space/face-lock
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

Initial FastAPI face-lock scaffold

Browse Source
This commit is contained in:
Luna
2026-04-11 16:32:26 +02:00
commit 660ce4e7cc
9 changed files with 306 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.env.example Normal file
View File

@@ -0,0 +1 @@
ENV=dev

7
.gitignore vendored Normal file
View File

@@ -0,0 +1,7 @@
__pycache__/
*.pyc
.venv/
.env
.pytest_cache/
.coverage
htmlcov/

13
README.md Normal file
View File

@@ -0,0 +1,13 @@
# face-lock
FastAPI microservice that finds the primary subject in an image, draws a square around it, and returns a buffered crop.
## Dev
```bash
cp .env.example .env
pip install -r requirements.txt
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000
```
Set `ENV=dev` to enable the Tailwind UI at `/`.

0
app/__init__.py Normal file
View File

13
app/config.py Normal file
View File

@@ -0,0 +1,13 @@
from dataclasses import dataclass
from dotenv import load_dotenv
import os
load_dotenv()
@dataclass(frozen=True)
class Settings:
env: str = os.getenv("ENV", "prod").strip().lower()
settings = Settings()

88
app/main.py Normal file
View File

@@ -0,0 +1,88 @@
from fastapi import FastAPI, File, HTTPException, UploadFile
from fastapi.responses import HTMLResponse, StreamingResponse
from app.config import settings
app = FastAPI(title="face-lock", version="0.1.0")
@app.get("/health")
def health():
return {"ok": True, "env": settings.env}
@app.get("/", response_class=HTMLResponse)
def index():
if settings.env != "dev":
return HTMLResponse("<h1>face-lock</h1><p>Set ENV=dev for the UI.</p>")
return HTMLResponse(
"""
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<script src="https://cdn.tailwindcss.com"></script>
<title>face-lock</title>
</head>
<body class="bg-slate-950 text-slate-100 min-h-screen">
<main class="mx-auto max-w-5xl p-6">
<div class="mb-6">
<h1 class="text-3xl font-bold">face-lock</h1>
<p class="text-slate-400">Drop an image, get the primary subject squared and cropped.</p>
</div>
<div class="grid gap-6 md:grid-cols-2">
<section class="rounded-2xl border border-slate-800 bg-slate-900 p-4">
<input id="file" type="file" accept="image/*" class="block w-full rounded-lg border border-slate-700 bg-slate-950 p-3" />
<button id="go" class="mt-4 rounded-lg bg-cyan-500 px-4 py-2 font-semibold text-slate-950">Process</button>
<pre id="meta" class="mt-4 whitespace-pre-wrap rounded-lg bg-slate-950 p-3 text-xs text-slate-300"></pre>
</section>
<section class="rounded-2xl border border-slate-800 bg-slate-900 p-4">
<div class="mb-3 text-sm font-semibold text-slate-400">Result</div>
<img id="result" class="hidden w-full rounded-xl border border-slate-800" />
</section>
</div>
</main>
<script>
const file = document.getElementById('file');
const go = document.getElementById('go');
const result = document.getElementById('result');
const meta = document.getElementById('meta');
go.onclick = async () => {
if (!file.files.length) return;
const form = new FormData();
form.append('file', file.files[0]);
meta.textContent = 'Working...';
const resp = await fetch('/api/focus', { method: 'POST', body: form });
const data = await resp.json();
meta.textContent = JSON.stringify(data, null, 2);
result.src = data.crop_data_url;
result.classList.remove('hidden');
};
</script>
</body>
</html>
"""
)
@app.post("/api/focus")
async def focus(file: UploadFile = File(...)):
from app.vision import process_image
try:
payload = await file.read()
return process_image(payload, file.filename or "upload")
except ValueError as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
@app.post("/api/focus/image")
async def focus_image(file: UploadFile = File(...)):
from app.vision import process_image
try:
payload = await file.read()
result = process_image(payload, file.filename or "upload")
return StreamingResponse(result["crop_bytes_io"], media_type=result["mime_type"])
except ValueError as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc

