Spaces:
Runtime error
Runtime error
File size: 3,102 Bytes
7045a9e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | """
HF Space: Image Preprocessor (MTCNN Face Detection)
----------------------------------------------------
Detects a face in the input image, crops it with a small margin,
and resizes it to 224x224 — the exact format expected by the
image-to-emotion model downstream.
API endpoint: POST /preprocess
Input : image (file upload)
Output: cropped & resized face image (PNG)
"""
import gradio as gr
from facenet_pytorch import MTCNN
from PIL import Image
# ---------------------------------------------------------------------------
# Initialise MTCNN once at module load so the Space is warm for requests.
# keep_all=False → only the highest-confidence face is returned.
# post_process=False → skip internal normalisation; we only need the crop.
# ---------------------------------------------------------------------------
mtcnn = MTCNN(
image_size=224,
margin=20,
keep_all=False,
post_process=False,
)
# ---------------------------------------------------------------------------
# Core preprocessing function
# ---------------------------------------------------------------------------
def preprocess(image: Image.Image) -> Image.Image:
"""
Detect a single face, apply a 10 % context margin, and resize to 224x224.
Raises gr.Error if no face is detected so the caller receives a clear
HTTP-level error (status 400) rather than a silent None.
"""
if image is None:
raise gr.Error("No image provided.")
img = image.convert("RGB")
boxes, probs = mtcnn.detect(img)
if boxes is None or len(boxes) == 0:
raise gr.Error("No face detected in the provided image.")
# Pick the face with highest detection confidence.
best_idx = int(probs.argmax()) if probs is not None else 0
x1, y1, x2, y2 = boxes[best_idx]
# Add a 10 % context margin for robustness.
w, h = x2 - x1, y2 - y1
margin = 0.10
x1 -= w * margin
y1 -= h * margin
x2 += w * margin
y2 += h * margin
# Clamp to image bounds.
img_w, img_h = img.size
x1 = max(0, int(round(x1)))
y1 = max(0, int(round(y1)))
x2 = min(img_w, int(round(x2)))
y2 = min(img_h, int(round(y2)))
if x2 <= x1 or y2 <= y1:
raise gr.Error("Face bounding box is degenerate after clamping.")
face_img = img.crop((x1, y1, x2, y2)).resize((224, 224), Image.BILINEAR)
return face_img
# ---------------------------------------------------------------------------
# Gradio Interface
# ---------------------------------------------------------------------------
demo = gr.Interface(
fn=preprocess,
inputs=gr.Image(type="pil", label="Input Image"),
outputs=gr.Image(type="pil", label="Preprocessed Face (224×224)"),
title="Image Preprocessor — MTCNN Face Detection",
description=(
"Upload any photo. The service detects the dominant face, "
"crops it with a small context margin, and returns a 224×224 RGB image "
"ready for the image-to-emotion model."
),
api_name="preprocess",
allow_flagging="never",
)
if __name__ == "__main__":
demo.launch()
|