MobileNetV2 Model for Image Classification

Ismail

Wireless Communications and Mobile Computing

et al. 2022

The rapid spreading of Coronavirus disease 2019 (COVID-19) is a major health risk that the whole world is facing for the last two years. One of the main causes of the fast spreading of this virus is the direct contact of people with each other. There are many precautionary measures to reduce the spread of this virus; however, the major one is wearing face masks in public places. Detection of face masks in public places is a real challenge that needs to be addressed to reduce the risk of spreading the virus. To address these challenges, an automated system for face mask detection using deep learning (DL) algorithms has been proposed to control the spreading of this infectious disease effectively. This work applies deep convolution neural network (DCNN) and MobileNetV2-based transfer learning models for effectual face mask detection. We evaluated the performance of these two models on two separate datasets, i.e., our developed dataset by considering real-world scenarios having 2500 images (dataset-1) and the dataset taken from PyImage Search Reader Prajna Bhandary and some random sources (dataset-2). The experimental results demonstrated that MobileNetV2 achieved 98 % and 99 % accuracies on dataset-1 and dataset-2, respectively, whereas DCNN achieved 97 % accuracy on both datasets. Based on our findings, it can be concluded that the MobileNetV2-based transfer learning model would be an alternative to the DCNN model for highly accurate face mask detection.

Section: Mobilenetv2mentioning

confidence: 99%

Face Mask Detection Using Deep Convolutional Neural Network and MobileNetV2-Based Transfer Learning

Ismail

Wireless Communications and Mobile Computing

et al. 2022

“…The final layer of this model belongs to the categorization level. The MobileNetV2 [25] network was customised for our purposes. Size of the filter together with padding and changing the pace makes the network reliable or suitable for small images.…”

Section: Mobilenetv2mentioning

confidence: 99%

A Land Use Land Cover Map Generation of Satellite Image Using Deep Learning Techniques

M¹,

K²,

G³

et al. 2022

INDJCSE

Land use land cover (LULC) usually alludes to the assortment and cataloging of certain activities carried out by humans together with the natural elements on the land. Sentinel satellite images are meant to obtain optical images at high spatial resolution say of about 10m. In this paper, LULC map generation approach using Sentinel satellite images is proposed. Our objective is to classify the entire sentinel image to generate LULC map, which can be further used for predictive analysis. Here, we have used three predominant bands namely NIR, Red and Green to classify the sentinel data with five classes namely Water, Forest, Vegetation, Urban and Open land of silicon city of India. For the proposed dataset, an inclusive exactness of 95% was achieved with neural networks and various deep convolutional neural network architectures.

“…This research approached to compare the performance of MobileNetV1 and MobileNetV2 with several datasets from TensorFlow. The result represented that performance of MobileNetV2 was higher than MobileNetV1 [22]. MobileNetV2 model was used as a base of N-MobileNetV2 to classify various kinds of flowers.…”

Section: Introductionmentioning

confidence: 98%

Lotus species classification using transfer learning based on VGG16, ResNet152V2, and MobileNetV2

Rachburee

Punlumjeak

2022

IJ-AI

Technology has played an increasingly important role in daily life. Especially, technology in object classification that comes in to make human life more comfortable as well as to help people of all ages learning unlimited in anywhere, anytime. Lotus Museum located in Rajamangala University of Technology Thanyaburi (RMUTT) that is open to the general public to learn as well as to cultivate awareness for propagation and result in future preservation. In this paper, we proposed lotus species classification with three pre-trained weights in the ImageNet dataset: visual geometry group (VGG16), residual neural network (ResNet152V2), and MobileNetV2. Fine-turning is used in the last layer after retrained with the custom data we provided. The experimental result shows the accuracy of VGG16, ResNet152V2, and MobileNetV2 are 98.5%, 98.0%, and 99.5% respectively. Therefore, MobileNetV2 not only gives the best accuracy than others but also uses the lowest parameters which are effective in computation time and proper to mobile devices. The proposed research paper on lotus classification base on transfer learning is an effective way to encourage and support people to learn without limitations.