16741a96d6
## New Features ### L'Oréal Static General Profile - Created new profile with 3 checks optimized for digital marketing assets - Even weighting (33.3% each) for 100-point scoring scale - Removed print-specific requirements (3m viewing distance) - Focus on marketing text vs product packaging distinction ### Multi-File Queue System (web_ui.html) - Added file queue functionality for batch processing - Users can now upload and process multiple files simultaneously - Queue displays file status (pending, analyzing, complete, error) - Individual file removal and queue clearing options - Progress tracking for batch operations ### New General QC Checks 1. background_contrast_general - Optimized for digital assets (no distance requirements) - Checks logo, product, and marketing text contrast - Detects overlapping and blending issues - Provides element-by-element breakdown 2. text_readability_general - Focus on marketing text only (excludes product packaging) - Checks for overlapping elements - Digital readability optimization - Specific issue identification 3. language_consistency (enhanced) - Better distinction between marketing and packaging text - Detailed language detection and reporting - Lists specific text analyzed ### Usage Tracking System - Added usage_tracker.py for analysis logging - Tracks user activity, profile usage, and costs - Daily log files in JSONL format - Cost estimation per LLM provider ## Bug Fixes ### Authentication & User Management - Fixed Flask 'g' import missing issue - Fixed user info access in background threads - Pass user_info to threads instead of accessing g.user - Improved error handling for usage logging ### HTML Report Generation - Fixed missing analysis details in reports - Now extracts and displays all JSON fields properly - Shows comprehensive breakdowns: - Analysis details - Elements checked (logo, product, text) - Marketing text found - Issues identified - Specific recommendations - No more blank "Pass/Fail" results ### Scoring System - Fixed usage_tracker to handle dict of check results (not list) - Better handling of model_used field variations - Skip non-dict check results gracefully ## Configuration Changes ### Model Versions (llm_config.py) - Fixed invalid GPT-4.1 model ID to gpt-4o - Added Gemini 3 Pro beta model option - AVAILABLE_MODELS dict for UI selection - Model version override support ### Profile Updates - Static General: 3 checks, total weight 10.0 - Each check: text_readability_general (3.33), background_contrast_general (3.33), language_consistency (3.34) - Maximum score: 100 points ## Technical Improvements - Enhanced prompt engineering for consistent LLM outputs - Mandatory detailed explanations in all checks - Structured JSON responses with comprehensive fields - Better error messages and fallback handling - Client configuration support (client_config.py) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
74 lines
3.6 KiB
Python
74 lines
3.6 KiB
Python
import os
|
|
import sys
|
|
|
|
# Add parent directory to path to import shared modules
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
|
|
|
|
from visual_qc_apps.flask_app_template import FlaskAppTemplate
|
|
|
|
class BackgroundContrastGeneralApp(FlaskAppTemplate):
|
|
"""
|
|
Background Contrast General Check - For Digital Assets
|
|
"""
|
|
|
|
def __init__(self):
|
|
# Define the hardcoded prompt
|
|
prompt = """You are conducting a visual quality control check on a digital marketing asset to verify that crucial design elements—including product images, the brand logo, and MARKETING TEXT (not text on product packaging)—stand out clearly from the background.
|
|
|
|
IMPORTANT: Focus on the MARKETING/ADVERTISING elements (headlines, slogans, calls-to-action), NOT the text printed on product packaging or labels.
|
|
|
|
EVALUATION STEPS:
|
|
1. Identify primary visual elements:
|
|
a. Brand logo (extra scrutiny for brand consistency and visibility).
|
|
b. Product shots or key imagery (overall product visibility, not text on packaging).
|
|
c. Main marketing text, headlines, slogans, and calls to action (NOT text on product packaging).
|
|
|
|
2. Check clarity and visibility:
|
|
a. Ensure each element is immediately recognizable and legible.
|
|
b. Verify that no elements are blending into or getting lost in the background.
|
|
c. Check for text overlapping with backgrounds or images that reduce visibility.
|
|
|
|
3. Evaluate color and brightness contrast:
|
|
a. Visually verify that each key element "pops" against the background.
|
|
b. Pay special attention to the brand logo. Any condition that makes the logo less than immediately recognizable is grounds for failing.
|
|
c. If any key element (product, marketing text, logo) is difficult to distinguish from the background, consider contrast insufficient.
|
|
|
|
4. Check for color conflicts:
|
|
a. Ensure marketing text doesn't blend with similar-colored backgrounds.
|
|
b. Verify that products are clearly visible against their background.
|
|
c. Confirm the logo maintains its visibility across the entire design.
|
|
d. Identify any text that overlaps with background elements, making it hard to read.
|
|
|
|
5. Assess overall visual hierarchy:
|
|
a. Important elements should stand out clearly.
|
|
b. Background should support, not compete with, key content.
|
|
|
|
PASS/FAIL CRITERIA:
|
|
• "Pass" only if ALL key marketing elements (logo, product, marketing text) are sharp, legible, and clearly distinct from the background.
|
|
• "Fail" if any single critical element has low contrast, appears to blend in, overlaps poorly with background, or is difficult to see against its background.
|
|
|
|
YOUR OUTPUT MUST INCLUDE:
|
|
• Detailed explanation of what you observed (which elements pass/fail and why)
|
|
• If it fails, specific recommendations for improvement
|
|
• Format your response as a JSON code block with the structure:
|
|
|
|
{
|
|
"background_contrast": "Pass" or "Fail",
|
|
"analysis_details": "Detailed explanation of what was checked and findings for logo, product, and marketing text",
|
|
"elements_checked": {
|
|
"logo": "Pass/Fail - Brief explanation",
|
|
"product": "Pass/Fail - Brief explanation",
|
|
"marketing_text": "Pass/Fail - Brief explanation"
|
|
},
|
|
"recommended_adjustments": "None (if Pass) OR specific recommendations to improve contrast (if Fail)"
|
|
}
|
|
|
|
CRITICAL: Always provide detailed analysis_details and element-by-element breakdown. Never return just "Pass" or "Fail" without explanation."""
|
|
|
|
# Initialize the Flask app with the prompt
|
|
super().__init__(__name__, prompt)
|
|
|
|
# Run the app if executed directly
|
|
if __name__ == "__main__":
|
|
app = BackgroundContrastGeneralApp()
|
|
app.run(debug=True)
|