DataBall 助力快速掌握数据集的信息和使用方式，会员享有 百种数据集，持续增加中。
需要更多数据资源和技术解决方案，知识星球： “DataBall - X 数据球(free)”
-----------------------------------------------------------------
Paddle OCR 中英文检测识别
具体实现代码如下：
#-*-coding:utf-8-*-
# date:2024-12-22
# Author: DataBall - XIAN
# Function: OCR 检测识别import os
import cv2
import numpy as np
import time
from paddleocr import PaddleOCRif __name__ == '__main__':if False: # 中文cls_model_dir='paddleModels/whl/cls/ch_ppocr_mobile_v2.0_cls_infer'rec_model_dir='paddleModels/whl/rec/ch/ch_PP-OCRv4_rec_infer'ocr = PaddleOCR(use_angle_cls=True, lang="ch", det=False,cls_model_dir=cls_model_dir,rec_model_dir=rec_model_dir) # need to run only once to download and load model into memoryelse: # 英文# ocr = PaddleOCR(use_angle_cls=True, lang="en")cls_model_dir='paddleModels/whl/cls/en_ppocr_mobile_v2.0_cls_infer'rec_model_dir='paddleModels/whl/rec/ch/en/en_PP-OCRv4_rec_infer'ocr = PaddleOCR(use_angle_cls=True, lang="en", det=False,cls_model_dir=cls_model_dir,rec_model_dir=rec_model_dir) # need to run only once to download and load model into memoryimg_path = "image/2.png"img = cv2.imread(img_path)result_det = ocr.ocr(img, cls=True)print(type(result_det))result_det = result_det[0]idx_ = 0for m_ in result_det:idx_ += 1bbox_,contant_ = m_print("[{}] bbox: {}, contant: {}".format(idx_,bbox_,contant_))pts = np.array(bbox_).astype(np.int32)pts = pts.reshape((-1,1,2))# 绘制区域cv2.polylines(img,[pts],True,(255,22,150),1)cv2.namedWindow("img",0)cv2.imshow("img",img)cv2.waitKey(0)cv2.imwrite("out.png",img)
示例如下：
助力快速掌握数据集的信息和使用方式。
数据可以如此美好！
