Update app.py

app.py

@@ -1,7 +1,5 @@
 # app.py
-import re
-import json
-import tempfile
+import re, json, tempfile
 import cv2
 import numpy as np
 import gradio as gr
@@ -17,125 +15,130 @@ CHAR_LIST = list("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ ")
 # ─── 2) Load YOLOv8 detector
 yolo = YOLO("models/best.pt")
 
-# ─── 3) Init PaddleOCR recognition-only
+# ─── 3) Init PaddleOCR recognition-only, override ALL params in-code
 ocr = PaddleOCR(
-    det=False,                   # sadece rec
-    rec=True,
+    det=False,                   # disable det on plate crops
+    rec=True,                    # recognition-only
     rec_model_dir="models/ocr_model",
-    rec_image_shape="3,32,128",  # eğitimde kullandığın input boyutu
-    cls=True,
+    rec_image_shape="3,32,128",  # must match your training
+    cls=True,                    # angle classifier
     use_angle_cls=True,
     use_space_char=True
 )
-ocr.text_recognizer.character = CHAR_LIST  # kendi karakter kümen
+# Force our exact char map (no dict file needed)
+ocr.text_recognizer.character = CHAR_LIST
 
-# ─── 4) OCR çıktısını normalize eden fonksiyon
+# ─── 4) Normalize & format OCR output
 def normalize_ocr(recs):
+    """
+    recs might be:
+      - []                                    → no read
+      - [["ABC123", 0.82]]                    → default det=False
+      - [["ABC123", 0.82], ...]               → (unlikely here)
+      - [[box,…], ("ABC123",0.82)]            → old det=True style
+    return text:str, score:float
+    """
     if not recs:
         return "", 0.0
     first = recs[0]
-    # ["TEXT", score]
+    # case: ["TXT",score]
     if isinstance(first, (list,tuple)) and len(first)==2 and isinstance(first[0], str):
         return first[0], float(first[1])
-    # [box, ("TEXT",score)] veya [box, ["TEXT",score]]
+    # case: [<box>, (<txt>,score)] or [<box>, [txt,score]]
     if isinstance(first, (list,tuple)) and len(first)==2 and isinstance(first[1], (list,tuple)):
         return first[1][0], float(first[1][1])
     return "", 0.0
 
-# ─── 5) Türk plaka formatlayıcı (gevşetilmiş son grup)
 def format_plate(s: str) -> str:
+    """‘DD AAA DDDD’  veya Unknown"""
     s = re.sub(r'[^A-Z0-9]', '', s.upper())
-    # son grup artık harf veya rakamı da kabul ediyor
-    m = re.match(r'^(\d{2})([A-Z]{1,3})([A-Z0-9]{2,4})$', s)
+    m = re.match(r'^(\d{2})([A-Z]{1,3})(\d{2,4})$', s)
     return f"{m.group(1)} {m.group(2)} {m.group(3)}" if m else "Unknown"
 
-# ─── 6) Tek resim için inference
+# ─── 5) Single-image inference
 def run_image(img, conf=0.25):
+    # YOLO wants BGR
     bgr = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
     res = yolo(bgr, conf=conf)[0]
     out = bgr.copy()
 
-    # YOLO'nun bulduğu tüm kutuları al, en büyüğünü seç
-    boxes = res.boxes.xyxy.cpu().numpy().astype(int)
-    if boxes.shape[0] > 0:
-        areas = (boxes[:,2] - boxes[:,0]) * (boxes[:,3] - boxes[:,1])
-        i = int(np.argmax(areas))
-        x1,y1,x2,y2 = boxes[i]
+    for box in res.boxes.xyxy.cpu().numpy().astype(int):
+        x1,y1,x2,y2 = box
         crop = out[y1:y2, x1:x2]
-
-        if crop.size > 0:
-            plate_img = cv2.resize(crop, (128,32))
-            try:
-                recs = ocr.ocr(plate_img, det=False, cls=True)
-            except Exception:
-                recs = []
-            txt, score = normalize_ocr(recs)
-            plate = format_plate(txt)
-            label = f"{plate} ({score:.2f})"
-
-            cv2.rectangle(out, (x1,y1),(x2,y2), (0,255,0), 2)
-            cv2.putText(out, label, (x1, y1-8),
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
-
-    return cv2.cvtColor(out, cv2.COLOR_BGR2RGB), f"{len(boxes)} plate(s) detected"
-
-# ─── 7) Video için inference (aynı “en büyük kutu” mantığı)
+        if crop.size == 0:
+            continue
+
+        # resize to OCR input
+        plate_img = cv2.resize(crop, (128,32))
+        # safe OCR
+        try:
+            recs = ocr.ocr(plate_img, det=False, cls=True)
+        except Exception:
+            recs = []
+        txt, score = normalize_ocr(recs)
+        plate = format_plate(txt)
+        label = f"{plate} ({score:.2f})"
+
+        # draw
+        cv2.rectangle(out, (x1,y1),(x2,y2), (0,255,0), 2)
+        cv2.putText(out, label, (x1, y1-8),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
+
+    return cv2.cvtColor(out, cv2.COLOR_BGR2RGB), f"{len(res.boxes)} plate(s) detected"
+
+# ─── 6) Video inference
 def run_video(video_file, conf=0.25):
     cap = cv2.VideoCapture(video_file)
     fps = cap.get(cv2.CAP_PROP_FPS) or 30
     w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
     h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
     out_path = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
     writer = cv2.VideoWriter(out_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w,h))
+    records, idx = [], 0
 
