Get the location of all text present in image using opencv

Here's a potential approach using morphological operations to filter out non-text contours. The idea is:

1. Obtain binary image. Load image, grayscale, then Otsu's threshold

2. Remove horizontal and vertical lines. Create horizontal and vertical kernels using cv2.getStructuringElement then remove lines with cv2.drawContours

3. Remove diagonal lines, circle objects, and curved contours. Filter using contour area cv2.contourArea and contour approximation cv2.approxPolyDP to isolate non-text contours

4. Extract text ROIs and OCR. Find contours and filter for ROIs then OCR using Pytesseract.

Removed horizontal lines highlighted in green

Removed vertical lines

Removed assorted non-text contours (diagonal lines, circular objects, and curves)

Detected text regions

import cv2
import numpy as np
import pytesseract

pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"

# Load image, grayscale, Otsu's threshold
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
clean = thresh.copy()

# Remove horizontal lines
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (15,1))
detect_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
cnts = cv2.findContours(detect_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(clean, [c], -1, 0, 3)

# Remove vertical lines
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,30))
detect_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
cnts = cv2.findContours(detect_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(clean, [c], -1, 0, 3)

cnts = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    # Remove diagonal lines
    area = cv2.contourArea(c)
    if area < 100:
        cv2.drawContours(clean, [c], -1, 0, 3)
    # Remove circle objects
    elif area > 1000:
        cv2.drawContours(clean, [c], -1, 0, -1)
    # Remove curve stuff
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.02 * peri, True)
    x,y,w,h = cv2.boundingRect(c)
    if len(approx) == 4:
        cv2.rectangle(clean, (x, y), (x + w, y + h), 0, -1)

open_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2,2))
opening = cv2.morphologyEx(clean, cv2.MORPH_OPEN, open_kernel, iterations=2)
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,2))
close = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, close_kernel, iterations=4)
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    area = cv2.contourArea(c)
    if area > 500:
        ROI = image[y:y+h, x:x+w]
        ROI = cv2.GaussianBlur(ROI, (3,3), 0)
        data = pytesseract.image_to_string(ROI, lang='eng',config='--psm 6')
        if data.isalnum():
            cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
            print(data)

cv2.imwrite('image.png', image)
cv2.imwrite('clean.png', clean)
cv2.imwrite('close.png', close)
cv2.imwrite('opening.png', opening)
cv2.waitKey()