The process of Apparel Product Development requires several major steps such as Pattern Digitizing, Grading, Marker Making, and Cutting Out. The current operation for Pattern Digitizing is conducted operators who amend apparel patterns on a computer after digitizing them based on a point-input method. The current process is laborious, time-consuming, and expensive due to error-prone work that leaves much to be desired in solution expansion.

These studies develop an automated system for apparel pattern input based on vectorising technique. Supporting industrial standardization (the detailed targets for the system development) minimizes the involvement of operators and include: automatic recognition of pattern domain, automatic recognition of sample shape, and inner part recognition performing apparel characteristic function.

The following picture shows an example using our system developed with a women bra pattern.
Figure 2 represents women a bra pattern
Figure 3 represents data implemented on the automated system we developed

The results of our study :
1. Analytical speed: under 4 seconds in resolution 150 dpi, image size A3.
2. Length error: under 0. 2mm.
3. Outline: 100% extract of outlines cutting and marker pattern.
4. Pattern elements: classification automatically and editing available by user.
5. Pattern division: try one acting scanning various pattern.
6. Data entry/output: converting of DXF, AAMA, TIP, DIGIT.

We developed an automated system based on vectorising software for implementation of apparel patterns. The cost of effective system repeatedly processes digitizing tasks with high quality in a few minutes. The system will contribute to the apparel industry field by implementing automatic steps for recognition and classification pattern.

• Hyang Ran Jeon(Howon University)
• Min Kyun Kim(Youth Hitec Co.)