A Color Extraction Method from Text for Use in Creating a Book Cover Image that Reflects Reader Impressions

• Published in: Knowledge, Information and Creativity Support Systems: Recent Trends, Advances and Solutions Vol. 364; pp. 201 - 211
• Main Authors: Iida, Takuya, Kajiyama, Tomoko, Ouchi, Noritomo, Echizen, Isao
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Advances in Intelligent Systems and Computing
• Subjects: Adjective; Artificial intelligence; Book cover image; Color extraction; Color psychology; User review
• ISBN: 331919089X; 9783319190891
• ISSN: 2194-5357; 2194-5365
• DOI: 10.1007/978-3-319-19090-7_16

The image on a book cover gives potential buyers not only an impression of the book’s contents but also a clue for search and browsing before or after buying the book. We propose using a color extraction method as the first step in automatically creating book cover images that reflect readers’ impressions. We constructed a database expressing the relationships between adjectives and colors and extracted colors from text such as sentences in the book and user reviews. In an experiment with 20 participants who were tasked with reading a book, writing a review of the book, and drawing an image of the book cover, we demonstrated that the colors extracted using this method were more consistent with the colors in the images drawn by the participants than the colors in the actual cover, especially for novels, regardless of the amount of text in the book.