Color Selection System Based on Linear Regression and ANN

Color Selection System Based on Linear Regression and ANN

Avalone Neto, Olavo; Cenci, Laline Elisangela; Pires, Júlio César Pinheiro

Full Article:

Color selection is one of several abilities necessary for architectural design. This study presents a web-based JavaScript application capable of foreseeing a color scheme combination that matches a client’s choice pattern based on previous choices made by them. It uses linear regression and Adapted Artificial Neural Network (ANN) for color and shade selection. First, it estimates users’ choice patterns through least mean squares and applies that in the generation of other patterns. It then considers the least square means through a weight factor for the training stage. This study presents the validation of the first process and the correlation between the application’s estimated results and users’ color match expectations. 81.9% of participants found estimated responses to be similar or very similar to the choices they would make; 88% found usage intuitive or very intuitive, and 88.6% agrees the application has some utility to their professional life.

Color selection is one of several abilities necessary for architectural design. This study presents a web-based JavaScript application capable of foreseeing a color scheme combination that matches a client’s choice pattern based on previous choices made by them. It uses linear regression and Adapted Artificial Neural Network (ANN) for color and shade selection. First, it estimates users’ choice patterns through least mean squares and applies that in the generation of other patterns. It then considers the least square means through a weight factor for the training stage. This study presents the validation of the first process and the correlation between the application’s estimated results and users’ color match expectations. 81.9% of participants found estimated responses to be similar or very similar to the choices they would make; 88% found usage intuitive or very intuitive, and 88.6% agrees the application has some utility to their professional life.

Palavras-chave:

DOI: 10.5151/sigradi2021-97

Referências bibliográficas

• [1]

Como citar:

Avalone Neto, Olavo; Cenci, Laline Elisangela; júlio pires; "Color Selection System Based on Linear Regression and ANN", p-327-338. In: XXV International Conference of the Iberoamerican Society of Digital Graphics. São Paulo: Blucher, 2021.
ISSN 23186968, DOI 10.5151/sigradi2021-97