Ptesa

[dkingfarhan88]

pip install pytesseract pillow opencv-python

import pytesseract
from PIL import Image
import cv2
import json
import os

Optional: If Tesseract is not in PATH (Windows example)

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

def ocr_to_json(image_path, output_json="output.json"):
# Load image using OpenCV
image = cv2.imread(image_path)

# Convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Optional: Apply thresholding to improve accuracy
_, thresh = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)

# Extract OCR data (word-level with bounding boxes)
data = pytesseract.image_to_data(thresh, output_type=pytesseract.Output.DICT)

results = []

for i in range(len(data['text'])):
    word = data['text'][i].strip()
    if word != "":
        results.append({
            "text": word,
            "confidence": data['conf'][i],
            "bounding_box": {
                "x": data['left'][i],
                "y": data['top'][i],
                "width": data['width'][i],
                "height": data['height'][i]
            }
        })

final_output = {
    "file_name": os.path.basename(image_path),
    "total_words": len(results),
    "extracted_data": results
}

with open(output_json, "w", encoding="utf-8") as f:
    json.dump(final_output, f, indent=4)

return final_output

Example usage

if name == "main":
result = ocr_to_json("sample_image.jpg")
print(json.dumps(result, indent=4))

{
"file_name": "sample_image.jpg",
"total_words": 3,
"extracted_data": [
{
"text": "Invoice",
"confidence": "96",
"bounding_box": {
"x": 100,
"y": 50,
"width": 120,
"height": 30
}
}
]
}

def simple_ocr_json(image_path):
text = pytesseract.image_to_string(Image.open(image_path))

return {
    "file": image_path,
    "text": text.strip(),
    "lines": text.strip().split("\n")
}

pytesseract.image_to_string(img, lang='eng+ben')

pip install pytesseract pillow opencv-python easyocr paddleocr flask fastapi uvicorn python-multipart

import pytesseract
import cv2
import json
from pytesseract import Output

def basic_ocr_to_json(image_path):
img = cv2.imread(image_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

data = pytesseract.image_to_data(gray, output_type=Output.DICT)

words = []
for i in range(len(data['text'])):
    if data['text'][i].strip() != "":
        words.append({
            "text": data['text'][i],
            "confidence": data['conf'][i],
            "box": {
                "x": data['left'][i],
                "y": data['top'][i],
                "w": data['width'][i],
                "h": data['height'][i]
            }
        })

return {"total_words": len(words), "words": words}

def advanced_preprocess(image_path):
img = cv2.imread(image_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (5,5), 0)
thresh = cv2.adaptiveThreshold(
blur, 255,
cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY,
11, 2
)

text = pytesseract.image_to_string(thresh)
return {"clean_text": text}

def bengali_english_ocr(image_path):
img = cv2.imread(image_path)
text = pytesseract.image_to_string(img, lang='eng+ben')
return {"text": text}

import easyocr

def easyocr_json(image_path):
reader = easyocr.Reader(['en','bn'])
results = reader.readtext(image_path)

data = []
for bbox, text, conf in results:
    data.append({
        "text": text,
        "confidence": conf,
        "bounding_box": bbox
    })

return {"results": data}

from paddleocr import PaddleOCR

def paddle_ocr_json(image_path):
ocr = PaddleOCR(lang='en')
result = ocr.ocr(image_path)

data = []
for line in result[0]:
    data.append({
        "text": line[1][0],
        "confidence": line[1][1],
        "bounding_box": line[0]
    })

return {"results": data}

from flask import Flask, request, jsonify
import os

app = Flask(name)

@app.route("/ocr", methods=["POST"])
def ocr_api():