Automatic Recognition of Coal and Gangue based on Convolution Neural Network

TL;DR

This paper presents a convolutional neural network-based system for automatic recognition of coal and gangue, utilizing data enhancement, transfer learning, and object detection to improve accuracy over traditional methods.

Contribution

The study introduces a CNN model based on AlexNet with data augmentation and transfer learning, and an object detection algorithm for optimized training data, improving recognition accuracy.

Findings

Higher recognition rate than traditional neural network and SVM algorithms

Effective data augmentation and transfer learning strategies

Improved object detection for training data optimization

Abstract

We designed a gangue sorting system,and built a convolutional neural network model based on AlexNet. Data enhancement and transfer learning are used to solve the problem which the convolution neural network has insufficient training data in the training stage. An object detection and region clipping algorithm is proposed to adjust the training image data to the optimum size. Compared with traditional neural network and SVM algorithm, this algorithm has higher recognition rate for coal and coal gangue, and provides important reference for identification and separation of coal and gangue.