app.py

import fitz  # PyMuPDF
from PIL import Image
import os
from itertools import islice
from collections import namedtuple
import pytesseract
import argparse
import imutils
import cv2
import shutil
import os
import numpy as np
import gradio as gr


def align_images(image, template, maxFeatures=500, keepPercent=0.2,debug=False):
	# convert both the input image and template to grayscale
  imageGray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
  templateGray = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
  orb = cv2.ORB_create(maxFeatures)
  (kpsA, descsA) = orb.detectAndCompute(imageGray, None)
  (kpsB, descsB) = orb.detectAndCompute(templateGray, None)
	# match the features
  method = cv2.DESCRIPTOR_MATCHER_BRUTEFORCE_HAMMING
  matcher = cv2.DescriptorMatcher_create(method)
  matches = matcher.match(descsA, descsB, None)
  matches = sorted(matches, key=lambda x:x.distance)
	# keep only the top matches
  keep = int(len(matches) * keepPercent)
  matches = matches[:keep]
	# check to see if we should visualize the matched keypoints
  if debug:
    matchedVis = cv2.drawMatches(image, kpsA, template, kpsB,matches, None)
    matchedVis = imutils.resize(matchedVis, width=1000)
    cv2_imshow(matchedVis)
    cv2.waitKey(0)
    # allocate memory for the keypoints (x, y)-coordinates from the
	# top matches -- we'll use these coordinates to compute our
	# homography matrix
  ptsA = np.zeros((len(matches), 2), dtype="float")
  ptsB = np.zeros((len(matches), 2), dtype="float")
	# loop over the top matches
  for (i, m) in enumerate(matches):
		# indicate that the two keypoints in the respective images
		# map to each other
    ptsA[i] = kpsA[m.queryIdx].pt
    ptsB[i] = kpsB[m.trainIdx].pt
    # compute the homography matrix between the two sets of matched
	# points
  (H, mask) = cv2.findHomography(ptsA, ptsB, method=cv2.RANSAC)
	# use the homography matrix to align the images
  (h, w) = template.shape[:2]
  aligned = cv2.warpPerspective(image, H, (w, h))
	# return the aligned image
  return aligned

def cleanup_text(text):
	return "".join([c if ord(c) < 128 else "" for c in text]).strip()




def detectarCatastro(pdf):
    if pdf.endswith(".pdf"):
        images = []
        pdf =  fitz.open(pdf)
        # Iterar sobre cada página del PDF
        for page_num in range(len(pdf)):
            page = pdf.load_page(page_num)
            pix = page.get_pixmap()
            
          
            img_array = np.frombuffer(pix.samples, dtype=np.uint8)
            
           
            if pix.alpha:
                img_array = img_array.reshape((pix.height, pix.width, 4))
            else:
                img_array = img_array.reshape((pix.height, pix.width, 3))
            
       
            images.append(img_array)


        aligned_images = []
        template = cv2.imread('alignImage1.png')
        aligned_image = align_images(images[0], template, debug=True)
        aligned_images.append(aligned_image)

        template = cv2.imread('alignImage2.png')
        aligned_image = align_images(images[1], template, debug=True)
        aligned_images.append(aligned_image)

        filtered_image = cv2.bilateralFilter(aligned_images[0], 9, 75, 75)
        
        alignedImage = filtered_image
        alignedImage = cv2.resize(alignedImage, None, fx=1, fy=1, interpolation=cv2.INTER_LINEAR)

        OCRLocation = namedtuple("OCRLocation", ["id", "bbox", "filter_keywords"])

        OCR_LOCATIONS = [
            OCRLocation("Numero de la parcela", (385, 33, 225, 20), ["numero", "de", "la", "parcela"]),
        ]
        
        mostrar = "Numero de la parcela: "
        
        for loc in OCR_LOCATIONS:
            (x, y, w, h) = loc.bbox
            roi = alignedImage[y:y + h, x:x + w]
        
            rgb = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
            text = pytesseract.image_to_string(rgb)

        mostrar = mostrar + text + " | Cultivos: "


        filtered_image = cv2.bilateralFilter(aligned_images[1], 9, 75, 75)
        
        alignedImage = filtered_image
        alignedImage = cv2.resize(alignedImage, None, fx=1, fy=1, interpolation=cv2.INTER_LINEAR)
        
     
        

        OCR_LOCATIONS = [
            OCRLocation("Cultivos", (75, 58, 180, 190), ["cultivos", "y", "aprovechamientos"]),
        ]
        

        
        
        for loc in OCR_LOCATIONS:
         
            (x, y, w, h) = loc.bbox
            roi = alignedImage[y:y + h, x:x + w]
            
            rgb = cv2.cvtColor(roi, cv2.COLOR_BGR2RGB)
            text = pytesseract.image_to_string(rgb)
        mostrar = mostrar + text

        return mostrar


pdf = gr.File(label="Input PDF", value="ejemplo.pdf")
method = gr.Radio(["PaddleOCR","EasyOCR", "KerasOCR"],value="PaddleOCR")
output = gr.Textbox(label="Output")

demo = gr.Interface(
    detectarCatastro,
    [pdf],
    output,
    title="DetectorCatastro",
    css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
    article = """<p style='text-align: center;'>Feel free to give us your thoughts on this demo and please contact us at 
                    <a href="mailto:[email protected]" target="_blank">[email protected]</a> 
                    <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com/" target="_blank">Pragnakalp Techlabs</a></p>"""


)
demo.launch()