A cost effective eye movement tracker based wheel chair control algorithm for people with paraplegia

Spinal cord injuries can often lead to quadriplegia in patients limiting their mobility. Wheelchairs could be a good proposition for patients, but most of them operate either manually or with the help of electric motors operated with a joystick. This, however, requires the use of hands, making it unsuitable for quadriplegic patients. Controlling eye movement, on the other hand, is retained even by people who undergo brain injury. Monitoring the movements in the eye can be a helpful tool in generating control signals for the wheelchair. This paper is an approach to converting obtained signals from the eye into meaningful signals by trying to control a bot that imitates a wheelchair. The overall system is cost-effective and uses simple image processing and pattern recognition to control the bot. An android application is developed, which could be used by the patients' aid for more refined control of the wheelchair in the actual scenario.

Selfie Detection by Synergy-Constraint Based Convolutional Neural Network

Categorisation of huge amount of data on the multimedia platform is a crucial task. In this work, we propose a novel approach to address the subtle problem of selfie detection for image database segregation on the web, given rapid rise in number of selfies clicked. A Convolutional Neural Network (CNN) is modeled to learn a synergy feature in the common subspace of head and shoulder orientation, derived from Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) features respectively. This synergy was captured by projecting the aforementioned features using Canonical Correlation Analysis (CCA). We show that the resulting network's convolutional activations in the neighbourhood of spatial keypoints captured by SIFT are discriminative for selfie-detection. In general, proposed approach aids in capturing intricacies present in the image data and has the potential for usage in other subtle image analysis scenarios apart from just selfie detection. We investigate and analyse the performance of popular CNN architectures (GoogleNet, AlexNet), used for other image classification tasks, when subjected to the task of detecting the selfies on the multimedia platform. The results of the proposed approach are compared with these popular architectures on a dataset of ninety thousand images comprising of roughly equal number of selfies and non-selfies. Experimental results on this dataset shows the effectiveness of the proposed approach.