색상 및 형태 특성을 이용한 로고 영상의 기억용이성 측정 및 예측

• Published in: 멀티미디어학회논문지 Vol. 18; no. 12; pp. 1509 - 1518
• Main Authors: 오상일(Sang-Il Oh), 강행봉(Hang-Bong Kang)
• Format: Journal Article
• Language: Korean
• Published: 한국멀티미디어학회 2015
• Subjects: 전자/정보통신공학; Memorability; Prediction; Logo
• ISSN: 1229-7771; 2384-0102
• DOI: 10.9717/kmms.2015.18.12.1509

Because a logo is a medium that connects between consumers and corporations or brands, designing memorable logo images is vital. Although predicting logo's memorability for brand marketing is essential, there have been only few researches that deal with memorability of logo images. In this paper, we analyze the memorability characteristics in logo images by performing experiments based upon our proposed prediction method for logo image's memorability. Our proposed research consists of three phases: crowdsourcing for memorability computing, computational phase for logo image's memorability, and development of a prediction model. Using computed memorability of logo images by "Visual Memory Game," we analyze the different characteristics of logo's memorability. We first developed a novel computational method that reflects logo image's color and shape. Each computational method on color and shape are selected by comparing the correlations between result values and ground truth memorability. Selected computational value is then converged with generic image feature descriptors such as SIFT and HoG to make a prediction model of logo's memorability. Using our method, we obtain reasonable performances in predicting logo image's memorability.