Lifelog Moment Retrieval With Interactive Watershed-Based Clustering and Hierarchical Similarity Search

Abstract

Recently, the “lifelogging” and “lifelog” terminologies are frequently used to represent the activity of continuously recording people's everyday experiences, and the dataset contained these recorded experiences, respectively. Hence, providing an excellent tool to retrieve life moments from lifelogs to fast and accurately bring a memory back to a human when required, has become a challenging but exciting task for researchers. In this paper, a new method to meet this challenge by utilizing the hypothesis that “a sequence of images taken during a specific period can share the same context and content” is introduced. This manuscript per the authors introduces a new system to overcome the drawbacks. The experimental results confirm the high productivity of the proposed method in both stable and accuracy aspects as well as the advantage of having an interactive schema to push the accuracy when there is a conflict between a query and how to interpret such a query. Especially, this system requires only a few interactive steps to retrieve relevant images with high accuracy completely.