Over the past 20 years, the web has transformed from a tool for the scientists at CERN to an information access centre for the world to a platform where people can get things done. Web 2.0 is this transition from the web being a static information access point to a dynamic, customizable and social platform. IIL contributes to this transformation of the web. We are currently working on one extension of Web 2.0, viz. Travel 2.0 where we aim at building technological revolutions in the travel industry. Travel 2.0 is all about “empowering” the user and enabling them to share information online that can be accessed by other travellers. We take the information to the traveller, rather than them searching for it.

Hyper Resolution

Hyper-Resolution, a new technique for super-resolution reconstruction of images, is based on matching low-resolution target image details to their high-resolution counterparts from an image database. Central to the algorithm is a novel transform of image content from the orthogonal pixel space to a parametric space structured around edges. This approach offers improved quality, more flexibility and significantly faster performance than previous work in the field.

3D Face Recognition

Human faces are remarkably similar in global properties, including size, aspect ratio, and location of main features, but can vary considerably in details across individuals, gender, race, or due to facial expression. 3D face recognition has the potential to achieve better accuracy than its 2D counterpart by measuring geometry of rigid features on the face. This avoids such pitfalls of 2D face recognition algorithms as change in lighting, different facial expressions, make-up and head orientation.

Emotion Recognition and Synthesis

In today’s world, there is need for more natural user interfaces for the overwhelmed computer users. Given that humans communicate with each other by using not only speech but also implicitly their facial expressions and body postures, machines that can understand human emotions and display affects through these multi-modal channels could be beneficial. If virtual agents and robots are able to recognize and express their emotions through these channels, the result of that will be more natural human-machine communication. This will allow human users to focus more on their tasks at hand.

Object Detection and Tracking

The project requires development of an automatic image analysis tool that will recognize object classes and determine the trajectory of their motions. In order to perform this task, knowledge of the object class is required which will be through supervised learning using training sets. Object classes will be pre-defined; also the system should be able to learn new objects on-line. The recognition algorithm should be invariant to occlusion, illumination, scale, rotation and viewpoint variations. On successful detection, the system should be able to track the objects and make note of their trajectories.

3D Object Recognition

Since RGB-D sensors are becoming cheaper and more easily available, they are being preferred for solving most of the problems faced in robotics pertaining to recognition/interaction with real world objects and motion planning. The aim of the project is to create an object recognition system using 3D point cloud data acquired using a RGB-D sensor such as Kinect. The 3D data acquired by such a sensor gives greater information about the shape, distance and pose of an object, hence allowing us to more accurately identify the object. The system will make use of a database of 3D models to identify objects in the 3D sensor data.