从Google Vision API OCR获取线条和相应的坐标

pip install google-cloud-vision

from google.cloud import vision
import io

# 设置您的Google Cloud凭据环境变量
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'path/to/your/credentials.json'

client = vision.ImageAnnotatorClient()

# 读取图像文件
with io.open('path/to/your/image.jpg', 'rb') as image_file:
    content = image_file.read()

image = vision.Image(content=content)

# 调用OCR API
response = client.text_detection(image=image)
texts = response.text_annotations

# 输出文本行及其坐标
for text in texts:
    print(f"Text: {text.description}")
    vertices = (['({},{})'.format(vertex.x, vertex.y) for vertex in text.bounding_poly.vertices])
    print(f"Coordinates: {','.join(vertices)}\n")

# 处理错误
if response.error.message:
    raise Exception(f"{response.error.message}")