Producing An Appropriate Glasses Based on Female Facial Features

Sei-Wo Winger TSENG

《管理資訊計算》 7卷1期 (2018/03) Pp. 23-31

https://doi.org/10.6285/MIC.201803_7(1).0003

摘要

In this paper, a neural network based approach for female eye glasses fitting suggestion is addressed in this article. The experimental results are analyzed by two stages of back-propagation neural network, which first categorize the Taiwan female faces, and then establish the relationships between adjective image words and female faces with different glasses. The data then is used to train two steps of back propagation application neural network for learning, computing, and approving in order to build a database for searching the proper female eyeglasses to fit their face. A fitting model for female glasses was then developed based on this database. With the aid of this glasses fitting system, a glasses store or a web based store can generate objective and professional fitting opinion to its female customers after a practical ophthalmic dispensing. Although the system is mainly designed for Taiwan female face, this method can be used to develop other countries or products.

關鍵字

Female facial features ； Eye glasses ； Kensei technology ； Neural network

參考文獻

Yeh, I.-C.,Wu, P.-J.(2009).Taguchi Method Based on Neural Networks and Cross Validation Methodology.Journal of Quality.16(4),261-279.

Information on www.paulsmith.co.jp.

Hertz, J.,Krough, A.,Palmer, R.G.(1991).Introduction to the Theory of Neural Computation.New York, USA:Addison-Wesley.

Hsiao, S.-W.,Tsai, H.C.(2002).A neural network based approach for product form design.Design Studies.23,67-84.

Li, q.z.(2005).Facial Anthropometric Dimensions of Taiwanese and Their Associations with Fit of Ophthalmic Frames, in Industrial management.Taipei:Taiwan University of Science and Technology.