简体   繁体   中英

Detecting specific rectangular part of the image

I am trying to find the rectangular regions from the image , but i am not getting my required result and also getting results slow , due to visiting every channel , What approach should i use to detect the Licence plate of the vehicle , should i need to detect the rectangular region first and than apply the OCR or i should directly apply the algorithm which are given

Thanks

Try to add one pre-processing step to enhance contrast by histogram equalization (remember that you first need to convert the color to one domain that luminance component is separated from color, then you equalize that luminace component), you can also use one clustering algoritm to make that work for you, but, keep in mind that image pre-processing is essential to have good results.

BTW, you can train one correlation filter to detect these rectangles (for example MACE).

LPR (License plate recognition) has a solid and practical solution if you search a little bit more. The solution contains edge detection(eg sobel), thresholding(on sobel), morphological operations(find close edges, something that letters have), contours(to get the rectangle from them) and an optional classifier to validate the results(filter the False Positives).

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM