Update app.py

app.py

@@ -2,13 +2,15 @@ import cv2 as cv
 import numpy as np
 import gradio as gr
 from pathlib import Path
-from collections import Counter
+from collections import Counter, defaultdict
 from huggingface_hub import hf_hub_download
+import matplotlib.pyplot as plt
+import io
 
 from facial_fer_model import FacialExpressionRecog
 from yunet import YuNet
 
-# Download ONNX-modellen van Hugging Face
+# Download ONNX-modellen
 FD_MODEL_PATH = hf_hub_download(repo_id="opencv/face_detection_yunet", filename="face_detection_yunet_2023mar.onnx")
 FER_MODEL_PATH = hf_hub_download(repo_id="opencv/facial_expression_recognition", filename="facial_expression_recognition_mobilefacenet_2022july.onnx")
 
@@ -18,7 +20,7 @@ target_id = cv.dnn.DNN_TARGET_CPU
 fer_model = FacialExpressionRecog(modelPath=FER_MODEL_PATH, backendId=backend_id, targetId=target_id)
 detect_model = YuNet(modelPath=FD_MODEL_PATH)
 
-# === EN -> NL mapping van emotielabels ===
+# EN -> NL mapping
 EN_TO_NL = {
     "neutral": "Neutraal",
     "happy": "Blij",
@@ -36,120 +38,109 @@ def to_dutch(label: str) -> str:
     if not label:
         return "Onbekend"
     key = label.strip().lower()
-    return EN_TO_NL.get(key, label)  # fallback naar origineel indien onbekend
+    return EN_TO_NL.get(key, label)
+
+# Opslag voor statistieken
+emotion_stats = defaultdict(int)
 
 def visualize(image, det_res, fer_res):
     output = image.copy()
     landmark_color = [(255, 0, 0), (0, 0, 255), (0, 255, 0), (255, 0, 255), (0, 255, 255)]
-
     for det, fer_type in zip(det_res, fer_res):
         bbox = det[0:4].astype(np.int32)
-        fer_type_str_en = FacialExpressionRecog.getDesc(fer_type)
-        fer_type_str_nl = to_dutch(fer_type_str_en)
-
+        fer_type_str_nl = to_dutch(FacialExpressionRecog.getDesc(fer_type))
         cv.rectangle(output, (bbox[0], bbox[1]), (bbox[0]+bbox[2], bbox[1]+bbox[3]), (0, 255, 0), 2)
         cv.putText(output, fer_type_str_nl, (bbox[0], max(0, bbox[1] - 10)),
                    cv.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2, cv.LINE_AA)
-
         landmarks = det[4:14].astype(np.int32).reshape((5, 2))
         for idx, landmark in enumerate(landmarks):
             cv.circle(output, landmark, 2, landmark_color[idx], 2)
-
     return output
 
 def summarize_emotions(fer_res):
-    """
-    Maakt een Markdown-tekst met een grote, vetgedrukte samenvatting (NL).
-    Bij meerdere gezichten wordt de meest voorkomende emotie uitgelicht.
-    """
     if not fer_res:
         return "## **Geen gezicht gedetecteerd**"
-
-    names_en = [FacialExpressionRecog.getDesc(x) for x in fer_res]
-    names_nl = [to_dutch(n) for n in names_en]
+    names_nl = [to_dutch(FacialExpressionRecog.getDesc(x)) for x in fer_res]
     counts = Counter(names_nl).most_common()
-    top, top_n = counts[0]
+    top = counts[0][0]
     details = ", ".join([f"{name} ({n})" for name, n in counts])
-
-    # Grote headline + toelichting (kleur regelen we via CSS)
     return f"# **{top}**\n\n_Gedetecteerde emoties: {details}_"
 
+def update_stats_and_plot(names_nl):
+    for name in names_nl:
+        emotion_stats[name] += 1
+    # Maak plot
+    fig, ax = plt.subplots()
+    labels = list(emotion_stats.keys())
+    values = [emotion_stats[k] for k in labels]
+    ax.bar(labels, values)
+    ax.set_ylabel("Aantal keer gedetecteerd")
+    ax.set_title("Live emotie-statistieken")
+    plt.xticks(rotation=45)
+    buf = io.BytesIO()
+    plt.tight_layout()
+    fig.savefig(buf, format="png")
+    plt.close(fig)
+    buf.seek(0)
+    return buf
+
 def detect_expression(input_image):
     image = cv.cvtColor(input_image, cv.COLOR_RGB2BGR)
     h, w, _ = image.shape
     detect_model.setInputSize([w, h])
-
     dets = detect_model.infer(image)
     if dets is None:
         emotion_md = summarize_emotions([])
-        return cv.cvtColor(image, cv.COLOR_BGR2RGB), emotion_md
-
-    fer_res = []
-    for face_points in dets:
-        result = fer_model.infer(image, face_points[:-1])
-        fer_res.append(result[0])
-
+        stats_plot = update_stats_and_plot([])
+        return cv.cvtColor(image, cv.COLOR_BGR2RGB), emotion_md, stats_plot
+    fer_res = [fer_model.infer(image, face_points[:-1])[0] for face_points in dets]
     output = visualize(image, dets, fer_res)
     emotion_md = summarize_emotions(fer_res)
-    return cv.cvtColor(output, cv.COLOR_BGR2RGB), emotion_md
+    names_nl = [to_dutch(FacialExpressionRecog.getDesc(x)) for x in fer_res]
+    stats_plot = update_stats_and_plot(names_nl)
+    return cv.cvtColor(output, cv.COLOR_BGR2RGB), emotion_md, stats_plot
 
