0

I am writing a handwriting recognition app and my inputs have to be of a certain size (128x128). When I detect a letter it looks like this:

this

That image for instance has a size of 40x53. I want to make it 128x128, but simply resizing it lowers the quality especially for smaller images. I want to somehow fill the rest up to 128x128 with the 40x53 in the middle. The background color should also stay relatively the same. I am using Python's opencv but I am new to it. How can I do this, and is it even possible?

Megid
  • 105
  • 12

2 Answers2

1

I believe you want to scale your image.

This code might help:

import cv2

img = cv2.imread('name_of_image', cv2.IMREAD_UNCHANGED)

# Get original size of image
print('Original Dimensions: ',img.shape)

# Percentage of the original size
scale_percent = 220

width = int(img.shape[1] * scale_percent / 100)
height = int(img.shape[0] * scale_percent / 100)
dim = (width, height)

# Resize/Scale the image
resized = cv2.resize(img, dim, interpolation = cv2.INTER_AREA)

# The new size of the image
print('Resized Dimensions: ',resized.shape)

cv2.imshow("Resized image", resized)
cv2.waitKey(0)
cv2.destroyAllWindows()
Wool
  • 138
  • 1
  • 10
  • 2
    I mentioned that I don't want to resize/scale it, I want to basically add more content to it until it's the size I want. Basically from 10x10 I want to "border" it up to 100x100, not resize it. – Megid May 09 '18 at 11:55
1

Here you can get what you have asked using outputImage. Basically I have added a border using copyMakeBorder method. You can refer this for more details. You have to set the color value as you want in the value parameter. For now it is white [255,255,255].

But I would rather suggest you to resize the original image, seems like it is the better option than what you have asked. Get the image resized you can use resized in the following code. For your convenience I have added both methods in this code. 

import cv2
import numpy as np
inputImage = cv2.imread('input.jpg', 1)

outputImage = cv2.copyMakeBorder(inputImage,37,38,44,44,cv2.BORDER_CONSTANT,value=[255,255,255])

resized = cv2.resize(inputImage, (128,128), interpolation = cv2.INTER_AREA)
cv2.imwrite('output.jpg', outputImage)
cv2.imwrite('resized.jpg', resized)
Ishara Madhawa
  • 3,549
  • 5
  • 24
  • 42
  • I think this is what I need, yes. My issue with resizing is that my sample size for the neural network has centered images with plenty of space around, so I'm not sure how well it will classify letters that just take up the whole space. Not to mention when resizing thin letters like 'I' it spreads them way too much to the point that even I can't figure out what it is. I'll try the border approach that you mentioned and see if it works for me. – Megid May 09 '18 at 12:38
  • It is totally up to you. Hope you find the answer here. – Ishara Madhawa May 09 '18 at 12:44
  • Yeah, I think border is the way to go. Thanks, I will accept your answer. – Megid May 09 '18 at 12:47