在 google-vision text-detection api 中在哪里使用语言提示?

问题描述

所以我知道 google-vision api 支持多种语言进行文本检测.通过使用下面的代码，我可以从图像中检测英语.但是根据谷歌，我可以使用参数语言提示来检测其他语言.那么我想在下面的代码中到底把这个参数放在哪里?

So I know that google-vision api supports multiple language for text-detection. And by using the code below I can detect english language from image. But according to google I can use the parameter language hints to detect other languages. So where exactly am I suppose to put this parameter in the code below?

def detect_text(path):
    """Detects text in the file."""
    from google.cloud import vision
    imageContext = 'bn'
    client = vision.ImageAnnotatorClient(imageContext)

    with io.open(path, 'rb') as image_file:
        content = image_file.read()

    image = vision.types.Image(content=content)

    response = client.text_detection(image=image)
    texts = response.text_annotations
    print('Texts:')

    for text in texts:
        print('\n"{}"'.format(text.description))

        vertices = (['({},{})'.format(vertex.x, vertex.y)
                    for vertex in text.bounding_poly.vertices])

        print('bounds: {}'.format(','.join(vertices)))


detect_text('Outline-of-the-Bangladesh-license-plates_Q320.jpg')

推荐答案

像这样:

response = client.text_detection(
    image=image,
    image_context={"language_hints": ["bn"]},  # Bengali
)

参见 ImageContext" 了解更多详情.

See "ImageContext" for more details.

这篇关于在 google-vision text-detection api 中在哪里使用语言提示?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！