• Prachi Suresh Sakhare
• Yogesh Golhar

In this paper we discuss an efficient approach to detect license plate and recognize them. Our approach automatically detects and track license plate using Kanade Lucas Tomasi (KLT) algorithm. In this algorithm, we used two modes. First is detection and second is tracking mode. In detection mode, we used two-stage approach to detect license plate (LP) to improve accuracy. In first stage, a set of candidate plate regions were detected using Viola-Jones algorithm. In second stage, AlexNet as a feature extractor and SVM as a classifier are used. If image passes the test then using various morphological operations, exact plate region extracted. After successful detection of LP, alphanumeric areas were extracted. To recognize alphanumeric images backpropogational neural network is used. In second mode licence plate tracked. Counter applied to refresh target after every 50 intervals. Experimental results show that this method provides improved LP detection as compared to the existing baseline methods.

Kanade Lucas Tomasi (KLT) algorithm, Viola-Jones algorithm, AlexNet, SVM Classifier, Morphological operations, Alphanumeric, Backpropogational Neural Network

"License Plate Detection Using Hybrid Morphological Technique And Recognition Using Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 5, page no.864-870, May-2020, Available :http://www.jetir.org/papers/JETIR2005121.pdf

"License Plate Detection Using Hybrid Morphological Technique And Recognition Using Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 5, page no. pp864-870, May-2020, Available at : http://www.jetir.org/papers/JETIR2005121.pdf