Accumulative image categorization: a personal photo classification method for progressive collection

摘要

With the explosive growth of personal photos, an effective classification tool is becoming an urgent need to organize our progressive image collections. Facing the dynamically growing collections, we present a new method to categorize images effectively by integrating image clustering, incremental updating and user feedback together in an online framework. Considering the user burden and the user-specific preference during image classification, we propose several strategies to learn a customized classification model progressively for each user. Firstly, we use a multi-view learning method to learn the preferred classification perspective of the user. Secondly, we cluster similar images into groups according to user's preference, so that images in a group can be categorized simultaneously with high efficiency. Thirdly, we propose a multi-centroid nearest class mean classifier to online learn the user's preferred category granularity, and use it to classify the image groups. Unlike offline systems where pre-labeling and batch training often take hours or even days to perform, our approach is fully online. It can learn the classification model and classify newly acquired images alternately in no time. The sufficient experimental results and a user study demonstrate the effectiveness of the proposed method.