-    records = []
-    idx = 0
     while True:
         ret, frame = cap.read()
         if not ret: break
-        idx += 1; t = idx / fps
+        idx += 1; t = idx/fps
 
         res = yolo(frame, conf=conf)[0]
-        boxes = res.boxes.xyxy.cpu().numpy().astype(int)
-        if boxes.shape[0] > 0:
-            areas = (boxes[:,2] - boxes[:,0]) * (boxes[:,3] - boxes[:,1])
-            i = int(np.argmax(areas))
-            x1,y1,x2,y2 = boxes[i]
+        for box in res.boxes.xyxy.cpu().numpy().astype(int):
+            x1,y1,x2,y2 = box
             crop = frame[y1:y2, x1:x2]
-            if crop.size > 0:
-                plate_img = cv2.resize(crop, (128,32))
-                try:
-                    recs = ocr.ocr(plate_img, det=False, cls=True)
-                except:
-                    recs = []
-                txt, score = normalize_ocr(recs)
-                plate = format_plate(txt)
-                if plate != "Unknown":
-                    records.append({
-                        "time_s": round(t,2),
-                        "plate": plate,
-                        "conf": round(score,3)
-                    })
-                cv2.rectangle(frame, (x1,y1),(x2,y2), (0,255,0), 2)
-                cv2.putText(frame, plate, (x1, y1-8),
-                            cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
+            if crop.size == 0: continue
+
+            plate_img = cv2.resize(crop, (128,32))
+            try:
+                recs = ocr.ocr(plate_img, det=False, cls=True)
+            except:
+                recs = []
+            txt, score = normalize_ocr(recs)
+            plate = format_plate(txt)
+
+            if plate != "Unknown":
+                records.append({"time_s":round(t,2),"plate":plate,"conf":round(score,3)})
+
+            cv2.rectangle(frame, (x1,y1),(x2,y2), (0,255,0), 2)
+            cv2.putText(frame, plate, (x1, y1-8),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0,255,0), 2)
 
         writer.write(frame)
 
-    cap.release()
-    writer.release()
+    cap.release(); writer.release()
     with open("output.json","w") as f:
         json.dump(records, f, indent=2)
     return out_path, "Done"
 
-# ─── 8) Gradio UI ────────────────────────────────────────────────
+# ─── 7) Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("## 🚗 License Plate Detection + Recognition")
+
     with gr.Row():
         with gr.Column():
             img_in = gr.Image(type="numpy", label="Upload Image")
             vid_in = gr.File(label="Upload Video (.mp4)")
-            conf   = gr.Slider(0.0, 1.0, 0.25, 0.01, label="YOLO Confidence")
+            conf   = gr.Slider(0.0,1.0,0.25,0.01, label="YOLO Confidence")
             btn_i  = gr.Button("Run Image")
             btn_v  = gr.Button("Run Video")
         with gr.Column():
@@ -143,8 +146,8 @@ with gr.Blocks() as demo:
             vid_out = gr.Video(label="Annotated Video")
             status  = gr.Textbox(label="Status / JSON Path")
 
-    btn_i.click(run_image, [img_in, conf], [img_out, status])
-    btn_v.click(run_video, [vid_in, conf], [vid_out, status])
-
+    btn_i.click(run_image, [img_in,conf], [img_out,status])
+    btn_v.click(run_video, [vid_in,conf], [vid_out,status])
+ 
 if __name__ == "__main__":
     demo.launch()