AFDL: a new adaptive fuzzy dictionary learning for medical image classification
- PDF / 3,066,412 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 197 Views
THEORETICAL ADVANCES
AFDL: a new adaptive fuzzy dictionary learning for medical image classification Majid Ghasemi1 · Manoochehr Kelarestaghi2 · Farshad Eshghi2 · Arash Sharifi1 Received: 7 August 2019 / Accepted: 5 September 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Sparse coding allows the representation of complex data as a linear combination of basis sparse vectors (alternatively called atoms or codewords), a collection of which constitutes a dictionary. Dictionary learning is a learning process aimed at finding a small number of optimal basis vectors for a more accurate representation of the original data. The existing dictionary learning methods do not address the inherent uncertainty of the input data in their learning processes. To compensate for the uncertainty, and to obtain a flexible and effective learning system, we introduce a new adaptive fuzzy dictionary learning (AFDL) method for image classification purposes. The new method iteratively alternates between sparse coding based on a given dictionary and an adaptive fuzzy dictionary learning approach to learn (improve) dictionary atoms. The adjustability of the dictionary and coefficients vectors, in this method, provide us a more accurate and straight representation of input data. AFDL was applied on magnetic resonance images from the cancer image archive datasets, for medical image classification of cancer tumors. Finally, the overall experimental results clearly show that our approach outperforms its rival techniques in terms of accuracy, sensitivity, and specificity. Convergence speed in the experimental results shows that AFDL can achieve its acceptable precision in a reasonable time. Keywords Sparse coding · Adaptive fuzzy dictionary learning · Medical image classification · Sparse representation
1 Introduction It has been demonstrated that sparse coding is an efficient method in different classification problems [39, 87, 88]. The sparse coding can approximate high-dimensional image features by decomposing a feature vector into a linear combination of a small set of basis elements. The latter is done by finding a minimal set of dictionary items that can adequately represent the image and signal data. Also, it is well * Manoochehr Kelarestaghi [email protected] Majid Ghasemi [email protected] Farshad Eshghi [email protected] Arash Sharifi [email protected] 1
Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Department of Electrical and Computer Engineering, Faculty of Engineering, Kharazmi University, Tehran, Iran
2
understood that learning a dictionary using training images would lead to more precise results in classification and pattern recognition tasks. However, in classification tasks, by learning a specific dictionary for each class using robust algorithms, more accurate sparse representations will be obtained. On the other hand, an accurate method that automatically classifies medical images into some various categories can
Data Loading...
