diff --git a/CLAUDE.md b/CLAUDE.md index db9f478..1417dfb 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -678,6 +678,38 @@ All 4 defective assets correctly detected as Fail by both models. Previously "Mi - OpenAI scores background_contrast at 5/10 for "Missing text or in black" vs Gemini at 3/10 — OpenAI is more lenient on dark-on-dark product contrast. - "Text on top of image" text_readability scores 6-7 (borderline pass) — the text is actually reasonably legible (black on white), so this may be accurate. Main issue is the missing brand logo caught by background_contrast. +#### L'Oreal Prompt Tuning Round 2 (2026-04-07) +Prompts refined based on testing with 5 new assets — L'Oreal Professionnel Absolut Repair Molecular product range: + +**Test files location**: `/Users/nickviljoen/Desktop/AI_QC_Bitbucket/loreal/New Assets/AI QC test/` +**Reports location**: `/Users/nickviljoen/Desktop/AI_QC_Bitbucket/loreal/New Assets/reports3/` + +**Test files**: +| Test File | Type | Expected Result | +|---|---|---| +| LP-ARM_MASK_BELOWTHEFOLD_MODULE4_CARROUSEL4_COMMITMENTS...pt-PT.jpg | Marketing layout (Portuguese) with product | Pass | +| LP-ARM_SHAMPOO_BELOWTHEFOLD_MODULE4_CARROUSEL4_COMMITMENTS...pt-PT.jpg | Marketing layout (Portuguese) with product | Pass | +| LP-ARM_MASK_BELOWTHEFOLD_MODULE6_COMPARISONTABLE1_488X700_MULTIPLE_EAN.jpg | Product-only shot (mask jar) | Pass | +| LP-ARM_MASK_BELOWTHEFOLD_MODULE6_COMPARISONTABLE2_488X700_MULTIPLE_EAN.jpg | Product-only shot (leave-in bottle) | Pass | +| test.png | Kerastase products blending into light background (Hungarian) | Fail | + +**Issues found and fixes applied**: +1. **text_readability**: Product-only shots (no marketing text) were scoring 1-2/10 as "critical failure — text missing entirely." Fixed by adding a carve-out: product-only images with no marketing layout score 7/10 neutral with explanation "no marketing text to evaluate." Assets where marketing text SHOULD exist but is hidden/invisible still score 1-2. +2. **background_contrast**: Cream/light products on white backgrounds (standard cosmetics photography) were failing because the prompt had a rigid rule: "light-coloured products on light backgrounds = FAIL." Rewritten to focus on **actual visibility** — products pass if they have visual separation cues (shadows, edge definition, texture differences, contrasting elements like dark lids) even on similar-coloured backgrounds. Only fails if the product genuinely disappears into the background. +3. **UI fix**: Long filenames (common in L'Oreal asset naming) were overflowing the file queue container. Fixed with `overflow: hidden`, `text-overflow: ellipsis`, `min-width: 0` on queue items, and `word-break` on report filenames. + +**Current detection accuracy (2026-04-07, Gemini 3 Pro)**: + +| File | Score | Grade | Notes | +|---|---|---|---| +| MASK_COMMITMENTS (pt-PT) | 96.7 | Pass | Language 10, Contrast 10, Readability 9 | +| SHAMPOO_COMMITMENTS (pt-PT) | 93.3 | Pass | Language 10, Contrast 10, Readability 8 | +| COMPARISONTABLE2 (bottle) | 90.0 | Pass | Language 10, Contrast 10, Readability 7 (neutral) | +| COMPARISONTABLE1 (jar) | 86.7 | Pass | Readability 7 (neutral), Contrast 9, Language 10 | +| test.png (Kerastase) | 73.3 | Fail | Contrast 4 — products genuinely blend into background | + +All 4 good assets correctly pass. The defective asset (test.png) correctly fails due to poor product-background contrast. + ### Dow Jones QC Tools Dow Jones is a parent client with 3 sub-brands, each having its own QC profile with guidelines embedded in check prompts (sourced from live.standards.site scrapes, 2026-04-07). Test assets pending from client for prompt tuning. diff --git a/backend/CLAUDE.md b/backend/CLAUDE.md index 4eb88ae..99351a3 100644 --- a/backend/CLAUDE.md +++ b/backend/CLAUDE.md @@ -313,9 +313,12 @@ The system includes 12 focused QC profiles designed for different use cases: - Purpose: Diageo packaging design standards - Requirements: Brand guidelines recommended -7. **L'Oreal Static** (2 checks) - - Purpose: Focused L'Oreal QC with language consistency and visual readability/contrast - - Checks: language_consistency, visual_readability_contrast +7. **L'Oreal Static** (3 checks, 100-point scale) + - Purpose: Focused L'Oreal QC for digital static marketing materials + - Checks: language_consistency, text_readability, background_contrast + - Scoring: Equal weight distribution (3.33 each), any individual check <6 = overall Fail + - Note: text_readability scores 7/10 neutral for product-only shots (no marketing text) + - Note: background_contrast focuses on actual visibility, not theoretical colour similarity 8. **Amazon Static** (6 checks, 100-point scale) - Purpose: Amazon ASD 2025 design guidelines compliance