Update app.py

app.py

@@ -0,0 +1,130 @@
+import streamlit as st
+from PIL import Image
+import cv2
+import numpy as np
+
+from transformers import pipeline
+
+st.set_page_config(
+    page_title="Smart Vision Inspector",
+    page_icon="👁️",
+    layout="wide"
+)
+
+st.title("👁️ Smart Vision Inspector")
+
+st.markdown("""
+Upload an image and perform:
+
+- Object Detection
+- Image Analysis
+- Bounding Box Visualization
+- AI Powered Insights
+""")
+
+@st.cache_resource
+def load_detector():
+
+    detector = pipeline(
+        "object-detection",
+        model="facebook/detr-resnet-50"
+    )
+
+    return detector
+
+detector = load_detector()
+
+uploaded_file = st.file_uploader(
+    "Upload Image",
+    type=["jpg", "jpeg", "png"]
+)
+
+if uploaded_file:
+
+    image = Image.open(uploaded_file)
+
+    st.image(
+        image,
+        caption="Uploaded Image",
+        use_container_width=True
+    )
+
+    image_np = np.array(image)
+
+    image_bgr = cv2.cvtColor(
+        image_np,
+        cv2.COLOR_RGB2BGR
+    )
+
+    results = detector(image)
+
+    object_counts = {}
+
+    for obj in results:
+
+        label = obj["label"]
+
+        object_counts[label] = (
+            object_counts.get(label, 0) + 1
+        )
+
+        box = obj["box"]
+
+        x1 = int(box["xmin"])
+        y1 = int(box["ymin"])
+        x2 = int(box["xmax"])
+        y2 = int(box["ymax"])
+
+        cv2.rectangle(
+            image_bgr,
+            (x1, y1),
+            (x2, y2),
+            (0, 255, 0),
+            2
+        )
+
+        cv2.putText(
+            image_bgr,
+            label,
+            (x1, y1 - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.6,
+            (0,255,0),
+            2
+        )
+
+    result_rgb = cv2.cvtColor(
+        image_bgr,
+        cv2.COLOR_BGR2RGB
+    )
+
+    st.subheader(
+        "Detection Results"
+    )
+
+    st.image(
+        result_rgb,
+        use_container_width=True
+    )
+
+    st.subheader(
+        "Detected Objects"
+    )
+
+    st.json(object_counts)
+
+    st.subheader(
+        "Summary"
+    )
+
+    summary = []
+
+    for k, v in object_counts.items():
+
+        summary.append(
+            f"{v} {k}"
+        )
+
+    st.success(
+        "Detected: " + ", ".join(summary)
+    )