Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -186,6 +186,47 @@ def explain_grade(focus_score, readability_score, read):
|
|
| 186 |
return "a mix of small readability and focus factors - see details below"
|
| 187 |
|
| 188 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
def coverage_description(spread_score):
|
| 190 |
if spread_score < 15:
|
| 191 |
return "concentrated on one clear focal point - that's usually a good sign, not a problem"
|
|
@@ -195,12 +236,18 @@ def coverage_description(spread_score):
|
|
| 195 |
return "spread fairly widely across the design"
|
| 196 |
|
| 197 |
|
| 198 |
-
def create_score_chart(focus_score, spread_score, readability_score):
|
| 199 |
labels = ["Clear Focal\nPoint", "Attention\nCoverage"]
|
| 200 |
values = [focus_score, spread_score]
|
| 201 |
if readability_score is not None:
|
| 202 |
labels.append("Readability")
|
| 203 |
values.append(readability_score)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
colors = []
|
| 205 |
for v in values:
|
| 206 |
if v >= 75:
|
|
@@ -350,6 +397,7 @@ def analyze_readability(pil_img):
|
|
| 350 |
small_text_issues = 0
|
| 351 |
issue_lines = []
|
| 352 |
issue_boxes = []
|
|
|
|
| 353 |
for i in range(len(ocr_data['text'])):
|
| 354 |
word = ocr_data['text'][i].strip()
|
| 355 |
conf = int(ocr_data['conf'][i])
|
|
@@ -359,11 +407,12 @@ def analyze_readability(pil_img):
|
|
| 359 |
if w < 3 or h < 3:
|
| 360 |
continue
|
| 361 |
words_checked += 1
|
|
|
|
|
|
|
| 362 |
text_color, bg_color = sample_text_and_bg_color(img_arr, x, y, w, h)
|
| 363 |
if text_color is None:
|
| 364 |
continue
|
| 365 |
ratio = contrast_ratio(text_color, bg_color)
|
| 366 |
-
size_pct = (h / img_h) * 100
|
| 367 |
required_ratio = required_contrast_ratio(size_pct)
|
| 368 |
if ratio < required_ratio:
|
| 369 |
contrast_issues += 1
|
|
@@ -377,7 +426,8 @@ def analyze_readability(pil_img):
|
|
| 377 |
issue_lines.append(f"- \"{word}\" is a bit small to read comfortably")
|
| 378 |
issue_boxes.append({"box": (x, y, w, h), "label": "Small text"})
|
| 379 |
return {"words_checked": words_checked, "contrast_issues": contrast_issues,
|
| 380 |
-
"small_text_issues": small_text_issues, "issue_lines": issue_lines, "issue_boxes": issue_boxes
|
|
|
|
| 381 |
|
| 382 |
|
| 383 |
def merge_issue_boxes(issue_boxes, gap=15):
|
|
@@ -573,7 +623,11 @@ def analyze(pil_image, overlay_strength):
|
|
| 573 |
total_score, grade = compute_overall_grade(scores['focus_score'], scores['spread_score'], readability_score)
|
| 574 |
grade_reason = explain_grade(scores['focus_score'], readability_score, read)
|
| 575 |
tips = generate_recommendations(saliency_map, scores, read, h, w)
|
| 576 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 577 |
|
| 578 |
overlay_bgr = draw_scan_path(overlay_bgr, zones, h, w)
|
| 579 |
overlay_bgr = draw_zone_labels(overlay_bgr, zones, h, w)
|
|
@@ -616,6 +670,13 @@ def analyze(pil_image, overlay_strength):
|
|
| 616 |
for tip in tips:
|
| 617 |
summary += f"- {tip}\n"
|
| 618 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 619 |
summary += (
|
| 620 |
"\n---\n"
|
| 621 |
"**Methodology:** Attention prediction combines MSI-Net, a peer-reviewed saliency model "
|
|
@@ -660,7 +721,9 @@ with gr.Blocks(title="Design Analyzer") as demo:
|
|
| 660 |
"- **No inflated claims.** A cited, transparent process instead "
|
| 661 |
"of a marketing number.\n"
|
| 662 |
"- **Scan-path arrows** show the predicted order attention flows, "
|
| 663 |
-
"not just isolated hotspots.\n
|
|
|
|
|
|
|
| 664 |
"Coming soon: before/after comparisons."
