms- Convolution neural network, Bounding Box refinement, Run length smoothing algorithm

"Vehicle Number Plate Detection Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.268-271, April-2019, Available :http://www.jetir.org/papers/JETIR1904750.pdf

"Vehicle Number Plate Detection Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp268-271, April-2019, Available at : http://www.jetir.org/papers/JETIR1904750.pdf