ericek111/myscan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Desktop app with live scanning and OCR

Browse Source 
tools/app.py (myscan/app.py, Qt/PySide6) shows the camera and the page as it
is stitched, Start/Stop or the scan button (F5), then reads the finished page
with RapidOCR (myscan/ocr.py; bundled multilingual models, offline). Lines are
outlined on the page by confidence and linked to an editable text pane that
can be copied or saved. Existing images can be opened or dropped, so the app
is useful without the mouse.

The scan loop moves from tools/scan.py to myscan/scanner.py, shared by both.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
erik
2026-10-09 12:05:22 +00:00
co-authored by Claude Opus 5.5
parent c8b9f610bf
commit 909baec1e7
7 changed files with 880 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/scan.py
+7 -138
View File
@@ -3,116 +3,21 @@
mouse over the page, press it again to stop. Frames are registered while you scan;
after the stop press the page is assembled from all of them at once (see
myscan/stitching/pagegraph.py) and saved as <outdir>/scan-YYYYmmdd-HHMMSS.png. The mouse goes
back to mouse mode between scans (and on Ctrl-C).
back to mouse mode between scans (and on Ctrl-C). The loop itself is myscan/scanner.py.
With --view, a browser viewer (myscan/webview.py) shows the camera and the page as it
is being stitched, and has Start/Stop buttons that work like the scan button."""
import argparse
import csv
import os
import queue
import sys
import threading
import time
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
from myscan.session import ScanSession, quiet_libjpeg # noqa: E402
from myscan.session import quiet_libjpeg # noqa: E402
quiet_libjpeg()
import cv2 # noqa: E402
from myscan import calib # noqa: E402
from myscan.live import LiveSession # noqa: E402
from myscan.stitching import Corrector, PageGraph # noqa: E402
from myscan.xu import XU # noqa: E402
def wait_press(x, viewer=None, poll=0.05):
"""Block until the scan button goes down then up again, or Start is clicked."""
prev = 1
while True:
if viewer and viewer.take_start():
return
b = x.scan_button()
if b and not prev:
break
prev = b
time.sleep(poll)
while x.scan_button():
time.sleep(poll)
def scan_page(x, a, frames_dir=None, corrector=None, gains=None, viewer=None):
"""Capture until the button is pressed again. Frames are registered (and saved) on a
worker thread so capture never waits; returns (PageGraph or None, LiveSession or None)."""
g, live, rows, work, saves = None, None, [], queue.Queue(), queue.Queue()
def worker():
while (item := work.get()) is not None:
n, im, v = item
f = g.add(im, v)
if live:
live.on_frame(f)
def saver():
while (item := saves.get()) is not None:
cv2.imwrite(os.path.join(frames_dir, f"f{item[0]:05d}.png"), item[1])
th = None
sv = threading.Thread(target=saver, daemon=True) if frames_dir else None
if sv:
sv.start()
if viewer:
viewer.take_stop() # ignore a Stop clicked before the scan started
with ScanSession(a.video, a.target, a.exposure, xu=x, gains=gains) as s:
down, last = 0, 0.0
for t, n, im, rec in s.frames(color=not a.gray):
if g is None:
g = PageGraph(im.shape, corrector)
if viewer:
live = LiveSession(g, viewer)
th = threading.Thread(target=worker, daemon=True)
th.start()
work.put((n, im, rec.v))
if sv:
saves.put((n, im))
if live:
live.raw = im
if frames_dir:
rows.append([round(t, 4), n, rec.counter, *rec.v, rec.b14, rec.b15, rec.b16, rec.flags, s.e6,
round(float(im.mean()), 1), rec.raw.hex()])
