What does A Screenshot Is Not a Payment conclude, in numbers, about “Average Hash and Hamming Distance: Detecting Repeated Screenshots, and Where Detection Is Blind”?
Answer: Chapter 5 shows that a whole-image average hash at threshold 4 flags 0.9135 of same-layout genuine receipts as resends, while a hash of the fields alone recognises 0.8333 of resends at threshold 10 with no false positives.
Scope of the numbers: Orders, account tails, amounts, screenshots and hashes are synthesised from fixed seeds, parameters are illustrative, and every calculation is generated by the book's programs. Marked boxes separate published evidence, runnable Python calculations (20 programs), classical sources and the author's hypotheses.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.9135, 10
| pairs: copies 300, same-layout genuine 14850, cross-layout 30000 | |||
| median distance: copies 0, same layout 1, cross layout 17 | |||
| t | TPR copies | FPR same layout | FPR cross layout |
| 0 | 0.5933 | 0.2773 | 0.0000 |
| 1 | 0.6700 | 0.5872 | 0.0000 |
| 2 | 0.7000 | 0.7304 | 0.0000 |
| 3 | 0.7400 | 0.8339 | 0.0000 |
| 4 | 0.7500 | 0.9135 | 0.0000 |
| 6 | 0.8167 | 0.9896 | 0.0000 |
| 8 | 0.8733 | 0.9995 | 0.2544 |
| 10 | 0.8867 | 1.0000 | 0.3036 |
Show the full program
# Chapter 5. p52: whole-image hashes cannot tell a layout from a copy
# Model: 300 synthetic genuine receipts (3 app layouts x 100, random
# amounts, times, last five digits and transaction numbers from a
# seeded generator) and 300 returned copies, each a genuine receipt
# put through one of six benign changes from p51 in turn (noise,
# brightness, contrast, rescale, 3-row shift, new status clock). For
# a threshold t, a pair at aHash distance <= t is flagged as the same
# screenshot. TPR = copies flagged against their source; FPR = pairs
# of different genuine receipts of the same layout that are flagged.
import math
import hashlib
import random
SIZE = 64
FONT = {"0": "111101101101111", "1": "010110010010111",
"2": "111001111100111", "3": "111001111001111",
"4": "101101111001001", "5": "111100111001111",
"6": "111100111101111", "7": "111001001001001",
"8": "111101111101111", "9": "111101111001111",
":": "000010000010000", ".": "000000000000010"}
# three illustrative app layouts: header shade, header rows, logo box
APPS = [(40, 9, (11, 18, 26, 38)), (70, 12, (14, 20, 4, 14)),
(245, 0, (3, 9, 50, 60))]
def blank(app):
shade, rows, (r0, r1, c0, c1) = APPS[app]
img = [[245] * SIZE for _ in range(SIZE)]
for r in range(rows):
img[r] = [shade] * SIZE
for r in range(r0, r1):
for c in range(c0, c1):
img[r][c] = 90
for r in (37, 43, 49, 55): # fixed field labels
for c in range(4, 20):
img[r][c] = img[r + 1][c] = 150
return img
def text(img, s, row, col, scale, ink):
for ch in s:
bits = FONT[ch]
for k, b in enumerate(bits):
if b == "1":
y, x = row + (k // 3) * scale, col + (k % 3) * scale
for dy in range(scale):
for dx in range(scale):
if 0 <= y + dy < SIZE and 0 <= x + dx < SIZE:
img[y + dy][x + dx] = ink
col += 4 * scale
def receipt(app, amount, clock, tail, txn, status="09:41"):
img = blank(app)
text(img, status, 0, 44, 1, 200 if app < 2 else 30)
text(img, amount, 23, 8, 2, 20)
text(img, clock, 36, 30, 1, 60)
text(img, tail, 42, 30, 1, 60)
text(img, txn[:8], 48, 28, 1, 60)
text(img, txn[8:], 54, 28, 1, 60)
return img
def ahash(img, n=8):
step = SIZE // n
means = []
for i in range(n):
for j in range(n):
cell = [img[r][c] for r in range(i * step, i * step + step)
for c in range(j * step, j * step + step)]
means.append(math.fsum(cell) / len(cell))
avg = math.fsum(means) / len(means)
bits = 0
for m in means:
bits = (bits << 1) | (m > avg)
return bits
def dhash(img):
bits = 0
for i in range(8):
rows = range(i * 8, i * 8 + 8)
cols = [(j * SIZE) // 9 for j in range(10)]
cells = []
for j in range(9):
cell = [img[r][c] for r in rows
