語言導向色彩意象辨識與商品設計應用(I)

Project: Government MinistryMinistry of Science and Technology

Project Details

Description

The decision of color image is a key step of product design. The automatic or semi-automatic design assistance are becoming more and more important, under the trend of more and more diversified customization and real-time design requirements. This project proposes a possible solution to the design for requirements of such a new type. Firstly, a color image recognition algorithm, based on artificial intelligence and machine learning; will be deigned to analyze the non-professional requirement description from general customers, to identify the terms of color images used by professional designers conventionally. Such identification result automatically generates color combinations that meets the customer's original needs and forms a complete color scheme during design process. A prototype application system of automatic color scheme for product design will be developed. This study applies the color image (Kobayashi, 2006) listed in the Color Image Scale (Kobayashi, 1991) as a design parameter to develop a "color image extraction algorithm" and "multi-images color harmony algorithm" to establish a "parameterized color image and color scheme system". In order to verify the effectiveness of the two algorithms and the system, using questionnaires to evaluate the effectiveness of the methods. In summary, the "multi-images color harmony algorithm" and the " parameterized color image and color scheme system " can provide the conversion requirements for language and color scheme, it is highly feasible in the correspondence between color images and color scheme.
StatusFinished
Effective start/end date2019/08/012020/12/31

Keywords

  • color image
  • natural language processing
  • word embedding
  • word2vec model
  • artificial intelligence
  • color scheme
  • product design

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.