Object Recognition & Optimization

In the field of image recognition, a method using deep learning has been successful. We are doing research to improve this recognition accuracy. We also propose an effective algorithm for the optimization problem, which is the core technology of image processing and computer vision.

Multimedia Lifelog : Foodlog

Our lab opens up a new research field called life log. Especially, we are trying research of food log and its social development, and made a system called FoodLog. We are focusing on analysis of trend estimation between users and individuals and image recognition using large scale data.

3D & Omnidirectional Image Processing

We are studying 3D images. Especially, we are conducting research on various city images.

Manga Image Processing

We are making media processing research for culture such as manga and animation. We are conducting research on automatic detection of objects in manga and constructed a dataset called Manga 109 for academic use.

Multimodal Processing

We are personalizing the saliency model, which now does not consider the characteristics of the observer. We are investigating the influence of observer's behavior and building a personalized model.

Attractiveness Computing

We are interested in analyzing why and how we are attracted to specific persons, content, and services. We have been trying to analyze and enhance such “attractiveness” in multimedia big data.

A New Domain of Machine Learning & Pattern Recognition

We developed a new algorithm in the field of machine learning and pattern recognition such as object detection, noise removal and image resolution improvement.

Application to Real World Problems

We are conducting research on how to apply machine learning and pattern recognition techniques to real world problems such as medical information processing and text chat analysis.