I am trying to use the Google Cloud Vision API to detect text in an image. I followed the code in the following tutorial: https://cloud.google.com/vision/docs/fulltext-annotations
The full code is below:
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, 'red')
bounds = get_document_bounds(filein, FeatureType.PARA)
draw_boxes(image, bounds, 'red')
bounds = get_document_bounds(filein, FeatureType.WORD)
draw_boxes(image, bounds, 'red')
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)
I am using Windows 10 with Python 3.7 and use the following code in the command prompt:
C:\Users\ariel\Dropbox\Research\Mestizo\Code>python doctext.py censo_19940_tab_corta-30.png -out_file out.jpg
And I get the following error and traceback:
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\PIL\ImagePalette.py", line 99, in getcolor
return self.colors[color]
KeyError: (255, 0, 0)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "doctext.py", line 96, in <module>
render_doc_text(args.detect_file, args.out_file)
File "doctext.py", line 78, in render_doc_text
draw_boxes(image, bounds, 'red')
File "doctext.py", line 35, in draw_boxes
bound.vertices[3].x, bound.vertices[3].y], None, color)
File "C:\ProgramData\Anaconda3\lib\site-packages\PIL\ImageDraw.py", line 239, in polygon
ink, fill = self._getink(outline, fill)
File "C:\ProgramData\Anaconda3\lib\site-packages\PIL\ImageDraw.py", line 113, in _getink
ink = self.palette.getcolor(ink)
File "C:\ProgramData\Anaconda3\lib\site-packages\PIL\ImagePalette.py", line 109, in getcolor
self.palette[index + 256] = color[1]
IndexError: bytearray index out of range
I have looked through previous posts about this error but I can't figure out where this is coming from.
The issue was that I was using a png file when I was supposed to use a jpg. The documentation of the code/tutorial uses a jpg file as an input:
https://cloud.google.com/vision/docs/fulltext-annotations
After converting to a jpg, the code ran without problems and produced the expected output.