A review of convolutional neural networks and gabor filters in object recognition
Convolutional neural networks (CNNs) have become a classic approach to solving
challenging computer vision problems. Much of its success is due to its ability to discover …
challenging computer vision problems. Much of its success is due to its ability to discover …
GaborNet: Gabor filters with learnable parameters in deep convolutional neural network
A Alekseev, A Bobe - 2019 International Conference on …, 2019 - ieeexplore.ieee.org
The article describes a system for image recognition using deep convolutional neural
networks. Modified network architecture is proposed that focuses on improving convergence …
networks. Modified network architecture is proposed that focuses on improving convergence …
Rotation invariant Gabor convolutional neural network for image classification
X Yao, T Song - Pattern Recognition Letters, 2022 - Elsevier
Gabor filters have been recently integrated with deep convolutional neural networks to learn
better features with fewer model parameters. However, during feature learning the rotation …
better features with fewer model parameters. However, during feature learning the rotation …
Maintaining filter structure: A Gabor-based convolutional neural network for image analysis
S Molaei, MESA Abadi - Applied Soft Computing, 2020 - Elsevier
In image segmentation and classification tasks, utilizing filters based on the target object
improves performance and requires less training data. We use the Gabor filter as …
improves performance and requires less training data. We use the Gabor filter as …
Gabor convolutional networks
In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of
a set of “basis filters.” Steerable properties dominate the design of the traditional filters, eg …
a set of “basis filters.” Steerable properties dominate the design of the traditional filters, eg …
Hybrid gabor convolutional networks
Despite great effectiveness of very wide and deep convolutional neural networks (DCNNs)
in various computer vision tasks, the significant cost in terms of storage requirement of such …
in various computer vision tasks, the significant cost in terms of storage requirement of such …
Gabor binary layer in convolutional neural networks
C Jiang, J Su - 2018 25th IEEE International Conference on …, 2018 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have achieved overwhelming success in image
recognition. For all the architectures of CNNs, the low-level features extracted from the input …
recognition. For all the architectures of CNNs, the low-level features extracted from the input …
Energy-efficient Gabor kernels in neural networks with genetic algorithm training method
F Meng, X Wang, F Shao, D Wang, X Hua - Electronics, 2019 - mdpi.com
Deep-learning convolutional neural networks (CNNs) have proven to be successful in
various cognitive applications with a multilayer structure. The high computational energy …
various cognitive applications with a multilayer structure. The high computational energy …
Global filter networks for image classification
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision
have shown great potential in achieving promising performance with fewer inductive biases …
have shown great potential in achieving promising performance with fewer inductive biases …
Gabor filter assisted energy efficient fast learning convolutional neural networks
Convolutional Neural Networks (CNN) are being increasingly used in computer vision for a
wide range of classification and recognition problems. However, training these large …
wide range of classification and recognition problems. However, training these large …