I am trying to test out Easy OCR. Now when I run my code
path = "{image file}" read = easyocr.Reader(['en'], gpu=True) result = read.readtext(path) print(result)
It outputs this
[([[887, 1], [975, 1], [975, 13], [887, 13]], 'Photoshop PSD hle', 0.7655935865739645), ([[978, 2], [1022, 2], [1022, 10], [978, 10]], 'Jownioao', 0.2720053768871571), ([[1044, 2], [1152, 2], [1152, 10], [1044, 10]], 'Resolution 1230x1024P}', 0.3419384126594147), ([[1169, 2], [1274, 2], [1274, 10], [1169, 10]], 'uDsooradhics cor', 0.10438481226211914), ([[285, 474], [980, 474], [980, 716], [285, 716]], 'TEXT', 0.999515175819397)]
Instead of just
([[285, 474], [980, 474], [980, 716], [285, 716]], 'TEXT', 0.999515175819397)]
I want to get an simple output but it seems it also prints the image details and such.
EDIT: Sorry I posted a wrong output. If anyone is wondering here’s the link of the photo
Advertisement
Answer
As it is explained in the repo: “The output will be in a list format, each item represents a bounding box, the text detected and confident level, respectively.”
You can set detail=0
for simpler output:
result = read.readtext(path, detail = 0)