First try at anonymizer app.

README.md

@@ -1,8 +1,8 @@
 ---
 title: Image Anonymizer
-emoji: 😻
-colorFrom: purple
-colorTo: red
+emoji: 🕶
+colorFrom: yellow
+colorTo: black
 sdk: gradio
 sdk_version: 3.27.0
 app_file: app.py

app.py

@@ -1,7 +1,72 @@
 import gradio as gr
+import yolov5
+import numpy as np
+from PIL import Image, ImageDraw, ImageFilter
+from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation
 
-def greet(name):
-    return "Hello " + name + "!!"
+person_processor = OneFormerProcessor.from_pretrained("shi-labs/oneformer_cityscapes_swin_large")
+person_model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_cityscapes_swin_large")
 
-interface = gr.Interface(fn=greet, inputs="text", outputs="text")
-interface.launch()
+lp_model = yolov5.load('keremberke/yolov5m-license-plate')  
+lp_model.conf = 0.25  # NMS confidence threshold
+lp_model.iou = 0.45  # NMS IoU threshold
+lp_model.agnostic = False  # NMS class-agnostic
+lp_model.multi_label = False  # NMS multiple labels per box
+lp_model.max_det = 1000  # maximum number of detections per image
+
+def detect_person(image: Image):
+    semantic_inputs = person_processor(images=image, task_inputs=["semantic"], return_tensors="pt")
+    semantic_outputs = person_model(**semantic_inputs)
+    predicted_semantic_map = person_processor.post_process_semantic_segmentation(semantic_outputs, target_sizes=[image.size[::-1]])[0]
+    mask = transform(predicted_semantic_map.to(torch.uint8))
+    mask = Image.eval(mask, lambda x: 0 if x == 11 else 255)
+    return mask  
+
+
+def detect_license_plate(image: Image):
+    results = lp_model(image, size=image.size[0])
+    predictions = results.pred[0]
+    boxes = predictions[:, :4]
+    from PIL import Image, ImageDraw, ImageFilter
+    mask = Image.new(mode="L", size=image.size, color=255)
+    draw = ImageDraw.Draw(mask)
+    for box in boxes:
+        draw.rectangle(list(box), fill=0)
+    return mask
+
+
+def detect_dummy(image: Image):
+    return Image.new(mode="L", size=image.size, color=255)
+
+
+detectors = {
+    "Person": detect_person,
+    "License Plate": detect_license_plate
+}
+
+
+def anonymize(path: str, detectors: list):
+    # Read image
+    image = Image.open(path)
+    # Run requested detectors 
+    masks = [implemented_detectors.get(det, detect_dummy)(image) for det in detectors]
+    # Combine masks
+    combined = np.minimum.reduce([np.array(m) for m in masks])
+    mask = Image.fromarray(combined)
+    # Apply blur through mask
+    blurred = image.filter(ImageFilter.GaussianBlur(15))
+    anonymized = Image.composite(image, blurred, mask)
+    return anonymized    
+
+
+def test_gradio(image):
+    masks = [detect_person(image), detect_license_plate(image)]
+    combined = np.minimum.reduce([np.array(m) for m in masks])
+    mask = Image.fromarray(combined)
+    # Apply blur through mask
+    blurred = image.filter(ImageFilter.GaussianBlur(15))
+    anonymized = Image.composite(image, blurred, mask)
+    return anonymized
+
+interface = gr.Interface(fn=test_gradio, inputs=gr.Image(type="pil"), outputs="image")
+interface.launch(share=True)

requirements.txt

@@ -0,0 +1,4 @@
+yolov5
+transformers
+Pillow
+numpy