# Stop on a press: two "down" reads in a row (debounce), ignoring the first
# 0.7 s so a bouncing start press can't end the scan.
if n % 2 == 0:
down = down + 1 if x.scan_button() else 0
if down >= 2 and t > 0.7:
break
if viewer and viewer.take_stop():
break
if t >= a.max_time:
print("max scan time reached", flush=True)
break
if viewer:
viewer.set_status(t=t, frames=n + 1, backlog=work.qsize())
if t - last >= 1:
print(f"\r {t:5.1f}s {n + 1} frames ({g.n} registered) E6={s.e6}", end="", flush=True)
last = t
print()
if viewer:
viewer.set_status(state="assembling", message="finishing registration")
if th:
work.put(None)
th.join()
if sv:
saves.put(None)
sv.join()
if frames_dir: # same layout as tools/record.py, so tools/stitch.py can replay it
with open(os.path.join(frames_dir, "records.csv"), "w", newline="") as fh:
w = csv.writer(fh)
w.writerow(["t", "frame", "counter", "v0", "v1", "v2", "v3", "v4", "v5",
"b14", "b15", "b16", "flags", "e6", "brightness", "raw"])
w.writerows(rows)
return g, live
from myscan.scanner import Scanner # noqa: E402
def main():
@@ -120,7 +25,7 @@ def main():
ap.add_argument("-o", "--outdir", default="scans")
ap.add_argument("--once", action="store_true", help="exit after one page")
ap.add_argument("--now", action="store_true", help="start the first scan immediately")
ap.add_argument("--video", default="/dev/video4")
ap.add_argument("--video", help="capture device (default: find the myScan, else /dev/video4)")
ap.add_argument("--target", type=float, default=200, help="auto-exposure target for paper (95th pct of brightest channel)")
ap.add_argument("--exposure", type=int, help="fixed E6 value instead of auto-exposure")
ap.add_argument("--gray", action="store_true")
@@ -132,56 +37,20 @@ def main():
ap.add_argument("--view", type=int, nargs="?", const=8000, metavar="PORT",
help="serve a live browser view on PORT (default 8000)")
a = ap.parse_args()
os.makedirs(a.outdir, exist_ok=True)
viewer = None
if a.view is not None:
from myscan.webview import Viewer
viewer = Viewer(a.view)
print("live view: " + " ".join(viewer.urls()), flush=True)
x = XU(a.video)
print("reading calibration from the mouse's EEPROM (cached after the first time)", flush=True)
cal = calib.load(x)
corrector = Corrector(None if a.no_flat else calib.FlatField(cal),
None if a.no_undistort else calib.Undistort(cal))
gains = cal["gains_rgb"]
scanner = Scanner(a, viewer)
first = True
try:
while True:
if not (first and a.now):
print("press the scan button to start (Ctrl-C to quit)", flush=True)
if viewer:
viewer.set_status(state="idle", message="press the scan button or Start")
wait_press(x, viewer)
scanner.wait_press()
first = False
print("scanning - press the scan button again to stop", flush=True)
if viewer:
viewer.set_status(state="scanning", message="press the scan button or Stop to finish")
name = time.strftime("scan-%Y%m%d-%H%M%S")
frames_dir = os.path.join(a.outdir, name) if a.save_frames else None
if frames_dir:
os.makedirs(frames_dir)
g, live = scan_page(x, a, frames_dir, corrector, gains, viewer)
if live:
live.stop_solving()
live.close()
if g is None or g.n < 2:
print("no frames captured")
if viewer:
viewer.set_status(state="idle", message="no frames captured")
else:
print("assembling the page...", flush=True)
t0 = time.time()
if viewer:
viewer.set_status(message="solving")
page = g.image(white_balance=not a.no_wb)
path = os.path.join(a.outdir, name + ".png")
cv2.imwrite(path, page)
print(f"saved {path} ({time.time() - t0:.1f} s; {g.stats})", flush=True)
if viewer:
s = min(1.0, 1600 / max(page.shape[:2]))
viewer.publish("page", cv2.resize(page, None, fx=s, fy=s, interpolation=cv2.INTER_AREA))
viewer.set_result(path)
viewer.set_status(state="done", message=f"saved {path}", backlog=0)
scanner.scan()
if a.once:
break
except KeyboardInterrupt: