4/03/2020

Example python code for : Download s3 object as opencv image in memory and upload too

Just see the code
It's not difficult.

...

...
import cv2
import numpy as np
...

def lambda_handler(event, context):
# TODO implement
bucket_name = event['Records'][0]['s3']['bucket']['name']
s3_path = event['Records'][0]['s3']['object']['key']
#download object
obj = s3_client.get_object(Bucket=bucket_name, Key=s3_path)
#obj to cv2
nparr = np.frombuffer(obj['Body'].read(), np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
#simple image processing
reimg = cv2.resize(img, (100,100) )
#cv2 to string
image_string = cv2.imencode('.png', reimg)[1].tostring()
#upload
s3_client.put_object(Bucket='thum-prj-output', Key = s3_path, Body=image_string)
...

...

4/02/2020

PDF to OpenCV as page by page using PyMuPDF library (python example code)

Just see the below example code 😊

pip install PyMuPDF
document : https://pymupdf.readthedocs.io/en/latest/

I think this is better library than pypdf2 🤔
..

import fitz
import numpy as np
import cv2
fname = 'information-10-00248-v2'
doc = fitz.open(fname+'.pdf')

#split pages
for i, page in enumerate(doc.pages()):
print(i)
zoom = 1
mat = fitz.Matrix(zoom, zoom)
pix = page.getPixmap(matrix = mat)
imgData = pix.getImageData("png")
 
#save image from byte
f = open('./save_by_byte_{}_{}.png'.format(fname, i), 'wb')
f.write(imgData)
f.close()
 
#save image from opencv
nparr = np.frombuffer(imgData, np.uint8)
img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
print(img.shape)
cv2.imwrite('./save_by_opencv_{}_{}.png'.format(fname, i),img)

..