Image Classification Based on Light Convolutional Neural Network Using Pulse Couple Neural Network

Abstract

Recently, most image classification studies solicit the intervention of convolutional neural networks because these DL-based classification methods generally outperform other methodologies with higher accuracy. However, this type of deep learning networks require many parameters and have a complex structure with multiple convolutional and pooling layers depending on the objective. These layers compute a large volume of data and it may impact the processing time and the performance. Therefore, this paper proposes a new method of image classification based on the light convolutional neural network. It consists of replacing the feature extraction layers of standard convolutional neural network with a single pulse coupled neural network by introducing the notion of foveation. This module provides the feature map of input image and the data compression using Discrete Wavelet Transform which is an optional step depending on the information quantity of this signature. The fully connected neural network, which has six hidden layers, classifies the image. With this technique, the computation time is reduced, and the network architecture is identical and simple independent of the type of dataset. The number of parameter is less than that in current research. The proposed method was validated with different dataset such as Caltech-101, Caltech-256, CIFAR-10, CIFAR-100, and ImageNet, and the accuracy reaches 92%, 90%, 99%, 94%, and 91%, respectively, which are better than the previous related works.

Neural networks contribution in face mask detection to reduce the spread of COVID-19

“…For a gray-level image ( x , y ), let R i be ith segmented region, A i be the area of R i (that is the number of pixels contained in region R i ) and C be the normalization factor, then the gray-level uniformity measure of f ( x , y ) [ 24 ] is defined as in Eq. (8).…”

“…In a gray-level image f ( x , y ) consisting of the object with the average graylevel f O and the background with the average gray-level f b [ 24 ], a gray-level contrast measure can be calculated using Eq. ( 9 ).…”

“…( 11 )). The minimum cross entropy principle is used in image segmentation to search for the threshold which results in the least information difference between the two images before and after segmentation [ 24 ].…”

Comparison of Activation Functions in Convolutional Neural Network for Poisson Noisy Image Classification

“…In this layer, each neuron is connected to all neurons in the respective previous layer, this is referred to as the Fully Connected (FC) approach. It is used as a CNN classifier [29]. This layer follows the basic method of a conventional multi-layer perceptron neural network, as it is a type of Artificial Neural Network (ANN) so it is feed-forward in nature.…”

Refining tomato disease recognition: hyperparameter tuning on ResNet-101 architecture for precise leaf-based classification

“…ResNet constitute a convolutional network that has undergone training on a dataset exceeding 1 million images sourced from the ImageNet database [27] and ResNet-101 model boasts a pre-trained neural network capable of classifying images across 1,700 object categories, making it proficient in learning diverse and effective feature representations for various images. Our research brings notable contributions to the field, particularly in devising a novel CNN model tailored for the classification of diseases in tomato plants.…”