A Computer Vision Methodology to Predict Brand Personality from Image Features

被引：5

作者：

Wen, Taylor Jing ^{[1
,4
,5
]}

Peng, Yilang ^{[2
,6
]}

Yang, Jing ^{[3
,7
]}

机构：

[1] Univ South Carolina, Columbia, SC USA

[2] Univ Georgia, Athens, GA USA

[3] Loyola Univ Chicago, Chicago, IL USA

[4] Univ South Carolina, Sch Journalism & Mass Commun, Coll Informat & Commun, Room 331, 800 Sumter St, Columbia, SC 29208 USA

[5] Univ South Carolina, Coll Informat & Commun, Sch Journalism & Mass Commun, Columbia, SC USA

[6] Univ Georgia, Dept Financial Planning Housing & Consumer Econ, Athens, GA USA

[7] Loyola Univ Chicago, Sch Commun, Chicago, IL USA

来源：

JOURNAL OF ADVERTISING | 2024年 / 53卷 / 04期

关键词：

VISUAL COMPLEXITY; COLOR; DESIGN; PERCEPTIONS; BEAUTY;

D O I：

10.1080/00913367.2023.2250842

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

Using the computer vision method, this study proposes an analytical model of visual aesthetics for brand communication and analyzes the effects of visual features (i.e., colors and visual complexity) on brand personality. This study illustrates a four-step procedure correlating computationally coded visual attributes with human ratings of perceived brand personality. This study has important methodological implications for advertising researchers and practitioners.

引用

页码：626 / 638

页数：13

共 54 条

[1] When good brands do bad [J].