The Automatic Number Plate Extraction is an innovative system where characters are extracted from a number plate image. Many image processing steps are used in order to extract only text from number plate image. Since the image is more susceptible to noise and many other unwanted objects, noise is first removed from the image. Before image preprocessing steps, the RGB image is converted to a gray-scale image and the image is resized keeping aspect ratio same. Morphological processing is used to detect text more accurately. The image is converted to double. Edge detection method is used to detect edges and image intensity level is increased. Objects with gaps are filled. After edge detection, the image might contain many horizontal and vertical lines. These lines are removed from the image to extract only the text from the image. After applying these preprocessing steps, the image is left with few smaller unwanted objects. These unwanted objects are removed from the image, and the text from number plate are extracted.
Vehicle Number plate, Natural Language Processing, Pattern Recognition
Cite This Article
"Automatic Number Plate Extraction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.4, Issue 4, page no.14-16, April-2017, Available :http://www.jetir.org/papers/JETIR1704004.pdf
Published Paper ID: JETIR1704004
Registration ID: 170160
Published In: Volume 4 | Issue 4 | Year April-2017