Data Distribution-based Curriculum Learning

The order of training samples can have a significant impact on the performance of a classifier. Curriculum learning is a method of ordering training samples from easy to hard. This paper proposes the novel idea of a curriculum learning approach called Data Distribution-based Curriculum Learning (DDCL). DDCL uses the data distribution of a dataset to build a curriculum based on the order of samples. Two types of scoring methods known as DDCL (Density) and DDCL (Point) are used to score training samples thus determining their training order. DDCL (Density) uses the sample density to assign scores while DDCL (Point) utilises the Euclidean distance for scoring. We evaluate the proposed DDCL approach by conducting experiments on multiple datasets using a neural network, support vector machine and random forest classifier. Evaluation results show that the application of DDCL improves the average classification accuracy for all datasets compared to standard evaluation without any curriculum. Moreover, analysis of the error losses for a single training epoch reveals that convergence is faster when using DDCL over the no curriculum method.

Design of a Mobile Face Recognition System for Visually Impaired Persons

It is estimated that 285 million people globally are visually impaired. A majority of these people live in developing countries and are among the elderly population. One of the most difficult tasks faced by the visually impaired is identification of people. While naturally, voice recognition is a common method of identification, it is an intuitive and difficult process. The rise of computation capability of mobile devices gives motivation to develop applications that can assist visually impaired persons. With the availability of mobile devices, these people can be assisted by an additional method of identification through intelligent software based on computer vision techniques. In this paper, we present the design and implementation of a face detection and recognition system for the visually impaired through the use of mobile computing. This mobile system is assisted by a server-based support system. The system was tested on a custom video database. Experiment results show high face detection accuracy and promising face recognition accuracy in suitable conditions. The challenges of the system lie in better recognition techniques for difficult situations in terms of lighting and weather.