|
| 665 |
)
|
| 666 |
with gr.Row():
|
|
|
|
| 186 |
return "a mix of small readability and focus factors - see details below"
|
| 187 |
|
| 188 |
|
| 189 |
+
def compute_hierarchy(text_sizes):
|
| 190 |
+
if len(text_sizes) < 2:
|
| 191 |
+
return None
|
| 192 |
+
largest = max(text_sizes)
|
| 193 |
+
smallest = min(text_sizes)
|
| 194 |
+
ratio = largest / max(smallest, 0.1)
|
| 195 |
+
score = round(min(100, ratio * 20), 1)
|
| 196 |
+
return score, ratio
|
| 197 |
+
|
| 198 |
+
|
| 199 |
+
def hierarchy_description(ratio):
|
| 200 |
+
if ratio < 1.5:
|
| 201 |
+
return "text sizes are very similar - there's no single element that clearly leads the eye"
|
| 202 |
+
elif ratio < 2.5:
|
| 203 |
+
return "there's some size variation, but the hierarchy could be stronger"
|
| 204 |
+
else:
|
| 205 |
+
return "clear size hierarchy - one element leads, the rest support it"
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
def compute_balance(saliency_map):
|
| 209 |
+
h, w = saliency_map.shape
|
| 210 |
+
left = saliency_map[:, :w // 2].mean()
|
| 211 |
+
right = saliency_map[:, w // 2:].mean()
|
| 212 |
+
top = saliency_map[:h // 2, :].mean()
|
| 213 |
+
bottom = saliency_map[h // 2:, :].mean()
|
| 214 |
+
horiz_diff = abs(left - right) / max(left + right, 1e-6)
|
| 215 |
+
vert_diff = abs(top - bottom) / max(top + bottom, 1e-6)
|
| 216 |
+
imbalance = (horiz_diff + vert_diff) / 2
|
| 217 |
+
score = round(max(0, 100 - imbalance * 200), 1)
|
| 218 |
+
return score
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
def balance_description(score):
|
| 222 |
+
if score >= 75:
|
| 223 |
+
return "well balanced - visual weight is evenly distributed"
|
| 224 |
+
elif score >= 50:
|
| 225 |
+
return "somewhat uneven - one side carries noticeably more visual weight"
|
| 226 |
+
else:
|
| 227 |
+
return "heavily lopsided - attention is pulled hard toward one side or corner"
|
| 228 |
+
|
| 229 |
+
|
| 230 |
def coverage_description(spread_score):
|
| 231 |
if spread_score < 15:
|
| 232 |
return "concentrated on one clear focal point - that's usually a good sign, not a problem"
|
|
|
|
| 236 |
return "spread fairly widely across the design"
|
| 237 |
|
| 238 |
|
| 239 |
+
def create_score_chart(focus_score, spread_score, readability_score, hierarchy_score=None, balance_score=None):
|
| 240 |
labels = ["Clear Focal\nPoint", "Attention\nCoverage"]
|
| 241 |
values = [focus_score, spread_score]
|
| 242 |
if readability_score is not None:
|
| 243 |
labels.append("Readability")
|
| 244 |
values.append(readability_score)
|
| 245 |
+
if hierarchy_score is not None:
|
| 246 |
+
labels.append("Visual\nHierarchy")
|
| 247 |
+
values.append(hierarchy_score)
|
| 248 |
+
if balance_score is not None:
|
| 249 |
+
labels.append("Balance")
|
| 250 |
+
values.append(balance_score)
|
| 251 |
colors = []
|
| 252 |
for v in values:
|
| 253 |
if v >= 75:
|
|
|
|
| 397 |
small_text_issues = 0
|
| 398 |
issue_lines = []
|
| 399 |
issue_boxes = []
|
| 400 |
+
text_sizes = []
|
| 401 |
