Automatic Recognition of Rock Images Based on Convolutional Neural Network and Discrete Cosine Transform

Received: 10 April 2019 Accepted: 21 August 2019 This paper aims to overcome two major defects with the traditional rock image classification framework based on convolutional neural network (CNN), namely, slow training and poor classification accuracy. First, the causes of the two defects were analyzed in details. Through the analysis, the slow training is attributable to the information redundancy in the original image, and the classification error to the lack of differentiation of rock features extracted from the spatial domain. Therefore, the original image was divided into multiple blocks of equal size, and the discrete cosine transform (DCT) was introduced to process each block. After the transform, ten or fifteen frequency coefficients in the upper left corner of the 2D frequency coefficient matrix were retained, and added to the traditional CNN framework for image classification. Experimental results show that the proposed DCT-CNN framework outperformed the CNN framework in training time and classification accuracy.

[1]  Na Li,et al.  A transfer learning method for automatic identification of sandstone microscopic images , 2017, Comput. Geosci..

[2]  Bahadir Karasulu An Optimized Image Segmentation Approach Based on Boltzmann Machine , 2017, Appl. Artif. Intell..

[3]  V Nagi Reddy,et al.  Comparative analysis of breast cancer detection using K-means and FCM and EM segmentation techniques , 2018, Ingénierie des Systèmes d Inf..

[4]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[5]  Naresh Singh,et al.  Textural identification of basaltic rock mass using image processing and neural network , 2010 .

[6]  Ali Tavakoli,et al.  Modified algorithms for image inpainting in Fourier transform domain , 2018 .

[7]  Miodrag Djukic,et al.  An Automatic Instruction-Level Parallelization of Machine Code , 2018 .

[8]  Shihong Du,et al.  Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Chun Chen,et al.  Graph Regularized Sparse Coding for Image Representation , 2011, IEEE Transactions on Image Processing.

[10]  Raimondo Schettini,et al.  Deep Learning for Logo Recognition , 2017, Neurocomputing.

[11]  Hujun Yin,et al.  Image denoising using self-organizing map-based nonlinear independent component analysis , 2002, Neural Networks.

[12]  Wei Li,et al.  Diverse Region-Based CNN for Hyperspectral Image Classification , 2018, IEEE Transactions on Image Processing.

[13]  Richa Singh,et al.  Group sparse representation based classification for multi-feature multimodal biometrics , 2016, Inf. Fusion.

[14]  Babita Majhi,et al.  Reduced Feature Based Efficient Cancer Classification Using Single Layer Neural Network , 2012 .

[15]  Giles M. Foody,et al.  A relative evaluation of multiclass image classification by support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Xiaodong Yang,et al.  Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification , 2015, IEEE Transactions on Neural Networks and Learning Systems.