Image Classification Combined with Fusion Gaussian–Hermite Moments Feature and Improved Nonlinear SVM Classifier
School of Electronics and Information Engineering, Hunan University of Science and Engineering
Building 130, Yangzitang Road, Lingling District, Yongzhou City, Hunan 425199, China
With the development of computer technology, data mining, artificial intelligence, and image-processing technology have been applied to medical diagnosis. Image classification is one of the main technologies of medical image processing, which can be used to determine whether a patient suffers from breast cancer according to x-ray images of the breast. To achieve reliable classification of breast images, an image classification method combined with a fusion Gaussian–Hermite moments feature and improved nonlinear support vector machine (SVM) classifier is proposed. The proposed fusion Gaussian–Hermite moments features can improve the robustness and distinguish the ability of features by constructing Gaussian–Hermite invariant moments according to invariant moment theory and constructing a Gaussian–Hermite Fisher moment according to Fisher’s idea. The proposed improved nonlinear SVM classifier can improve the efficiency and accuracy of the classifier through eigen decomposition and sample learning. Experimental results demonstrate that the proposed method has a high accuracy rate for breast x-ray image classification.
-  C. Zhao, J. Kanicki, A. C. Konstantinidis et al., “Large area CMOS active pixel sensor x-ray imager for digital breast tomosynthesis: Analysis, modeling, and characterization,” Medical Physics, Vol.42, No.11, pp. 6294-6308, 2015.
-  S. Sharma and P. Khanna, “Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM,” J. of Digital Imaging, Vol.28, No.1, pp. 77-90, 2015.
-  U. R. Acharya, V. K. Sudarshana, D. N. Ghista et al., “Computer-aided diagnosis of diabetic subjects by heart rate variability signals using discrete wavelet transform method,” Knowledge-Based Systems, Vol.81, pp. 56-64, 2015.
-  Q. Huang, F. Yang, L. Liu et al., “Automatic segmentation of breast lesions for interaction in ultrasonic computer-aided diagnosis,” Information Sciences, Vol.314, pp. 293-310, 2015.
-  B. Mohamed, A. Issam, A. Mohamed et al., “ECG Image Classification in Real time based on the Haar-like Features and Artificial Neural Networks,” Procedia Computer Science, Vol.73, No.5183, pp. 32-39, 2015.
-  T. Vo, D. Tran, and W. Ma, “Tensor decomposition and application in image classification with histogram of oriented gradients,” Neurocomputing, Vol.165, pp. 38-45, 2015.
-  S. Cvetkovic, B. Rajkovic, and S. Nikolic, “Real-time image classification using LBP and ensembles of ELM,” Vol.8, No.1, pp. 101-109, 2016.
-  B. Kumar and O. Dikshit, “Spectral–Spatial Classification of Hyperspectral Imagery Based on Moment Invariants,” IEEE J. of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.8, No.6, pp. 2457-2463, 2015.
-  D. R. Nayak, R. Dash, and B. Majhi, “Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests,” Neurocomputing, Vol.177, pp. 188-197, 2016.
-  B. Huo and F. Yin, “Research on Novel Image Classification Algorithm based on Multi-Feature Extraction and Modified SVM Classifier,” Int. J. of Smart Home, Vol.9, No.9, pp. 103-112, 2015.
-  K. Millard and M. Richardson, “On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping,” Remote Sensing, Vol.7, No.7, pp. 8489-8515, 2015.
-  C. Breen et al., “Ontology-based image classification using neural networks,” Proc. of SPIE - The Int. Society for Optical Engineering, Vol.4862, pp. 198-208, 2015.
-  H. Rezaeilouyeh, A. Mollahosseini, and M. H. Mahoor, “Microscopic medical image classification framework via deep learning and shearlet transform,” J. of Medical Imaging, Vol.3, No.4, pp. 501-512, 2016.
-  Y. Xu, Z. Jia, Y. Ai et al., “Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp. 947-951, 2015.
-  Y. Ioannou, D. Robertson, J. Shotton et al., “Training Convolutional Neural Networks with Low-rank Filters for Efficient Image Classification,” Int. Conf. on Learning Representations (ICLR), 2016.
-  B. Yang and M. Dai, “Image analysis by Gaussian–Hermite moments,” Signal Processing, Vol.91, No.10, pp. 2290-2303, 2011.
-  X. Guocheng, J. Yun, and C. Na, “New medical image classification approach based on hypersphere multi-class support vector data description,” J. of Computer Applications, Vol.33, No.11, pp. 3300-3304, 2013.
-  University of South Florida Digital Mammography Home Page, http://marathon.csee.usf.edu/Mammography/Database [accessed July 11, 2017]
-  B. O. Hua, M. A. Fu-Long, and J. Li-Cheng, “Research on Computation of GLCM of Image Texture,” Acta Electronica Sinica, Vol.1, No.1, pp. 155-158, 2006.
-  K. Huang and S. Aviyente, “Wavelet Feature Selection for Image Classification,” IEEE Trans. on image processing: a publication of the IEEE Signal Processing Society, Vol.17, No.9, pp. 1709-1720, 2008.
-  G. H. B. Miranda and J. C. Felipe, “Computer-aided diagnosis system based on fuzzy logic for breast cancer categorization,” Computers in Biology and Medicine, Vol.64, pp. 334-346, 2015.
-  G. Fatemeh, H. M. Sadegh, R. Mahmoud et al., “Fuzzy-based Medical X-Ray Image Classification,” J. of Medical Signals and Sensors, Vol.2, No.2, pp. 73-85, 2012.