-# === Automatisch voorbeelden inladen uit de map "examples/" ===
+# Voorbeelden automatisch laden
 IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".bmp", ".webp"}
 EXAMPLES_DIR = Path("examples")
-
-if EXAMPLES_DIR.exists() and EXAMPLES_DIR.is_dir():
-    example_paths = [
-        str(p) for p in sorted(EXAMPLES_DIR.iterdir())
-        if p.is_file() and p.suffix.lower() in IMAGE_EXTS
-    ]
+if EXAMPLES_DIR.exists():
+    example_paths = [str(p) for p in sorted(EXAMPLES_DIR.iterdir()) if p.suffix.lower() in IMAGE_EXTS]
 else:
     example_paths = []
-
 example_list = [[p] for p in example_paths]
 CACHE_EXAMPLES = bool(example_list)
-# =============================================================
 
-# Gradio Interface (NL) + groene kleur voor de emotietekst
+# CSS voor groene tekst
 custom_css = """
-.example * { font-style: italic; font-size: 18px !important; color: #0ea5e9 !important; }
-#emotie-uitslag { color: #16a34a; }  /* GROEN */
+#emotie-uitslag { color: #16a34a; }
 #emotie-uitslag h1, #emotie-uitslag h2, #emotie-uitslag h3 { margin: 0.25rem 0; }
 """
 
-with gr.Blocks(css=custom_css, theme=gr.themes.Default()) as demo:
+with gr.Blocks(css=custom_css) as demo:
     gr.Markdown("## Herkenning van gezichtsuitdrukkingen (FER) met OpenCV DNN")
     gr.Markdown("Detecteert gezichten en herkent gezichtsuitdrukkingen met YuNet + MobileFaceNet (ONNX).")
 
     with gr.Row():
-        with gr.Column(scale=1):
+        with gr.Column():
             input_image = gr.Image(type="numpy", label="Afbeelding uploaden")
             with gr.Row():
                 submit_btn = gr.Button("Verstuur", variant="primary")
                 clear_btn = gr.Button("Wissen")
-        with gr.Column(scale=1):
-            # Eerst de afbeelding, daaronder de (groene) emotie-uitslag
+        with gr.Column():
             output_image = gr.Image(type="numpy", label="Resultaat gezichtsuitdrukking")
-            emotion_md = gr.Markdown(
-                value="## **Nog geen resultaat**",
-                elem_id="emotie-uitslag"
-            )
-
-    # Output(s) leegmaken bij nieuwe upload
-    def _clear_output_on_new_image():
-        return None, "## **Nog geen resultaat**"
-    input_image.change(fn=_clear_output_on_new_image, outputs=[output_image, emotion_md])
-
-    # Knop-actie(s)
-    submit_btn.click(fn=detect_expression, inputs=input_image, outputs=[output_image, emotion_md])
-    clear_btn.click(fn=lambda: (None, None, "## **Nog geen resultaat**"),
-                    outputs=[input_image, output_image, emotion_md])
+            emotion_md = gr.Markdown("## **Nog geen resultaat**", elem_id="emotie-uitslag")
+            stats_image = gr.Image(label="Statistieken", type="numpy")
 
-    gr.Markdown("Klik op een voorbeeld om te testen.", elem_classes=["example"])
+    def clear_all():
+        return None, "## **Nog geen resultaat**", None
+    input_image.change(fn=clear_all, outputs=[output_image, emotion_md, stats_image])
+    submit_btn.click(fn=detect_expression, inputs=input_image, outputs=[output_image, emotion_md, stats_image])
+    clear_btn.click(fn=clear_all, outputs=[input_image, output_image, emotion_md, stats_image])
 
     gr.Examples(
         examples=example_list,
         inputs=input_image,
-        outputs=[output_image, emotion_md],
+        outputs=[output_image, emotion_md, stats_image],
         fn=detect_expression,
         examples_per_page=20,
         cache_examples=CACHE_EXAMPLES