pull down to refresh
I'm running a test against stuff I screenshotted from the MLK files, it is still running and I suspect that it will crash lol
Prompt:
1. Identify the characteristics of the font in the image
2. Find opentype fonts that match these characteristics
3. Compare text written in the font with text from the image and identify the closest matchreply
It crashed.
It wrote this python script tho:
#!/usr/bin/env python3
"""
Detailed glyph-level comparison.
Render specific phrases in each candidate font, blur to match scan softness,
resize to original dimensions, compute per-pixel MSE, and produce a side-by-side grid.
"""
from PIL import Image, ImageDraw, ImageFont, ImageFilter, ImageChops, ImageOps
import os, math
orig = Image.open("/home/user/uploads/scan.png").convert("L")
# Crop the text region roughly (with some margin) - exclude off-white paper background edges
ORIG_CROP = orig.crop((10, 5, 855, 365))
W,H = ORIG_CROP.size
print("Original crop size:", W, H)
# 7 lines, each ~52px tall
LINES = [
"At the very outset of the investigation telegrams",
"went to all field offices of the Bureau instructing the",
"Special Agents in Charge to take personal supervision of",
"the investigation, to check out all leads in 24 hours, and",
"noting that they would be held personally responsible.",
"(HQ 44-38861-153). The files we reviewed show that this",
"directive was conscientiously followed. The Bureau sought",
]
FONTS = [
("Courier New Reg", "/home/user/fonts/cour.ttf"),
("Courier New Bold", "/home/user/fonts/courbd.ttf"),
("Courier Prime Reg", "/home/user/fonts/CourierPrime.ttf"),
("Courier Prime Bold", "/home/user/fonts/CourierPrime-Bold.ttf"),
("Special Elite", "/home/user/fonts/SpecialElite.ttf"),
("IBM Plex Mono", "/home/user/fonts/IBMPlexMono.ttf"),
("1942 Report", "/home/user/fonts/1942.ttf"),
("Cutive Mono", "/home/user/fonts/CutiveMono.ttf"),
("Old Typewriter 2.0", "/home/user/fonts/old_tw_dir/Old Typewriter2.0.ttf"),
("Ubuntu Mono Bold", "/home/user/fonts/UbuntuMono-B.ttf"),
("Nimbus Mono Reg", "/home/user/fonts/NimbusMono-Regular.otf"),
("Nimbus Mono Bold", "/home/user/fonts/NimbusMono-Bold.otf"),
("DejaVu Sans Mono", "/usr/share/fonts/truetype/dejavu/DejaVuSansMono.ttf"),
("DejaVu Sans Mono Bd", "/usr/share/fonts/truetype/dejavu/DejaVuSansMono-Bold.ttf"),
]
def render_font(path, size, leading=6, margin_left=20, margin_top=15, inkspread=0, blur=0.0):
try:
font = ImageFont.truetype(path, size)
except Exception as e:
return None
# measure line heights
img_tmp = Image.new("L",(10,10),255)
d = ImageDraw.Draw(img_tmp)
heights=[]
widths=[]
for ln in LINES:
bb = d.textbbox((0,0), ln, font=font)
heights.append(bb[3]-bb[1])
widths.append(bb[2]-bb[0])
line_h = heights[0]
w = max(widths)+margin_left*2
h = line_h*7 + leading*6 + margin_top*2
img = Image.new("L",(w,h),255)
d = ImageDraw.Draw(img)
y = margin_top
for i,ln in enumerate(LINES):
d.text((margin_left, y), ln, font=font, fill=0)
y += line_h + leading
# ink spread (dilate)
for _ in range(inkspread):
img = img.filter(ImageFilter.MaxFilter(3))
if blur > 0:
img = img.filter(ImageFilter.GaussianBlur(radius=blur))
return img
def mse(a,b):
# both same size
import numpy as np
aa = np.asarray(a, dtype=np.float32)
bb = np.asarray(b, dtype=np.float32)
diff = (aa-bb)/255.0
return float((diff*diff).mean())
# Search for best parameters per font
results = []
for name, path in FONTS:
if not os.path.exists(path):
continue
best = None
for size in range(20, 38):
for leading in range(0, 12, 2):
for ink in range(0, 3):
for blur in [0.6, 0.9, 1.2, 1.5]:
im = render_font(path, size, leading=leading, inkspread=ink, blur=blur)
if im is None: continue
im2 = im.resize((W,H), Image.LANCZOS)
e = mse(im2, ORIG_CROP)
if best is None or e < best[0]:
best = (e, size, leading, ink, blur, im2)
results.append((best[0], name, best[1:]))
print(f"{name:28s} MSE={best[0]:.4f} size={best[1]} leading={best[2]} ink={best[3]} blur={best[4]}")
results.sort()
print("\n=== Ranking (lower MSE = better match) ===")
for e, name, _ in results:
print(f" {name:28s} MSE={e:.4f}")
# Build side-by-side comparison of the top 6 + original
TOP_N = 8
strips = []
lab_h = 30
# Add original
strip = Image.new("RGB",(W*2+6, H+lab_h+8),(220,220,220))
d = ImageDraw.Draw(strip)
d.text((10,5), "ORIGINAL", fill=(0,0,180))
strip.paste(Image.merge("RGB",(ORIG_CROP,ORIG_CROP,ORIG_CROP)),(2,lab_h+4))
strips.append(("ORIGINAL", strip))
for e, name, (size, leading, ink, blur, im2) in results[:TOP_N]:
strip = Image.new("RGB",(W*2+6, H+lab_h+8),(220,220,220))
d = ImageDraw.Draw(strip)
d.text((10,5), f"{name} sz={size} lead={leading} ink={ink} blur={blur} MSE={e:.4f}", fill=(150,0,0))
# Left: rendered; Right: side-by-side diff overlay
rrgb = Image.merge("RGB",(im2,im2,im2))
strip.paste(rrgb,(2,lab_h+4))
# diff
diff = ImageChops.difference(im2, ORIG_CROP)
# colorize diff: red channel where diff
diff_rgb = Image.merge("RGB",(diff, Image.new("L",diff.size,255), Image.new("L",diff.size,255)))
strip.paste(diff_rgb,(W+4,lab_h+4))
strips.append((name, strip))
WW = W*2+6
HH = sum(s.height+6 for _,s in strips)
out = Image.new("RGB",(WW,HH),(180,180,180))
y=0
for _,s in strips:
out.paste(s,(0,y)); y+=s.height+6
out.save("/home/user/comparison3.png")
print("Saved comparison3.png", out.size)
# Also save best match image separately
best_err, best_name, best_params = results[0]
best_size, best_lead, best_ink, best_blur, best_im = best_params
print(f"\n==> Best match: {best_name} (MSE={best_err:.4f})")GIving that to the next agent will probably speed it up... iterations... ugh
reply
shouldn't it be something NOT complicated?
reply
reply
I used the font the agent suggested, it's actually not bad! I'm going to print the doc out to see how it goes. 😂 almost feel like doing detective work.
reply
reply
yet people said they are using AI to build whatever? really? it sounds like building a castle in sand. 😂
reply
I just asked in arena.ai, it gave me a much better result, but still I would like to know your workflow in this.