for i in range(len(ocr_data['text'])):
|
| 402 |
word = ocr_data['text'][i].strip()
|
| 403 |
conf = int(ocr_data['conf'][i])
|
|
|
|
| 407 |
if w < 3 or h < 3:
|
| 408 |
continue
|
| 409 |
words_checked += 1
|
| 410 |
+
size_pct = (h / img_h) * 100
|
| 411 |
+
text_sizes.append(size_pct)
|
| 412 |
text_color, bg_color = sample_text_and_bg_color(img_arr, x, y, w, h)
|
| 413 |
if text_color is None:
|
| 414 |
continue
|
| 415 |
ratio = contrast_ratio(text_color, bg_color)
|
|
|
|
| 416 |
required_ratio = required_contrast_ratio(size_pct)
|
| 417 |
if ratio < required_ratio:
|
| 418 |
contrast_issues += 1
|
|
|
|
| 426 |
issue_lines.append(f"- \"{word}\" is a bit small to read comfortably")
|
| 427 |
issue_boxes.append({"box": (x, y, w, h), "label": "Small text"})
|
| 428 |
return {"words_checked": words_checked, "contrast_issues": contrast_issues,
|
| 429 |
+
"small_text_issues": small_text_issues, "issue_lines": issue_lines, "issue_boxes": issue_boxes,
|
| 430 |
+
"text_sizes": text_sizes}
|
| 431 |
|
| 432 |
|
| 433 |
def merge_issue_boxes(issue_boxes, gap=15):
|
|
|
|
| 623 |
total_score, grade = compute_overall_grade(scores['focus_score'], scores['spread_score'], readability_score)
|
| 624 |
grade_reason = explain_grade(scores['focus_score'], readability_score, read)
|
| 625 |
tips = generate_recommendations(saliency_map, scores, read, h, w)
|
| 626 |
+
hierarchy_result = compute_hierarchy(read.get('text_sizes', []))
|
| 627 |
+
balance_score = compute_balance(saliency_map)
|
| 628 |
+
hierarchy_score = hierarchy_result[0] if hierarchy_result else None
|
| 629 |
+
chart_image = create_score_chart(scores['focus_score'], scores['spread_score'], readability_score,
|
| 630 |
+
hierarchy_score, balance_score)
|
| 631 |
|
| 632 |
overlay_bgr = draw_scan_path(overlay_bgr, zones, h, w)
|
| 633 |
overlay_bgr = draw_zone_labels(overlay_bgr, zones, h, w)
|
|
|
|
| 670 |
for tip in tips:
|
| 671 |
summary += f"- {tip}\n"
|
| 672 |
|
| 673 |
+
summary += "\n**Layout & Composition:** *(based on classic layout principles - hierarchy and balance)*\n"
|
| 674 |
+
if hierarchy_result:
|
| 675 |
+
summary += f"- Visual Hierarchy: {hierarchy_description(hierarchy_result[1])}\n"
|
| 676 |
+
else:
|
| 677 |
+
summary += "- Visual Hierarchy: not enough distinct text elements to judge\n"
|
| 678 |
+
summary += f"- Balance: {balance_description(balance_score)}\n"
|
| 679 |
+
|
| 680 |
summary += (
|
| 681 |
"\n---\n"
|
| 682 |
"**Methodology:** Attention prediction combines MSI-Net, a peer-reviewed saliency model "
|
|
|
|
| 721 |
"- **No inflated claims.** A cited, transparent process instead "
|
| 722 |
"of a marketing number.\n"
|
| 723 |
"- **Scan-path arrows** show the predicted order attention flows, "
|
| 724 |
+
"not just isolated hotspots.\n"
|
| 725 |
+
"- **Grounded in classic layout theory** - checks visual hierarchy "
|
| 726 |
+
"and balance, principles used by professional designers for decades.\n\n"
|
| 727 |
"Coming soon: before/after comparisons."
|
| 728 |
)
|
| 729 |
with gr.Row():
|