Update app.py

app.py

@@ -7,22 +7,26 @@ import gradio as gr
 from ultralytics import YOLO
 from paddleocr import PaddleOCR
 
-# 1) Load models
+# ─── 1) Load models ───────────────────────────────────────────────
 yolo = YOLO("models/best.pt")
-ocr  = PaddleOCR(
-    text_detection_model_dir=None,
-    text_recognition_model_dir="models/ocr_model",
-    use_textline_orientation=False,
-    lang="en"
+
+# Use recognition‐only mode (no detector), with angle‐cls to handle simple flips
+ocr = PaddleOCR(
+    det=False,               # skip built‐in detection
+    rec=True,                # enable recognition
+    rec_model_dir="models/ocr_model",
+    cls=True,                # turn on angle classification
+    use_angle_cls=True,      # v2.x flag
+    lang="en"                # our char dict is basic Latin+digits
 )
 
-# 2) Turkish plate formatter
+# ─── 2) Turkish plate formatter ────────────────────────────────────
 def format_turkish_plate(s: str) -> str:
     s = re.sub(r'[^A-Z0-9]', '', s.upper())
     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"
 
-# 3) Single‐image inference
+# ─── 3) Single‐image inference ─────────────────────────────────────
 def run_image(img, conf=0.25):
     bgr = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
     res = yolo(bgr, conf=conf)[0]
@@ -32,10 +36,12 @@ def run_image(img, conf=0.25):
                                res.boxes.conf.cpu().numpy()):
         x1,y1,x2,y2 = box.astype(int)
         crop = out[y1:y2, x1:x2]
-        if crop.size==0: continue
+        if crop.size == 0:
+            continue
 
         plate_img = cv2.resize(crop, (128,32))
-        recs = ocr.ocr(plate_img, cls=False)
+        # explicitly tell PaddleOCR: skip detection here
+        recs = ocr.ocr(plate_img, det=False, cls=False)
 
         if recs and recs[0]:
             _, (raw, ocr_score) = recs[0]
@@ -51,7 +57,7 @@ def run_image(img, conf=0.25):
 
     return cv2.cvtColor(out, cv2.COLOR_BGR2RGB), f"{len(res.boxes)} plate(s) detected"
 
-# 4) Video inference (same pattern)
+# ─── 4) Video inference (same pattern) ───────────────────────────
 def run_video(video_file, conf=0.25):
     cap = cv2.VideoCapture(video_file)
     fps = cap.get(cv2.CAP_PROP_FPS)
@@ -62,16 +68,19 @@ def run_video(video_file, conf=0.25):
 
     while True:
         ret, frame = cap.read()
-        if not ret: break
+        if not ret:
+            break
         idx += 1
         t = idx / fps
 
         res = yolo(frame, conf=conf)[0]
         for (x1,y1,x2,y2) in res.boxes.xyxy.cpu().numpy().astype(int):
             crop = frame[y1:y2, x1:x2]
-            if crop.size==0: continue
+            if crop.size == 0:
+                continue
+
             plate_img = cv2.resize(crop, (128,32))
-            recs = ocr.ocr(plate_img, cls=False)
+            recs = ocr.ocr(plate_img, det=False, cls=False)
 
             if recs and recs[0]:
                 _, (raw, ocr_score) = recs[0]
@@ -88,25 +97,26 @@ def run_video(video_file, conf=0.25):
 
         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 outfp
 
-# 5) Gradio UI
+# ─── 5) 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")
-            vid_in = gr.File(label="Video (.mp4)")
-            conf   = gr.Slider(0,1,0.25,0.01)
+            img_in = gr.Image(type="numpy", label="Upload Image")
+            vid_in = gr.File(label="Upload Video (.mp4)")
+            conf   = gr.Slider(0,1,0.25,0.01, label="YOLO Confidence")
             b1     = gr.Button("Run Image")
             b2     = gr.Button("Run Video")
         with gr.Column():
-            img_out = gr.Image(type="numpy")
-            vid_out = gr.Video()
-            status  = gr.Textbox()
+            img_out = gr.Image(type="numpy", label="Annotated Image")
+            vid_out = gr.Video(label="Annotated Video")
+            status  = gr.Textbox(label="Status / JSON Path")
 
     b1.click(run_image, [img_in,conf], [img_out,status])
     b2.click(run_video, [vid_in,conf], [vid_out,status])