[Python] Segmenting License Plate Characters

I am facing a problem in segmenting characters from a license plate image. I have applied following method to extract license plate characters"

1. Adaptive threshold the license plate image.
2. Select contours which having particular aspect ratio.

If there is any shade in the license plate image as in attached file, I am not able to properly segment the characters due to improper binarization. The shade in the image merges adjacent characters in the image.

I have thresholded the images with different window sizes. The results are attached. How can I segment characters from image if there is shade in the image? I am using OpenCV.









I have used following function in OpenCV to threshold my license plate image:

cvAdaptiveThreshold(licensePlateImg, threshImg, 255, CV_ADAPTIVE_THRESH_GAUSSIAN_C, CV_THRESH_BINARY_INV, wind);


I have tried with different window sizes (wind) and different adaptiveMethod (ADAPTIVE_THRESH_MEAN_C and ADAPTIVE_THRESH_GAUSSIAN_C) to get the thresholded images.

Continue reading...