Private photo recommendation system for in-person conversation

Abstract

Mobile devices equipped with cameras, such as smartphones, have become extremely popular in recent years, and have motivated users to capture an increasing number of digital photos in their daily lives. Users often invoke these photos during in-person interactions or conversations with others. In the context of a conversation between two people related to or involving reference to a photo, one of them might be inclined to show the photograph on his/her smartphone. However, it is difficult for users to search for a photo that they want to reference in the brief period during a conversation for which it might be relevant. Hence, in this study, we propose a system that shows users the photos relevant to the topic that they want to discuss in a given conversation according to their preferences. In the method of ranking photos used in our system, the index of the adequacy of a photo in the context of a conversation is defined as the degree of similarity to the photo that is used in the current conversation. Photos on each user's device are sorted by their degree of similarity with a given photo. We show that there is a strong relationship between our proposed ranking and those based on subjective assessment tasks, and confirmed the effectiveness of our system through experiments involving seven subjects.