for c in range(cols[j], cols[j + 1])]
cells.append(math.fsum(cell) / len(cell))
for j in range(8):
bits = (bits << 1) | (cells[j] > cells[j + 1])
return bits
def ham(a, b):
return bin(a ^ b).count("1")
def raw(img):
return bytes(v for row in img for v in row)
def clip(v):
return 0 if v < 0 else 255 if v > 255 else int(v)
def noisy(img, rng, amp=6):
return [[clip((v + rng.randint(-amp, amp)) // 4 * 4) for v in row]
for row in img]
def bright(img, d=25):
return [[clip(v + d) for v in row] for row in img]
def contrast(img, k=0.85):
return [[clip(128 + (v - 128) * k) for v in row] for row in img]
def rescale(img, m=48):
small = [[img[(r * SIZE) // m][(c * SIZE) // m] for c in range(m)]
for r in range(m)]
return [[small[(r * m) // SIZE][(c * m) // SIZE] for c in range(SIZE)]
for r in range(SIZE)]
def shift_up(img, k=3):
return [row[:] for row in img[k:]] + [[245] * SIZE for _ in range(k)]
rng = random.Random(20261113)
def fresh(app):
amt = "%d.%02d" % (rng.randrange(20, 1000), rng.choice((0, 0, 50)))
clock = "%02d:%02d" % (rng.randrange(24), rng.randrange(60))
tail = "%05d" % rng.randrange(100000)
txn = "".join(rng.choice("0123456789") for _ in range(16))
return receipt(app, amt, clock, tail, txn)
def variant(img, k):
if k == 0:
return noisy(img, rng)
if k == 1:
return bright(img)
if k == 2:
return contrast(img)
if k == 3:
return rescale(img)
if k == 4:
return shift_up(img)
out = [row[:] for row in img]
text(out, "%02d:%02d" % (rng.randrange(24), rng.randrange(60)),
0, 44, 1, 200 if out[0][0] < 100 else 30)
return out
genuine, apps = [], []
for app in range(3):
for _ in range(100):
genuine.append(fresh(app))
apps.append(app)
H = [ahash(g) for g in genuine]
dup = []
for i, g in enumerate(genuine):
dup.append(ham(H[i], ahash(variant(g, i % 6))))
same = [ham(H[i], H[j]) for i in range(300) for j in range(i + 1, 300)
if apps[i] == apps[j]]
cross = [ham(H[i], H[j]) for i in range(300) for j in range(i + 1, 300)
if apps[i] != apps[j]]
print("pairs: copies %d, same-layout genuine %d, cross-layout %d"
% (len(dup), len(same), len(cross)))
print("median distance: copies %d, same layout %d, cross layout %d"
% (sorted(dup)[150], sorted(same)[len(same) // 2],
sorted(cross)[len(cross) // 2]))
print(" t TPR copies FPR same layout FPR cross layout")
for t in (0, 1, 2, 3, 4, 6, 8, 10):
tpr = len([d for d in dup if d <= t]) / len(dup)
fs = len([d for d in same if d <= t]) / len(same)
fc = len([d for d in cross if d <= t]) / len(cross)
print("%4d %11.4f %16.4f %17.4f" % (t, tpr, fs, fc))Single source and citation
Fan, Y. (2026). Fault-Tolerant Parsing of Payment Receipts and Spoken Orders: Last-Five-Digit Write-Off Automata and Blocking Duplicate-Screenshot Fraud (Version 1.0.0), Chapter 5: Average Hash and Hamming Distance: Detecting Repeated Screenshots, and Where Detection Is Blind. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-267 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026267,
author = {Fan, Yafu},
title = {Fault-Tolerant Parsing of Payment Receipts and Spoken Orders: Last-Five-Digit Write-Off Automata and Blocking Duplicate-Screenshot Fraud},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Matching on Amount Alone Must Collide: the Birthday Problem of Same-Day, Same-Amount Payments
- Chapter 2 · The Last Five Digits and a Time Window: How Far Collisions Fall, and What Will Not Fall
- Chapter 3 · A Finite Automaton for Spoken and Written Chinese Amounts, Simplified and Traditional
- Chapter 4 · The Write-Off Automaton: a Screenshot Is a Claim, a Credit Is a Fact
- Chapter 6 · The Receipt Fingerprint Library: the Birthday Problem Among Hashes, and Pigeonhole Search
- Chapter 7 · Classics East and West: Half-Seal Tallies in the Collected Statutes of the Ming and Galton's Finger Prints
- Chapter 8 · The Buying Agent's Reconciliation Loop and a Protocol for Refutation