app.py

import gradio as gr
import cv2
import easyocr
import numpy as np
import json

# OCR Process - Inisialisasi Reader EasyOCR
reader = easyocr.Reader(['id', 'en'])

def detect_and_warp_ktp(input_img):
    """
    Fungsi untuk mendeteksi tepi KTP, melakukan cropping, 
    dan meluruskan perspektif gambar secara otomatis.
    """
    clone = input_img.copy()
    gray = cv2.cvtColor(input_img, cv2.COLOR_RGB2GRAY)
    
    # Efek blur dan deteksi tepi untuk mengekstrak kontur kartu
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(blurred, 50, 200)
    
    # Contour Detection - Mencari 5 kontur terbesar (KTP biasanya berbentuk persegi panjang dominan)
    contours, _ = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    contours = sorted(contours, key=cv2.contourArea, reverse=True)[:5]
    
    ktp_contour = None
    for c in contours:
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)
        
        # Jika kontur memiliki tepat 4 titik sudut, asumsikan sebagai KTP
        if len(approx) == 4:
            ktp_contour = approx
            break
            
    # Perspective Warp - Jika kartu terdeteksi, lakukan transformasi perspektif (Pelurusan)
    if ktp_contour is not None:
        pts = ktp_contour.reshape(4, 2)
        rect = np.zeros((4, 2), dtype="float32")
        
        # Mengurutkan koordinat titik sudut
        s = pts.sum(axis=1)
        rect[0] = pts[np.argmin(s)]  # Top-left
        rect[2] = pts[np.argmax(s)]  # Bottom-right
        
        diff = np.diff(pts, axis=1)
        rect[1] = pts[np.argmin(diff)] # Top-right
        rect[3] = pts[np.argmax(diff)] # Bottom-left
        
        # Standarisasi ukuran dimensi hasil crop (Rasio KTP standard)
        width = 600
        height = 380
        
        dst = np.array([
            [0, 0],
            [width - 1, 0],
            [width - 1, height - 1],
            [0, height - 1]], dtype="float32")
        
        M = cv2.getPerspectiveTransform(rect, dst)
        warped = cv2.warpPerspective(clone, M, (width, height))
        return warped
        
    # Jika gagal mendeteksi kartu, kembalikan gambar asli
    return input_img

def process_ktp(input_img):
    if input_img is None:
        return None, "Mohon unggah gambar KTP."
            
    # TAHAP 1: Deteksi area kartu dan perbaikan perspektif secara dinamis
    img_cropped = detect_and_warp_ktp(input_img)
    
    # Standarisasi ukuran prapemrosesan akhir
    scale_percent = 150 
    width = int(img_cropped.shape[1] * scale_percent / 100)
    height = int(img_cropped.shape[0] * scale_percent / 100)
    img = cv2.resize(img_cropped, (width, height), interpolation=cv2.INTER_CUBIC)
            
    display_img = img.copy()
    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
            
    # TAHAP 2: Jalankan OCR pada gambar yang sudah bersih dan lurus
    ocr_results = reader.readtext(gray, detail=1, paragraph=False)
            
    extracted_data = {
        "NIK": "-",
        "Nama": "-",
        "Tempat/Tgl Lahir": "-"
    }
            
    # Toleransi piksel vertikal (Y) menjadi sangat konsisten pasca pelurusan
    y_tolerance = 25         
    
    # TAHAP 3: Proses Ekstraksi Dinamis Berdasarkan Kedekatan Koordinat
    for i, (bbox, text, prob) in enumerate(ocr_results):
        text_clean = text.upper().strip()
        (tl, tr, br, bl) = bbox                        
        key_y_center = (tl[1] + bl[1]) / 2
        key_x_max = tr[0]                        
        
