Classification of Garments from Fashion MNIST Dataset Using CNN LeNet-5 Architecture

Kayed, Mohammed; Anter, Ahmed M.; Mohamed, Hadeer

doi:10.1109/itce48509.2020.9047776

Cited by 91 publications

(37 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We selected the most popular spectrums that are Audio Spectrum [16], Image Histogram [17], Demon [18] and LOFAR [19]. The datasets from related spectrum are input into LeNet [8] for training and testing. The experimental results show that the accuracy of LOFAR is much higher than the other three kinds of spectrum.…”

Section: Methodsmentioning

confidence: 99%

“…Fig. 6 shows the network architecture of LeNet [8]. LeNet has 7 layers, including 2 layers of convolution, 2 layers of pooling, and 3 layers of fully connected layers.…”

Section: Which Spectrum Is the Best?mentioning

confidence: 99%

“…Compared with machine learning methods, deep learning can extract deeper features of the image through a multi-level network and achieve higher precision in like classification on large datasets. The convolutional neural network proposed by [8] is the first multi-layer structure that uses spatial relative relationships to reduce the parameters and improve training performance. In 2012, deep convolutional neural networks were applied to ImageNet and achieved amazing results [9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Underwater acoustic signal analysis: preprocessing and classification by deep learning

Wu¹,

Song²,

Jin³

2020

NNW

View full text Add to dashboard Cite

The identification and classification is important parts of the research in the field like underwater acoustic signal processing. Recently, deep learning technology has been utilized to achieve good performance in the underwater acoustic signal case. On the other side, there are still some problems should be solved. The first one is that it cannot achieve high accuracy by the dataset that is transformed into audio spectrum. The second one is that the accuracy of classification on the dataset is still low, so that, it cannot satisfy the real demand. To solve those problems, we firstly evaluated four popular spectrums (Audio Spectrum, Image Histogram, Demon and LOFAR) for data preprocessing and selected the best one that is suitable for the neural networks (LeNet, ALEXNET, VGG16). Then, among these methods, we modified a neural network(LeNet) to fit the dataset that is transformed by the spectrum to improve the classification accuracy. The experimental result shows that the accuracy of our method can achieve 97.22 %, which is higher than existing methods and it met the expected target of practical application.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Fig. 6 shows the network architecture of LeNet [8]. LeNet has 7 layers, including 2 layers of convolution, 2 layers of pooling, and 3 layers of fully connected layers.…”

Section: Which Spectrum Is the Best?mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Underwater acoustic signal analysis: preprocessing and classification by deep learning

Wu¹,

Song²,

Jin³

2020

NNW

View full text Add to dashboard Cite

show abstract

“…In the case of group classification, either training from scratch or fine tuning is choices for researchers. Classification based on pre-training obtained a performance value of around 88 percent [10]. An assessment of preparing size effect on approval exactness for an upgraded CNN was presented in [11].…”

Section: Introductionmentioning

confidence: 99%

Pre-convoluted neural networks for fashion classification

Obaid

Jasim

2021

Bulletin EEI

View full text Add to dashboard Cite

In this work, concept of the fashion-MNIST images classification constructed on convolutional neural networks is discussed. Whereas, 28×28 grayscale images of 70,000 fashion products from 10 classes, with 7,000 images per category, are in the fashion-MNIST dataset. There are 60,000 images in the training set and 10,000 images in the evaluation set. The data has been initially pre-processed for resizing and reducing the noise. Then, this data is normalized for ensuring that all the data are on the same scale and this usually improves the performance. After normalizing the data, it is augmented where one image will be in three forms of output. The first output image is obtained by rotating the actual one; the second output image is obtained as acute angle image; and the third is obtained as tilt image. The new data set is of 180,000 images for training phase and 30,000 images for the testing phase. Finally, data is sent to training process as input for training model of the pre-convolution network. The pre-convolution neural network with the five layered convoluted deep neural network and do the training with the augmented data, The performance of the proposed system shows 94% accuracy where it was 93% in VGG16 and 92% in AlexNetnetworks.

show abstract

“…LeNet is characterized by the simplicity of its architecture, which is small in terms of memory capacity (light) and therefore low in computational complexity, making it excellent for use [14]. LeNet-5 is a very famous architecture in the field of object detection and image classification [15][16][17]. The traditional LeNet-5 consists of 7 layers including 3 convolutional layers, 3 subsampling layers, and a fully connected layer followed by an output layer.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Model for Traffic Sign Classification Based on Enhanced LeNet‐5 Network

2021

View full text Add to dashboard Cite

For several years, much research has focused on the importance of traffic sign recognition systems, which have played a very important role in road safety. Researchers have exploited the techniques of machine learning, deep learning, and image processing to carry out their research successfully. The new and recent research on road sign classification and recognition systems is the result of the use of deep learning-based architectures such as the convolutional neural network (CNN) architectures. In this research work, the goal was to achieve a CNN model that is lightweight and easily implemented for an embedded application and with excellent classification accuracy. We choose to work with an improved network LeNet-5 model for the classification of road signs. We trained our model network on the German Traffic Sign Recognition Benchmark (GTSRB) database and also on the Belgian Traffic Sign Data Set (BTSD), and it gave good results compared to other models tested by us and others tested by different researchers. The accuracy was 99.84% on GTSRB and 98.37% on BTSD. The lightness and the reduced number of parameters of our model (0.38 million) based on the enhanced LeNet-5 network pushed us to test our model for an embedded application using a webcam. The results we found are efficient, which emphasize the effectiveness of our method.

show abstract

Classification of Garments from Fashion MNIST Dataset Using CNN LeNet-5 Architecture

Cited by 91 publications

References 17 publications

Underwater acoustic signal analysis: preprocessing and classification by deep learning

Underwater acoustic signal analysis: preprocessing and classification by deep learning

Pre-convoluted neural networks for fashion classification

A Lightweight Model for Traffic Sign Classification Based on Enhanced LeNet‐5 Network

Contact Info

Product

Resources

About