Fabric Feature Extraction

Phase I: Proof of Concept

Action Result
Market Studies Creating daily video tutorials is the most effective way to reach customers. We use competitive pricing and sell similar products as a means to enter the market.
More detail:
Application of Website Crawlers for Competitor Analysis
Fabric/Product information As part of the preliminary setup of an in-house library, I implemented algorithms to automatically extract fabric features. This achieved processing speeds 12 to 63 times faster than human processing, with 98% accuracy. More details: Color Theme Extraction Based on the Bucket Sort Algorithm Repeated Pattern Detection of Printed Fabric Investigation of Algorithms for Retrieving Similar Images

Test

N: len(data): 4158 B: number of buckets: 36 T: number of predefined theme: 56 I: number of intervals in predefined theme: 3

Note: Human (baseline) is the average time of 100 consecutive process.

Original Image: 3500 x 4900 Resize Image: 100 x 140 B: number of buckets: 36 T: number of predefined theme I: number of intervals in predefined theme T * I = 22680 (4 theme) search color theme: 0.157sec search pattern size: 0.075sec Import + resize: 0.38sec + 0.2sec Total: 0.812 sec Human: 3 * 60 sec

Alan Hung (洪唯倫)
Alan Hung (洪唯倫)
Semiconductor Technologist
Intrapreneur | Project Manager | Data Analyst