Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition

Convolutional neural networks typically employ convolutional layers for feature extraction and pooling layers for dimensionality reduction. However, conventional pooling methods often lead to a loss of critical feature information, particularly in images with diverse content, such as vehicle images....

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng-Jian Lin, Bing-Hong Chen, Chun-Hui Lin, Jyun-Yu Jhang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/24/3885
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060134530678784
author Cheng-Jian Lin
Bing-Hong Chen
Chun-Hui Lin
Jyun-Yu Jhang
author_facet Cheng-Jian Lin
Bing-Hong Chen
Chun-Hui Lin
Jyun-Yu Jhang
author_sort Cheng-Jian Lin
collection DOAJ
description Convolutional neural networks typically employ convolutional layers for feature extraction and pooling layers for dimensionality reduction. However, conventional pooling methods often lead to a loss of critical feature information, particularly in images with diverse content, such as vehicle images. This study proposes a novel approach to address these problems: a convolutional neural network with type-2 fuzzy-based pooling (CNN-T2FP). This innovative pooling method utilizes type-2 fuzzy membership functions to effectively manage local imprecision in feature maps. Compared with type-1 fuzzy pooling, which only addresses uncertainty to a certain extent, type-2 fuzzy pooling exhibits improved adaptability to different image contents. The experimental results of this study revealed that the CNN-T2FP achieved average accuracies of 92.14% and 93.34% on two datasets, surpassing the performance of existing pooling techniques. In addition, t-distributed stochastic neighbor embedding plots and feature visualization maps further highlighted the potential of type-2 fuzzy-based pooling to overcome the limitations of conventional pooling methods and enhance the performance of convolutional neural networks in image analysis tasks.
format Article
id doaj-art-1068a4fa3544427b8fea9788753dae17
institution DOAJ
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-1068a4fa3544427b8fea9788753dae172025-08-20T02:50:41ZengMDPI AGMathematics2227-73902024-12-011224388510.3390/math12243885Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle RecognitionCheng-Jian Lin0Bing-Hong Chen1Chun-Hui Lin2Jyun-Yu Jhang3Ph.D. Program, Prospective Technology of Electrical Engineering and Computer Science, National Chin-Yi University of Technology, Taichung 411, TaiwanPh.D. Program, Prospective Technology of Electrical Engineering and Computer Science, National Chin-Yi University of Technology, Taichung 411, TaiwanDepartment of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung 411, TaiwanDepartment of Computer Science and Information Engineering, National Taichung University of Science and Technology, Taichung 404, TaiwanConvolutional neural networks typically employ convolutional layers for feature extraction and pooling layers for dimensionality reduction. However, conventional pooling methods often lead to a loss of critical feature information, particularly in images with diverse content, such as vehicle images. This study proposes a novel approach to address these problems: a convolutional neural network with type-2 fuzzy-based pooling (CNN-T2FP). This innovative pooling method utilizes type-2 fuzzy membership functions to effectively manage local imprecision in feature maps. Compared with type-1 fuzzy pooling, which only addresses uncertainty to a certain extent, type-2 fuzzy pooling exhibits improved adaptability to different image contents. The experimental results of this study revealed that the CNN-T2FP achieved average accuracies of 92.14% and 93.34% on two datasets, surpassing the performance of existing pooling techniques. In addition, t-distributed stochastic neighbor embedding plots and feature visualization maps further highlighted the potential of type-2 fuzzy-based pooling to overcome the limitations of conventional pooling methods and enhance the performance of convolutional neural networks in image analysis tasks.https://www.mdpi.com/2227-7390/12/24/3885vehicle recognitiontype-2 fuzzy setconvolutional neural networkpooling operation
spellingShingle Cheng-Jian Lin
Bing-Hong Chen
Chun-Hui Lin
Jyun-Yu Jhang
Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
Mathematics
vehicle recognition
type-2 fuzzy set
convolutional neural network
pooling operation
title Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
title_full Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
title_fullStr Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
title_full_unstemmed Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
title_short Design of a Convolutional Neural Network with Type-2 Fuzzy-Based Pooling for Vehicle Recognition
title_sort design of a convolutional neural network with type 2 fuzzy based pooling for vehicle recognition
topic vehicle recognition
type-2 fuzzy set
convolutional neural network
pooling operation
url https://www.mdpi.com/2227-7390/12/24/3885
work_keys_str_mv AT chengjianlin designofaconvolutionalneuralnetworkwithtype2fuzzybasedpoolingforvehiclerecognition
AT binghongchen designofaconvolutionalneuralnetworkwithtype2fuzzybasedpoolingforvehiclerecognition
AT chunhuilin designofaconvolutionalneuralnetworkwithtype2fuzzybasedpoolingforvehiclerecognition
AT jyunyujhang designofaconvolutionalneuralnetworkwithtype2fuzzybasedpoolingforvehiclerecognition