Interpolation aided fuzzy image classification

Yongfeng Zhang; Changjing Shang; Qiang Shen

doi:10.1109/FUZZ-IEEE.2015.7337903

Interpolation aided fuzzy image classification

Yongfeng Zhang, Changjing Shang, Qiang Shen

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

Abstract

This paper presents a novel application of interpolation in supporting fuzzy image classification. The recently introduced Deep Spatio-Temporal Inference Network (DeSTIN) is employed to carry out limited original feature extraction. A simple but effective linear interpolation is then used to artificially increase the dimensionality of the extracted feature sets for accurate classification, without incurring heavy computational cost. In particular, Fuzzy-Rough Nearest Neighbour (FRNN) and Fuzzy Ownership Nearest Neighbour (FRNN-O) are each utilised for image classification. The work is tested against the popular MNIST dataset of handwritten digits [1]. Experimental results indicate that the proposed approach is highly promising.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Publisher	IEEE Press
Pages	1-7
DOIs	https://doi.org/10.1109/FUZZ-IEEE.2015.7337903
Publication status	Published - 2015

Access to Document

10.1109/FUZZ-IEEE.2015.7337903

Permanent link

Persistent link

Cite this

@inproceedings{d5eb2c847120494b859246952aed1d7d,

title = "Interpolation aided fuzzy image classification",

abstract = "This paper presents a novel application of interpolation in supporting fuzzy image classification. The recently introduced Deep Spatio-Temporal Inference Network (DeSTIN) is employed to carry out limited original feature extraction. A simple but effective linear interpolation is then used to artificially increase the dimensionality of the extracted feature sets for accurate classification, without incurring heavy computational cost. In particular, Fuzzy-Rough Nearest Neighbour (FRNN) and Fuzzy Ownership Nearest Neighbour (FRNN-O) are each utilised for image classification. The work is tested against the popular MNIST dataset of handwritten digits [1]. Experimental results indicate that the proposed approach is highly promising.",

author = "Yongfeng Zhang and Changjing Shang and Qiang Shen",

year = "2015",

doi = "10.1109/FUZZ-IEEE.2015.7337903",

language = "English",

pages = "1--7",

booktitle = "IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)",

publisher = "IEEE Press",

address = "United States of America",

}

TY - GEN

T1 - Interpolation aided fuzzy image classification

AU - Zhang, Yongfeng

AU - Shang, Changjing

AU - Shen, Qiang

PY - 2015

Y1 - 2015

N2 - This paper presents a novel application of interpolation in supporting fuzzy image classification. The recently introduced Deep Spatio-Temporal Inference Network (DeSTIN) is employed to carry out limited original feature extraction. A simple but effective linear interpolation is then used to artificially increase the dimensionality of the extracted feature sets for accurate classification, without incurring heavy computational cost. In particular, Fuzzy-Rough Nearest Neighbour (FRNN) and Fuzzy Ownership Nearest Neighbour (FRNN-O) are each utilised for image classification. The work is tested against the popular MNIST dataset of handwritten digits [1]. Experimental results indicate that the proposed approach is highly promising.

AB - This paper presents a novel application of interpolation in supporting fuzzy image classification. The recently introduced Deep Spatio-Temporal Inference Network (DeSTIN) is employed to carry out limited original feature extraction. A simple but effective linear interpolation is then used to artificially increase the dimensionality of the extracted feature sets for accurate classification, without incurring heavy computational cost. In particular, Fuzzy-Rough Nearest Neighbour (FRNN) and Fuzzy Ownership Nearest Neighbour (FRNN-O) are each utilised for image classification. The work is tested against the popular MNIST dataset of handwritten digits [1]. Experimental results indicate that the proposed approach is highly promising.

UR - http://hdl.handle.net/2160/38789

U2 - 10.1109/FUZZ-IEEE.2015.7337903

DO - 10.1109/FUZZ-IEEE.2015.7337903

M3 - Conference Proceeding (Non-Journal item)

SP - 1

EP - 7

BT - IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

PB - IEEE Press

ER -

Interpolation aided fuzzy image classification

Abstract

Access to Document

Permanent link

Other files and links

Fingerprint

Cite this