        # --- DETEKSI NIK ---
        if "NIK" in text_clean:
            digits = ''.join(filter(str.isdigit, text_clean)) # Filtrasi Angka NIK
            if len(digits) >= 12:
                extracted_data["NIK"] = digits
            else:
                for sub_bbox, sub_text, _ in ocr_results:
                    sub_y_center = (sub_bbox[0][1] + sub_bbox[3][1]) / 2
                    if abs(sub_y_center - key_y_center) < y_tolerance and sub_bbox[0][0] > key_x_max:
                        sub_digits = ''.join(filter(str.isdigit, sub_text))
                        if len(sub_digits) >= 12:
                            extracted_data["NIK"] = sub_digits
                            cv2.rectangle(display_img, (int(sub_bbox[0][0]), int(sub_bbox[0][1])), (int(sub_bbox[2][0]), int(sub_bbox[2][1])), (0, 255, 0), 2)
                
        # --- DETEKSI NAMA ---
        elif "NAMA" in text_clean and not "IBU" in text_clean:
            for sub_bbox, sub_text, _ in ocr_results:
                sub_y_center = (sub_bbox[0][1] + sub_bbox[3][1]) / 2
                if abs(sub_y_center - key_y_center) < y_tolerance and sub_bbox[0][0] > key_x_max:
                    extracted_data["Nama"] = sub_text.replace(":", "").strip()
                    cv2.rectangle(display_img, (int(sub_bbox[0][0]), int(sub_bbox[0][1])), (int(sub_bbox[2][0]), int(sub_bbox[2][1])), (0, 255, 0), 2)
                
        # --- DETEKSI TEMPAT/TGL LAHIR ---
        elif "TEMPAT" in text_clean or "LAHIR" in text_clean or "TGL" in text_clean:
            ttl_parts = []
            for sub_bbox, sub_text, _ in ocr_results:
                sub_y_center = (sub_bbox[0][1] + sub_bbox[3][1]) / 2
                if abs(sub_y_center - key_y_center) < y_tolerance and sub_bbox[0][0] > key_x_max:
                    clean_part = sub_text.replace(":", "").strip() # Cleaning Text
                    if clean_part and clean_part not in ttl_parts:
                        ttl_parts.append(clean_part)
                        cv2.rectangle(display_img, (int(sub_bbox[0][0]), int(sub_bbox[0][1])), (int(sub_bbox[2][0]), int(sub_bbox[2][1])), (0, 255, 0), 2)
                        
            if ttl_parts:
                extracted_data["Tempat/Tgl Lahir"] = " ".join(ttl_parts)
                
    # TAHAP 4: Post-Processing & Pembersihan Simbol Sisa
    final_json_dict = {}
    for key, val in extracted_data.items():
        if val.startswith(":") or val.startswith("."):
            val = val[1:].strip()
                    
        # Mapping nama key menjadi lowercase untuk standarisasi JSON API
        if key == "NIK":
            final_json_dict["nik"] = val
        elif key == "Nama":
            final_json_dict["nama"] = val
        elif key == "Tempat/Tgl Lahir":
            final_json_dict["tempat_tgl_lahir"] = val
            
    # TAHAP 5: Konversi Dictionary ke Format Valid String JSON dengan Indentasi 4 Spasi
    json_output_string = json.dumps(final_json_dict, indent=4, ensure_ascii=False)
                
    return display_img, json_output_string

# --- ANTARMUKA GRADIO ---
with gr.Blocks(title="KTP Indonesia OCR Scanner") as demo:
    gr.Markdown("# 🪪 Indonesia ID Card (KTP) OCR Scanner")
    gr.Markdown("Aplikasi menggunakan EasyOCR dengan Deteksi Area Otomatis & Luaran Berformat JSON Standardized.")
            
    with gr.Row():
        with gr.Column():
            # MENAMBAHKAN parameter height agar ukuran kotak unggah terkunci (tidak melar)
            input_image = gr.Image(label="Unggah Foto KTP", height=350)
            btn = gr.Button("Ekstrak Data", variant="primary")
                            
        with gr.Column():
            # MENAMBAHKAN parameter height yang sama agar visualisasi hasil simetris
            output_image = gr.Image(label="Visualisasi Hasil Scan", height=350)
            # Mengunci jumlah baris tampilan agar layout tidak melompat saat teks JSON masuk
            output_results = gr.Textbox(label="Data Terdeteksi (JSON format)", lines=10, max_lines=10)
                    
    btn.click(fn=process_ktp, inputs=input_image, outputs=[output_image, output_results])

if __name__ == "__main__":
    demo.launch()