我正在做一个读身份证的OCR。在通过使用YOLO获得感兴趣区域之后,我将该裁剪区域交给Tesseract阅读。由于这些裁剪的图像非常小而且模糊,Tesseract无法阅读它们。当它能读懂它们时,它就会给出错误的预测。笔者认为,通过提高裁剪图像的图像质量,可以解决这些问题。
其中一幅剪裁的图片:
我的问题是,我如何改善这些图像?
发布于 2018-08-24 14:33:34
“vasilisg”的答案。是个很好的解决办法。一种进一步改进的方法是使用形态学开放手术来去除剩余的斑点。但是,这只适用于比图像中数字的直线度更小的点。另一种选择是使用openCV连接组件模块删除小于N个像素的“孤岛”。例如,您可以这样做:
# External libraries used for
# Image IO
from PIL import Image
# Morphological filtering
from skimage.morphology import opening
from skimage.morphology import disk
# Data handling
import numpy as np
# Connected component filtering
import cv2
black = 0
white = 255
threshold = 160
# Open input image in grayscale mode and get its pixels.
img = Image.open("image.jpg").convert("LA")
pixels = np.array(img)[:,:,0]
# Remove pixels above threshold
pixels[pixels > threshold] = white
pixels[pixels < threshold] = black
# Morphological opening
blobSize = 1 # Select the maximum radius of the blobs you would like to remove
structureElement = disk(blobSize) # you can define different shapes, here we take a disk shape
# We need to invert the image such that black is background and white foreground to perform the opening
pixels = np.invert(opening(np.invert(pixels), structureElement))
# Create and save new image.
newImg = Image.fromarray(pixels).convert('RGB')
newImg.save("newImage1.PNG")
# Find the connected components (black objects in your image)
# Because the function searches for white connected components on a black background, we need to invert the image
nb_components, output, stats, centroids = cv2.connectedComponentsWithStats(np.invert(pixels), connectivity=8)
# For every connected component in your image, you can obtain the number of pixels from the stats variable in the last
# column. We remove the first entry from sizes, because this is the entry of the background connected component
sizes = stats[1:,-1]
nb_components -= 1
# Define the minimum size (number of pixels) a component should consist of
minimum_size = 100
# Create a new image
newPixels = np.ones(pixels.shape)*255
# Iterate over all components in the image, only keep the components larger than minimum size
for i in range(1, nb_components):
if sizes[i] > minimum_size:
newPixels[output == i+1] = 0
# Create and save new image.
newImg = Image.fromarray(newPixels).convert('RGB')
newImg.save("newImage2.PNG")
在本例中,我同时执行了开始和连接组件方法,但是如果使用连接组件方法,通常可以省略开始操作。
结果如下:
脱粒和开场后:
经过阈值化、开启和连接后的组件过滤:
发布于 2018-08-24 12:35:41
一种方法是将图像转换为灰度,然后使用一个阈值与每个像素进行比较,以决定它应该是黑色还是白色。枕头是一个库,可以用于这种类型的处理:
from PIL import Image
black = (0,0,0)
white = (255,255,255)
threshold = (160,160,160)
# Open input image in grayscale mode and get its pixels.
img = Image.open("image.jpg").convert("LA")
pixels = img.getdata()
newPixels = []
# Compare each pixel
for pixel in pixels:
if pixel < threshold:
newPixels.append(black)
else:
newPixels.append(white)
# Create and save new image.
newImg = Image.new("RGB",img.size)
newImg.putdata(newPixels)
newImg.save("newImage.jpg")
结果图像:
https://stackoverflow.com/questions/52004133
复制相似问题