A Framework for Anomaly Classification Using Deep Transfer Learning Approach

Jayaswal, Ruchi; Dixit, Manish

doi:10.18280/ria.350309

Cited by 17 publications

(21 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All other modules are ringed by straight residual connections, except the first and last. Collet 18 described the Xception 19 architecture as a straight stack of depth wise‐separable convolutions with feedback connections when trained on the ImageNet dataset.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

A face mask detection system: An approach to fight with COVID‐19 scenario

Jayaswal

Dixit²

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

A new coronavirus has caused a pandemic crisis around the globe. According to the WHO, this is an infectious illness that spreads from person to person. Therefore, the only way to avoid this infection is to take precautions. Wearing a mask is the most critical COVID-19 protection method because it prevents the virus from spreading from an infected person to a healthy one. This study reflects a deep learning method to create a system for detecting Face Masks. The paper proposes a unique FMDRT (Face Mask Dataset in Real-Time) dataset to determine whether a person is wearing a mask or not. The RFMD and Face Mask datasets are also taken from the internet to evaluate the performance of the proposed method. The CLAHE preprocessing method is employed to enhance the image quality, then resizing and Image augmentation techniques are used to convert it into a standard format and increase the size of the dataset, respectively. The pretrained Caffe face detector model is used to detect the faces, and then the lightweight transfer learning-based Xception model is applied for the feature extraction process. This paper recommended a novel model that is, CL-SSDXcept to distinguish the Face Mask or no mask images. However, accession with the MobileNetV2, VGG16, VGG19, and InceptionV3 models with different hyperparameter settings has been tested on the FMDRT dataset. We have also compared the results of the synthesized dataset FMDRT to the existing Face Mask datasets. The experimental results attained 98% test accuracy on the suggested dataset 'FMDRT' using the CL-SSDXcept method. The empirical findings have been reported at 50 iterations with tuned hyperparameter values with an average accuracy 98% and a loss of 0.05.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

“…All other modules are ringed by straight residual connections, except the first and last. Collet 18 described the Xception19…”

mentioning

confidence: 99%

A face mask detection system: An approach to fight with COVID‐19 scenario

Jayaswal

Dixit²

2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Optical Flow estimation and motion based descriptor are used here to extract motion information and K Nearest Neighbour (KNN) is used for classification purpose. J a y a s w a l and D i x i t [14] classify different types of violence anomalies using deep neural architecture. The method to analyze human behavior in real-time scenarios uses fine-tuned Xception model for features extraction and an LSTM model for anomaly classification.…”

Section: Related Workmentioning

confidence: 99%

ESAR, An Expert Shoplifting Activity Recognition System

Ansari

Singh

2022

Cybernetics and Information Technologies

View full text Add to dashboard Cite

Shoplifting is a troubling and pervasive aspect of consumers, causing great losses to retailers. It is the theft of goods from the stores/shops, usually by hiding the store item either in the pocket or in carrier bag and leaving without any payment. Revenue loss is the most direct financial effect of shoplifting. Therefore, this article introduces an Expert Shoplifting Activity Recognition (ESAR) system to reduce shoplifting incidents in stores/shops. The system being proposed seamlessly examines each frame in video footage and alerts security personnel when shoplifting occurs. It uses dual-stream convolutional neural network to extract appearance and salient motion features in the video sequences. Here, optical flow and gradient components are used to extract salient motion features related to shoplifting movement in the video sequence. Long Short Term Memory (LSTM) based deep learner is modeled to learn the extracted features in the time domain for distinguishing person actions (i.e., normal and shoplifting). Analyzing the model behavior for diverse modeling environments is an added contribution of this paper. A synthesized shoplifting dataset is used here for experimentations. The experimental outcomes show that the proposed approach attains better consequences up to 90.26% detection accuracy compared to the other prevalent approaches.

show abstract

“…To validate the accuracy of the RTFMD dataset, this system is additionally trained using MobilenetV2 [16], VGG16 [17], VGG19 [2], and Xception [18] models with varied tuning of hyperparameters, as shown in Table 1. These models are ready for architecture fine-tuning [19]. Fine-tuning is an important step in improving the accuracy and speed of the training data.…”

Section: Classification Of Images Using Fine-tuned Inceptionv3 Architecturementioning

confidence: 99%

Detection of Hidden Facial Surface Masking in Stored and Real Time Captured Images: A Deep Learning Perspective in Covid Time

Jayaswal¹,

Dixit²

2021

Self Cite

View full text Add to dashboard Cite

A novel coronavirus has spread over the world and has become an outbreak. This, according to a WHO report, is an infectious disease that aims to spread. As a consequence, taking precautions is the only method to avoid catching this virus. The most important preventive measure against COVID-19 is to wear a mask. In this paper, a framework is designed for face mask detection using a deep learning approach. This paper aims to predict a person having a mask or unmask and also presents a proposed dataset named RTFMD (Real-Time Face Mask Dataset) to accomplish this objective. We have also taken the RFMD dataset from the internet to analyze the performance of system. Contrast Limited Adaptive Histogram Equalization (CLAHE) technique is applied at the time of pre-processing to enhance the visual quality of images. Subsequently, Inceptionv3 model used to train the face mask images and SSD face detector model has been used for face detection. Therefore, this paper proposed a model CLAHE-SSD_IV3 to classify the mask or without mask images. The system is also tested at VGG16, VGG19, Xception, MobilenetV2 models at different hyperparameters values and analyze them. Furthermore, compared the result of the proposed dataset RTFMD with the RFMD dataset. Additionally, proposed approach is compared with the existing approach on Face Mask dataset and RTFMD dataset. The outcomes have obtained 98% test accuracy on this proposed dataset RTFMD while 97% accuracy on the RFMD dataset in real-time.

show abstract

A Framework for Anomaly Classification Using Deep Transfer Learning Approach

Cited by 17 publications

References 26 publications

A face mask detection system: An approach to fight with COVID‐19 scenario

A face mask detection system: An approach to fight with COVID‐19 scenario

ESAR, An Expert Shoplifting Activity Recognition System

Detection of Hidden Facial Surface Masking in Stored and Real Time Captured Images: A Deep Learning Perspective in Covid Time

Contact Info

Product

Resources

About