Revision history [back]

I am planning to perform ocr on Indian number plates.I used tessract 4.0 beta which uses LSTM engine for ocr. Although recognized characters are not coming out to be correct. i used cv2.Laplacian() while picking up images without blur and performed noise reduction using cv2.fastNlMeansDenoisingColored() on the image . Still results seems not so accurate.

1)Can we please suggest what other preprocessing techniques that need to perform to enhance the image 2)Can we keep a check on tessract such that no special characters are detected.

Test images look like these.

detected characters: *DLBCAUS368 “HR 10¥5803

Thanks in advance

I am planning to perform ocr on Indian number plates.I used tessract 4.0 beta which uses LSTM engine for ocr. Although recognized characters are not coming out to be correct. i correct. I used cv2.Laplacian() while picking up images without blur and performed noise reduction using cv2.fastNlMeansDenoisingColored() on the image . Still results seems not so accurate.image. For preprocessing I performed following steps 1)Sharpened image

1)Can we please suggest what other preprocessing techniques that need to perform to enhance the image 2)Can we keep a check on tessract such that no special characters are detected.2)performed otsu thresholding

3)Eliminated smaller noises/contours

4)Then inverted image

5)OCR using tesseract 4.0 --oem 1(Which uses lstm as detectio module )

Test images look like these.

detected characters: *DLBCAUS368 “HR 10¥5803

Detected output: OL 1CT 5079 (Which seems ok)

Can you please suggest any other preprocessing required to improve image(Reduce noise)?

Also is there a way to restrict special characters in tesseract?(Could not find it in latest version)

(ps. I am using python)

Thanks in advance

I am planning to perform ocr on Indian number plates.I used tessract 4.0 beta which uses LSTM engine for ocr. Although recognized characters are not coming out to be correct. I used cv2.Laplacian() while picking up images without blur and performed noise reduction using cv2.fastNlMeansDenoisingColored() on the image. For preprocessing I performed following steps steps

1)Sharpened image

2)performed otsu thresholding

3)Eliminated smaller noises/contours

4)Then inverted image

5)OCR using tesseract 4.0 --oem 1(Which uses lstm as detectio module )

Test images look like these.

Detected output: OL 1CT 5079 (Which seems ok)

Can you please suggest any other preprocessing required to improve image(Reduce noise)?

Also is there a way to restrict special characters in tesseract?(Could not find it in latest version)

(ps. I am using python)

Thanks in advance