Statement
An interesting perspective is the relation between the manifold learning theory and graph embedding and how this will reflect on a feature matching and many other computer vision problems. The Work in the manifold learning theory includes techniques for dimensionality reduction; most of these techniques approximate the manifold by a graph to be embedded to a lower dimensionality space. As an example same reasoning can be applied to the problem of feature matching. The feature points of input images can be represented as a graph and hence can be embedded to a lower dimensionality space.

Not only the feature matching problem can be solved using the graph embedding, but also the object recognition and detection can be exploited. Exploring the relations, limitations and applications to the computer vision community is the core interest of my research.

My current research includes

Feature Matching

·We have developed a new framework for feature matching between multiple point sets depending on the spatial arrangement in each set and the feature similarity across different sets. CVPR2010.

One-Shot Multi-Set Non-rigid Feature-Spatial Matching

Object Recognition and Detection

• Using a novel framework for embedding feature points from different images into the same coordinate system. The embedding framework preserves the spatial arrangement in each image and the feature similarity across different images.
• Kernel functions between images are established using the coordinates computed.
• To deal with large number of features and large number of images an out-of-sample embedding is performed in a way that suits the object recognition context. CVPR2010.

Putting Local Features on a Manifold

Decision Support for Smart Trauma-Resuscitation Room TRU-IT: Trauma Resuscitation Unit -- Information Technology
Project web page
My role in the Project

·I helped in designing the environment that enable us to use the Stereo vision for applications of object detection and tracking objects that participate in the room.

·I helped in developing tracker for faces by working in the face detection step including training classifiers using Haar features.

·I am advising a master student working on multi-object tracker using the stereo vision PTGREY Camera