How to improve text extraction from an image? - python

I am using pytesseract to extract text from images. Before extracting text with pytesseract, I use Pillow and cv2 to reduce noise and enhance the image:
import numpy as np
import pytesseract
from PIL import Image, ImageFilter, ImageEnhance
import cv2
img = cv2.imread('ss.png')
img = cv2.resize(img, (0,0), fx=3, fy=3)
cv2.imwrite("new.png", img)
img1 = cv2.imread("new.png", 0)
#Apply dilation and erosion
kernel = np.ones((2, 2), np.uint8)
img1 = cv2.dilate(img1, kernel, iterations=1)
img1 = cv2.erode(img1, kernel, iterations=1)
img1 = cv2.adaptiveThreshold(img1,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,11,2)
cv2.imwrite("new1.png", img1)
img2 = Image.open("new1.png")
#Enhance the image
img2 = im.filter(ImageFilter.MedianFilter())
enhancer = ImageEnhance.Contrast(im)
img2 = enhancer.enhance(2)
img2.save('new2.png')
result = pytesseract.image_to_string(Image.open("new2.png"))
print(result)
I mostly get good results, but when I use some low quality/resolution images, I do not get the expected output. Can I improve this in my code?
Example:
Input:
new1.png:
new2.png:
The string that I get from the console is play. What could I change in my algorithm, so that I get the whole string extracted?
Any help would be greatly appreciated.

This is a late answer, but I just came across this. we can use Pillow and cv2 to reduce noise and enhance the image before extracting text from images using pytesseract. I hope it would help someone in future.
#import required library
src_path = "C:/Users/chethan/Desktop/"
def get_string(img_path):
# Read image with opencv
img = cv2.imread(img_path)
# Convert to gray
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)
# Write image after removed noise
cv2.imwrite(src_path + "removed_noise.png", img)
# Apply threshold to get image with only black and white
#img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2)
# Write the image after apply opencv to do some ...
cv2.imwrite(src_path + "thres.png", img)
# Recognize text with tesseract for python
result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))
# Recognize text with tesseract for python
result = pytesseract.image_to_string(Image.open(img_path))
# Remove template file
# os.remove(temp)
return result
print(get_string(src_path + "dummy.png"))

Related

OCR not performing well on clean image | Python Pytesseract

I have been working on project which involves extracting text from an image. I have researched that tesseract is one of the best libraries available and I decided to use the same along with opencv. Opencv is needed for image manipulation.
I have been playing a lot with tessaract engine and it does not seems to be giving the expected results to me. I have attached the image as an reference. Output I got is:
1] =501 [
Instead, expected output is
TM10-50%L
What I have done so far:
Remove noise
Adaptive threshold
Sending it tesseract ocr engine
Are there any other suggestions to improve the algorithm?
Thanks in advance.
Snippet of the code:
import cv2
import sys
import pytesseract
import numpy as np
from PIL import Image
if __name__ == '__main__':
if len(sys.argv) < 2:
print('Usage: python ocr_simple.py image.jpg')
sys.exit(1)
# Read image path from command line
imPath = sys.argv[1]
gray = cv2.imread(imPath, 0)
# Blur
blur = cv2.GaussianBlur(gray,(9,9), 0)
# Binarizing
thres = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 5, 3)
text = pytesseract.image_to_string(thresh)
print(text)
Images attached.
First image is original image. Original image
Second image is what has been fed to tessaract. Input to tessaract
Before performing OCR on an image, it's important to preprocess the image. The idea is to obtain a processed image where the text to extract is in black with the background in white. For this specific image, we need to obtain the ROI before we can OCR.
To do this, we can convert to grayscale, apply a slight Gaussian blur, then adaptive threshold to obtain a binary image. From here, we can apply morphological closing to merge individual letters together. Next we find contours, filter using contour area filtering, and then extract the ROI. We perform text extraction using the --psm 6 configuration option to assume a single uniform block of text. Take a look here for more options.
Detected ROI
Extracted ROI
Result from Pytesseract OCR
TM10=50%L
Code
import cv2
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
# Grayscale, Gaussian blur, Adaptive threshold
image = cv2.imread('1.jpg')
original = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 5, 5)
# Perform morph close to merge letters together
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5,5))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=3)
# Find contours, contour area filtering, extract ROI
cnts, _ = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[-2:]
for c in cnts:
area = cv2.contourArea(c)
if area > 1800 and area < 2500:
x,y,w,h = cv2.boundingRect(c)
ROI = original[y:y+h, x:x+w]
cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 3)
# Perform text extraction
ROI = cv2.GaussianBlur(ROI, (3,3), 0)
data = pytesseract.image_to_string(ROI, lang='eng', config='--psm 6')
print(data)
cv2.imshow('ROI', ROI)
cv2.imshow('close', close)
cv2.imshow('image', image)
cv2.waitKey()

how to extract numbers from captcha image in python?

