Detectar texto en documentos

Dibuja cuadros alrededor del texto detectado en un documento.

Investigar más

Para obtener documentación detallada que incluya este código de muestra, consulta lo siguiente:

Código de ejemplo

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración de Python que se indican en la guía de inicio rápido de Vision con bibliotecas de cliente. Para obtener más información, consulta la documentación de referencia de la API Python de Vision.

Para autenticarte en Vision, configura las credenciales predeterminadas de la aplicación. Para obtener más información, consulta el artículo Configurar la autenticación en un entorno de desarrollo local. 

import argparse
from enum import Enum

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):
    """Draws a border around the image using the hints in the vector list.

    Args:
        image: the input image object.
        bounds: list of coordinates for the boxes.
        color: the color of the box.

    Returns:
        An image with colored bounds added.
    """
    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):
    """Finds the document bounds given an image and feature type.

    Args:
        image_file: path to the image file.
        feature: feature type to detect.

    Returns:
        List of coordinates for the corresponding feature type.
    """
    client = vision.ImageAnnotatorClient()

    bounds = []

    with 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):
    """Outlines document features (blocks, paragraphs and words) given an image.

    Args:
        filein: path to the input image.
        fileout: path to the output image.
    """
    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)

Siguientes pasos

Para buscar y filtrar ejemplos de código de otros Google Cloud productos, consulta el Google Cloud navegador de ejemplos.