如何正确进行短数字识别
#16147
Replies: 2 comments
-
使用PP-OCRv4_server_rec模型识别为"L" |
Beta Was this translation helpful? Give feedback.
0 replies
-
最新的 PP-OCRv5 的模型有尝试吗?近期PaddleOCR3.2也会跟新 en_PP-OCRv5_rec 模型,可以尝试一下 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
我目前使用的是
rec_model_name = "en_PP-OCRv4_mobile_rec"
ocr = PaddleOCR(
use_angle_cls=False,
text_recognition_model_name=rec_model_name,
text_recognition_model_dir=os.path.join(ocr_model, rec_model_name)
)
cv2.imshow("ROI", img)
cv2.waitKey(0) # 按任意键关闭
cv2.destroyAllWindows()
ocr.ocr(img)
我的需求是识别类似下图(cv2.imshow("ROI", img))中的,带有一定背景的,文本清晰的,仅英文数字识别
但是我识别这张图的时候它给出的结果是 'rec_texts': ['-'] ,而不是正确的数字“1”,这是识别出错了?自动进行了旋转识别?我应该做些什么?
或者说有没有方法,能够限制它进行匹配的范围为0-9,是否能提高准确率?
Beta Was this translation helpful? Give feedback.
All reactions