g-ocr.py

# import cv2 
# import pytesseract
# import numpy as np

# image = cv2.imread('rzse0mcqxbgs8z2pf6lr.png')

# def get_grayscale(image):
#     return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# def remove_noise(image):
#     return cv2.medianBlur(image,5)
 
# def thresholding(image):
#     return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]

# def dilate(image):
#     kernel = np.ones((5,5),np.uint8)
#     return cv2.dilate(image, kernel, iterations = 1)
    
# def erode(image):
#     kernel = np.ones((5,5),np.uint8)
#     return cv2.erode(image, kernel, iterations = 1)

# def opening(image):
#     kernel = np.ones((5,5),np.uint8)
#     return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)

# def canny(image):
#     return cv2.Canny(image, 100, 200)

# def deskew(image):
#     coords = np.column_stack(np.where(image > 0))
#     angle = cv2.minAreaRect(coords)[-1]
#     if angle < -45:
#         angle = -(90 + angle)
#     else:
#         angle = -angle
#     (h, w) = image.shape[:2]
#     center = (w // 2, h // 2)
#     M = cv2.getRotationMatrix2D(center, angle, 1.0)
#     rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
#     return rotated

# def match_template(image, template):
#     return cv2.matchTemplate(image, template, cv2.TM_CCOEFF_NORMED) 

# custom_config = r'--oem 3 --psm 6'
# pytesseract.image_to_string(image, config=custom_config)

# gray = get_grayscale(image)
# thresh = thresholding(gray)
# opening = opening(gray)
# canny = canny(gray)


# ocr = PaddleOCR(use_angle_cls=True, lang='en', use_pdserving=False, cls_batch_num=8, det_batch_num=8, rec_batch_num=8)

# ocr = PaddleOCR(use_angle_cls=True, lang='en')

# def index(url):
#     response = requests.get(url)
#     img = Image.open(BytesIO(response.content))
#     resize_factor = 1
#     new_size = tuple(int(dim * resize_factor) for dim in img.size)
#     img = img.resize(new_size, Image.Resampling.LANCZOS)

#     img_array = np.array(img.convert('RGB'))

#     result = ocr.ocr(img_array)

#     boxes = [line[0] for line in result]
#     txts = [line[1][0] for line in result]
#     scores = [line[1][1] for line in result]

#     print(boxes)
#     print(txts)

#     output_dict = {"texts": txts, "boxes": boxes, "scores": scores}
#     output_json = json.dumps(output_dict)  # Convert to JSON string

#     return output_json



import easyocr

image_url = 'https://res.cloudinary.com/ddvajyjou/image/upload/v1706960876/rzse0mcqxbgs8z2pf6lr.png'

reader = easyocr.Reader(['en'])
result = reader.readtext(image_url)

for (bbox, text, prob) in result:
    print(f'Text: {text}, Probability: {prob}')