deep-anpr icon indicating copy to clipboard operation
deep-anpr copied to clipboard

Faster detection

Open ghost opened this issue 8 years ago • 6 comments

Hello everyone,

I use the YOLO method to detect the plates in 0.02 seconds. Now I would like to read the plate with the Mattwew Earl method by entering the area containing the plate directly in order to optimize the time. Do you have an idea ?

Thank's

ghost avatar Jun 02 '17 09:06 ghost

How do you train YOLO for detect just for plates? do you use your own labeled VOC format dataset?.

stanlee321 avatar Jun 15 '17 23:06 stanlee321

You can do this with this link : https://timebutt.github.io/static/how-to-train-yolov2-to-detect-custom-objects/

ghost avatar Jun 16 '17 09:06 ghost

can you share the dataset.

Abhi001vj avatar Jun 27 '17 08:06 Abhi001vj

@novsub can you share your dataset?

LiangHao92 avatar Aug 04 '17 02:08 LiangHao92

i want to hear more

vuducdung avatar Aug 08 '17 17:08 vuducdung

If it is any help, there are datasets linked to this paper and they provide datasets which single out license plates. I'm sorry I can find the direct download link I used.

toddb avatar Apr 30 '18 05:04 toddb