149
app/vision.py Normal file
View File

@@ -0,0 +1,149 @@
from __future__ import annotations
from dataclasses import dataclass
from io import BytesIO
from typing import Any
import cv2
import numpy as np
@dataclass(frozen=True)
class BBox:
x: int
y: int
w: int
h: int
@property
def right(self) -> int:
return self.x + self.w
@property
def bottom(self) -> int:
return self.y + self.h
HOG = cv2.HOGDescriptor()
HOG.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
def decode_image(image_bytes: bytes) -> np.ndarray:
data = np.frombuffer(image_bytes, dtype=np.uint8)
image = cv2.imdecode(data, cv2.IMREAD_COLOR)
if image is None:
raise ValueError("could not decode image")
return image
def select_primary_bbox(image: np.ndarray) -> tuple[BBox, str]:
person_bbox = detect_person(image)
if person_bbox is not None:
return person_bbox, "person_hog"
contour_bbox = detect_salient_object(image)
if contour_bbox is not None:
return contour_bbox, "contour"
h, w = image.shape[:2]
side = int(min(w, h) * 0.8)
x = max(0, (w - side) // 2)
y = max(0, (h - side) // 2)
return BBox(x=x, y=y, w=side, h=side), "center_fallback"
def detect_person(image: np.ndarray) -> BBox | None:
rects, weights = HOG.detectMultiScale(image, winStride=(8, 8), padding=(8, 8), scale=1.05)
if len(rects) == 0:
return None
best = max(zip(rects, weights), key=lambda item: int(item[0][2]) * int(item[0][3]))[0]
x, y, w, h = map(int, best)
return BBox(x=x, y=y, w=w, h=h)
def detect_salient_object(image: np.ndarray) -> BBox | None:
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (7, 7), 0)
edges = cv2.Canny(blurred, 40, 120)
kernel = np.ones((5, 5), np.uint8)
closed = cv2.morphologyEx(edges, cv2.MORPH_CLOSE, kernel, iterations=2)
contours, _ = cv2.findContours(closed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
if not contours:
return None
h, w = image.shape[:2]
image_area = h * w
candidates: list[tuple[int, BBox]] = []
for contour in contours:
x, y, bw, bh = cv2.boundingRect(contour)
area = bw * bh
if area < max(500, int(image_area * 0.01)):
continue
candidates.append((area, BBox(x=x, y=y, w=bw, h=bh)))
if not candidates:
return None
return max(candidates, key=lambda item: item[0])[1]
def square_bbox(bbox: BBox, image_shape: tuple[int, int, int], buffer_ratio: float = 0.15) -> BBox:
image_h, image_w = image_shape[:2]
side = int(round(max(bbox.w, bbox.h) * (1 + buffer_ratio * 2)))
side = max(1, min(side, image_w, image_h))
cx = bbox.x + bbox.w / 2
cy = bbox.y + bbox.h / 2
x = int(round(cx - side / 2))
y = int(round(cy - side / 2))
x = max(0, min(x, image_w - side))
y = max(0, min(y, image_h - side))
return BBox(x=x, y=y, w=side, h=side)
def draw_square(image: np.ndarray, bbox: BBox) -> np.ndarray:
annotated = image.copy()
cv2.rectangle(annotated, (bbox.x, bbox.y), (bbox.right, bbox.bottom), (0, 255, 0), 3)
return annotated
def crop_image(image: np.ndarray, bbox: BBox) -> np.ndarray:
return image[bbox.y:bbox.bottom, bbox.x:bbox.right]
def encode_image(image: np.ndarray, ext: str = ".jpg") -> tuple[bytes, str]:
ok, encoded = cv2.imencode(ext, image)
if not ok:
raise ValueError("could not encode image")
mime_type = "image/jpeg" if ext.lower() in {".jpg", ".jpeg"} else "image/png"
return encoded.tobytes(), mime_type
def _data_url(image_bytes: bytes, mime_type: str) -> str:
import base64
return f"data:{mime_type};base64,{base64.b64encode(image_bytes).decode('ascii')}"
def process_image(image_bytes: bytes, filename: str) -> dict[str, Any]:
image = decode_image(image_bytes)
bbox, method = select_primary_bbox(image)
square = square_bbox(bbox, image.shape)
crop = crop_image(image, square)
annotated = draw_square(image, square)
crop_bytes, mime_type = encode_image(crop, ".jpg")
annotated_bytes, _ = encode_image(annotated, ".jpg")
return {
"filename": filename,
"method": method,
"detected_bbox": bbox.__dict__,
"square_bbox": square.__dict__,
"source_size": {"width": int(image.shape[1]), "height": int(image.shape[0])},
"crop_data_url": _data_url(crop_bytes, mime_type),
"annotated_data_url": _data_url(annotated_bytes, mime_type),
"mime_type": mime_type,
"crop_bytes_io": BytesIO(crop_bytes),
}

5
requirements.txt Normal file
View File

@@ -0,0 +1,5 @@
fastapi
uvicorn[standard]
opencv-python-headless
python-dotenv
python-multipart

30
tests/test_vision.py Normal file
View File

@@ -0,0 +1,30 @@
import numpy as np
from app.vision import BBox, crop_image, detect_salient_object, square_bbox
def test_square_bbox_is_square_and_inside_bounds():
bbox = BBox(x=10, y=20, w=40, h=20)
square = square_bbox(bbox, (100, 120, 3), buffer_ratio=0.1)
assert square.w == square.h
assert square.x >= 0
assert square.y >= 0
assert square.right <= 120
assert square.bottom <= 100
def test_crop_image_uses_bbox():
image = np.zeros((60, 80, 3), dtype=np.uint8)
image[10:30, 20:50] = 255
bbox = BBox(x=20, y=10, w=30, h=20)
crop = crop_image(image, bbox)
assert crop.shape[:2] == (20, 30)
def test_detect_salient_object_finds_rectangle():
image = np.zeros((100, 100, 3), dtype=np.uint8)
image[25:75, 30:80] = 255
bbox = detect_salient_object(image)
assert bbox is not None
assert bbox.w >= 45
assert bbox.h >= 45