문서에서 텍스트 인식

문서에서 인식된 텍스트 주위에 상자를 그립니다.

이 코드 샘플이 포함된 문서 페이지

컨텍스트에서 사용된 코드 샘플을 보려면 다음 문서를 참조하세요.

코드 샘플

Python

이 샘플을 시도해 보기 전에 Vision 빠른 시작: 클라이언트 라이브러리 사용의 Python 설정 안내를 따르세요. 자세한 내용은 Vision Python API 참조 문서를 확인하세요.

import argparse
from enum import Enum
import io

from google.cloud import vision
from PIL import Image, ImageDraw

class FeatureType(Enum):
    PAGE = 1
    BLOCK = 2
    PARA = 3
    WORD = 4
    SYMBOL = 5

def draw_boxes(image, bounds, color):
    """Draw a border around the image using the hints in the vector list."""
    draw = ImageDraw.Draw(image)

    for bound in bounds:
        draw.polygon([
            bound.vertices[0].x, bound.vertices[0].y,
            bound.vertices[1].x, bound.vertices[1].y,
            bound.vertices[2].x, bound.vertices[2].y,
            bound.vertices[3].x, bound.vertices[3].y], None, color)
    return image

def get_document_bounds(image_file, feature):
    """Returns document bounds given an image."""
    client = vision.ImageAnnotatorClient()

    bounds = []

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

    image = vision.Image(content=content)

    response = client.document_text_detection(image=image)
    document = response.full_text_annotation

    # Collect specified feature bounds by enumerating all document features
    for page in document.pages:
        for block in page.blocks:
            for paragraph in block.paragraphs:
                for word in paragraph.words:
                    for symbol in word.symbols:
                        if (feature == FeatureType.SYMBOL):
                            bounds.append(symbol.bounding_box)

                    if (feature == FeatureType.WORD):
                        bounds.append(word.bounding_box)

                if (feature == FeatureType.PARA):
                    bounds.append(paragraph.bounding_box)

            if (feature == FeatureType.BLOCK):
                bounds.append(block.bounding_box)

    # The list `bounds` contains the coordinates of the bounding boxes.
    return bounds

def render_doc_text(filein, fileout):
    image = Image.open(filein)
    bounds = get_document_bounds(filein, FeatureType.BLOCK)
    draw_boxes(image, bounds, 'blue')
    bounds = get_document_bounds(filein, FeatureType.PARA)
    draw_boxes(image, bounds, 'red')
    bounds = get_document_bounds(filein, FeatureType.WORD)
    draw_boxes(image, bounds, 'yellow')

    if fileout != 0:
        image.save(fileout)
    else:
        image.show()

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('detect_file', help='The image for text detection.')
    parser.add_argument('-out_file', help='Optional output file', default=0)
    args = parser.parse_args()

    render_doc_text(args.detect_file, args.out_file)

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저를 참조하세요.