TY - GEN
T1 - A cascade of deep learning fuzzy rule-based image classifier and SVM
AU - Angelov, Plamen Parvanov
AU - Gu, Xiaowei
N1 - Funding Information:
This work was supported by The Royal Society (Grant number IE141329/2014)
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/1
Y1 - 2017/12/1
N2 - In this paper, a fast, transparent, self-evolving, deep learning fuzzy rule-based (DLFRB) image classifier is proposed. This new classifier is a cascade of the recently introduced DLFRB classifier called MICE and an auxiliary SVM. The DLFRB classifier serves as the main engine and can identify a number of human interpretable fuzzy rules through a very short, transparent, highly parallelizable training process. The SVM based auxiliary plays the role of a conflict resolver when the DLFRB classifier produces two highly confident labels for a single image. Only the fundamental image transformation techniques (rotation, scaling and segmentation) and feature descriptors (GIST and HOG) are used for pre-processing and feature extraction, but the proposed approach significantly outperforms the state-of-art methods in terms of both time and precision. Numerical experiments based on a handwritten digits recognition problem are used to demonstrate the highly accurate and repeatable performance of the proposed approach.
AB - In this paper, a fast, transparent, self-evolving, deep learning fuzzy rule-based (DLFRB) image classifier is proposed. This new classifier is a cascade of the recently introduced DLFRB classifier called MICE and an auxiliary SVM. The DLFRB classifier serves as the main engine and can identify a number of human interpretable fuzzy rules through a very short, transparent, highly parallelizable training process. The SVM based auxiliary plays the role of a conflict resolver when the DLFRB classifier produces two highly confident labels for a single image. Only the fundamental image transformation techniques (rotation, scaling and segmentation) and feature descriptors (GIST and HOG) are used for pre-processing and feature extraction, but the proposed approach significantly outperforms the state-of-art methods in terms of both time and precision. Numerical experiments based on a handwritten digits recognition problem are used to demonstrate the highly accurate and repeatable performance of the proposed approach.
KW - Cascade classifiers
KW - Deep learning
KW - Fuzzy rule-based classifier
KW - Handwritten digits recognition
KW - SVM
UR - http://www.research.lancs.ac.uk/portal/en/publications/a-cascade-of-deep-learning-fuzzy-rulebased-image-classifier-and-svm(08213491-8e69-4c2d-a08b-bab918d15e5c).html
UR - http://www.scopus.com/inward/record.url?scp=85043377418&partnerID=8YFLogxK
U2 - 10.1109/SMC.2017.8122697
DO - 10.1109/SMC.2017.8122697
M3 - Conference Proceeding (Non-Journal item)
SN - 9781538616468
T3 - 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017
SP - 746
EP - 751
BT - 2017 IEEE International Conference on Systems, Man, and Cybernetics
PB - IEEE Press
ER -