I want to extract numbers from captcha image, so I tried this code from this answer this answer:
try:
from PIL import Image
except ImportError:
import Image
import pytesseract
import cv2
file = 'sample.jpg'
img = cv2.imread(file, cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, None, fx=10, fy=10, interpolation=cv2.INTER_LINEAR)
img = cv2.medianBlur(img, 9)
th, img = cv2.threshold(img, 185, 255, cv2.THRESH_BINARY)
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (4,8))
img = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
cv2.imwrite("sample2.jpg", img)
file = 'sample2.jpg'
text = pytesseract.image_to_string(file)
print(''.join(x for x in text if x.isdigit()))
and it worked fine for this image: outPut: 436359 But, when I tried it on this image: It gave me nothing, outPut: .
How can I modify my code to get the numbers as a string from the second image?
EDIT:
I tried Matt's answer and it worked just fine for the image above. but it doesn't recognise numbers like (8,1) in image A, and number (7) in image B
image A
image B
How to fix that?
Often, getting OCR just right on an image like this has to do with the order and parameters of the transformations. For example, in the following code snippet, I first convert to grayscale, then erode the pixels, then dilate, then erode again. I use threshold to convert to binary (just blacks and whites) and then dilate and erode one more time. This for me produces the correct value of 859917 and should be reproducible.
import cv2
import numpy as np
import pytesseract
file = 'sample2.jpg'
img = cv2.imread(file)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ekernel = np.ones((1,2),np.uint8)
eroded = cv2.erode(gray, ekernel, iterations = 1)
dkernel = np.ones((2,3),np.uint8)
dilated_once = cv2.dilate(eroded, dkernel, iterations = 1)
ekernel = np.ones((2,2),np.uint8)
dilated_twice = cv2.erode(dilated_once, ekernel, iterations = 1)
th, threshed = cv2.threshold(dilated_twice, 200, 255, cv2.THRESH_BINARY)
dkernel = np.ones((2,2),np.uint8)
threshed_dilated = cv2.dilate(threshed, dkernel, iterations = 1)
ekernel = np.ones((2,2),np.uint8)
threshed_eroded = cv2.erode(threshed_dilated, ekernel, iterations = 1)
text = pytesseract.image_to_string(threshed_eroded)
print(''.join(x for x in text if x.isdigit()))

How to process and extract text from image

I'm trying to extract text from image using python cv2. The result is pathetic and I can't figure out a way to improve my code.
I believe the image needs to be processed before the extraction of text but not sure how.
I've tried to convert it into black and white but no luck.
import cv2
import os
import pytesseract
from PIL import Image
import time
pytesseract.pytesseract.tesseract_cmd='C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
cam = cv2.VideoCapture(1,cv2.CAP_DSHOW)
cam.set(cv2.CAP_PROP_FRAME_WIDTH, 8000)
cam.set(cv2.CAP_PROP_FRAME_HEIGHT, 6000)
while True:
return_value,image = cam.read()
image=cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
image = image[127:219, 508:722]
#(thresh, image) = cv2.threshold(image, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
cv2.imwrite('test.jpg',image)
print('Text detected: {}'.format(pytesseract.image_to_string(Image.open('test.jpg'))))
time.sleep(2)
cam.release()
#os.system('del test.jpg')
Preprocessing to clean the image before performing text extraction can help. Here's a simple approach
Convert image to grayscale and sharpen image
Adaptive threshold
Perform morpholgical operations to clean image
Invert image
First we convert to grayscale then sharpen the image using a sharpening kernel
Next we adaptive threshold to obtain a binary image
Now we perform morphological transformations to smooth the image
Finally we invert the image
import cv2
import numpy as np
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
sharpen_kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
sharpen = cv2.filter2D(gray, -1, sharpen_kernel)
thresh = cv2.threshold(sharpen, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=1)
result = 255 - close
cv2.imshow('sharpen', sharpen)
cv2.imshow('thresh', thresh)
cv2.imshow('close', close)
cv2.imshow('result', result)
cv2.waitKey()

No result when reading an image for Handwritten Recognition using tesseract

Currently I'm trying to implement a handwritten recognition program that will identify A,B,C,D, & E and numbers from 1-100. what I tried so far is using PyTesseract. I had made a simple pytesseract code with this one
import cv2
import numpy as np
import pytesseract
from PIL import Image
from pytesseract import image_to_string
src_path = "test-img/"
def get_string(img_path):
img = cv2.imread(img_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)
cv2.imwrite(src_path + "sample.jpg", img)
cv2.imwrite(src_path + "thres.png", img)
result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))
return result
print(get_string(src_path + "n.jpg") )
However, whenever I tried running the program. I don't get any result at all.
Can Someone help me with this one. Is there any alternative and easier way to implement handwritten recognition using python? Thank you
Sample image to detect

expected string or Unicode object, Photo found in django

here i want to read the image from db and apply some operations on my image like noise remove .... and finally i will appy pytesseract to get the text
def GetData(request):
img = Photo.objects.get(id=1)
#wrapper = FileWrapper(open(img.file))
# Read image with opencv
img = cv2.imread(img)
# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)
b,g,r = cv2.split(img)
# get b,g,r
rgb_img = cv2.merge([r,g,b])
# switch it to rgb
# Denoising
dst = cv2.fastNlMeansDenoisingColored(img,None,10,10,7,21)
img = cv2.cvtColor(dst, cv2.COLOR_BGR2GRAY)
# Apply threshold to get image with only black and white
img = cv2.adaptiveThreshold(img, 127, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11,2)
new_image = cv2.blur(img, (1, 1))
The error comes from cv2.imread(img) because imread take a string or unicode parameter with the URI of the image, but you are using a Django model class which is quite different.
Assuming that your Photo class model has an ImageField field named image you could fix your issue changing
img = cv2.imread(img)
to something like
img = cv2.imread(img.image.url)

Categories