Convolutional Neural Network-Assisted Adaptive Sampling for Sparse Feature Detection in Image and Video Data

In this article, we propose a feature detection approach that employs an adaptive sampling technique coupled with a convolutional neural network (CNN) model, to detect sparse features of interest in high-dimensional input data. Adaptive sampling criterion smartly explores the high-dimensional input and exploits the regions of interest. The CNN model determines the likelihood of the presence of the desired features, which guides the exploitation component of the sampling strategy. The effectiveness of the approach is illustrated using case studies, where emotions in a candidate's interview video are detected for evaluation purpose and anomalies in a product's image are extracted for quality control. The approach reduces evaluation time and minimizes amount of input data to be accessed and processed while effectively identifying desired sparse features.