Neural Architecture Search Net-Based Feature Extraction With Modular Neural Network for Image Classification of Copper/ Cobalt Raw Minerals

Abstract

Image processing is one of the most quickly evolving technologies today and it is an approach for applying operations on an image to improve it or extract relevant information from it. It is a critical research field in engineering and computer science. However, analyzing a high number of variables demands a lot of memory and processing resources, and it can cause a classification algorithm to overfit on training samples and underfit on test samples. As a result, various strategies, such as extraction can be used to reduce the number of features in a dataset by producing new ones from old ones. In this paper, we firstly propose a deep learning-based feature extraction approach with a modular neural network where we employ a pre-trained network, neural architecture search net (NASNet), as a feature extractor on a custom dataset of raw minerals of copper and cobalt images. It allows the input image to be feed-forwarded while performing feature learning and feature map, then stopping at a pooling layer before the fully connected (FC) layer in the NASNet to extract and save the outputs of that layer in dumped files. Secondly, the extracted features are then used as training data to build a deep neural network and machine learning algorithms for the image classification of copper and cobalt raw minerals. The experimental results show that the NASNet extracts the features efficiently, and the proposed modular neural network performs well with the boosting-decision tree as a classifier, which gives higher accuracy of 91% than 90% of the deep neural network; moreover, the precision is 1 higher than 0.98 for the deep neural network.