An ensemble approach for still image-based human action recognition

Banerjee, Avinandan; Roy, Sayantan; Kundu, Rohit; Singh, Pawan Kumar; Bhateja, Vikrant; Sarkar, Ram

doi:10.1007/s00521-022-07514-9

Cited by 5 publications

(1 citation statement)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs are capable of accurately classifying images on their own. However, the combined efforts of several CNNs can produce better outcomes than those of any one CNN alone [15]- [22]. Trained on ImageNet dataset, Two CNNs in the current model are loaded with weights.…”

Section: Ensemble Cnnmentioning

confidence: 99%

Masked facial recognition using ensemble convolutional neural network and grey-level co-occurrence matrix

Gupta,

Agrawal,

Pal

2024

IJEECS

View full text Add to dashboard Cite

The COVID-19 pandemic proved how face masks became necessary to stop the spread of infection. Due to this, effective identification of people wearing face mask became challenging. Masked facial recognition has significantly increased in accuracy because of developments in convolutional neural networks (CNNs). Small size of the dataset of masked facial images has been a problem in earlier research. As would be expected, this results in poorer accuracy when the model tries to identify faces. In this study, a novel model is proposed with textural feature extraction using grey-level co-occurrence matrix (GLCM) and an ensemble of two pre-trained CNNs DenseNet-121 and VGG-16. Using the minimum redundancy and maximum relevance, the model has improved accuracy by choosing the most important features of the image. The model was trained using in-house dataset that included 38,290 photos of 2,500 people with approximately equal distribution of properly masked, partially masked, and unmasked images. In this, we evaluated the performance of the model on different classifiers multi-class logistic regression (LR) and support vector machine (SVM) with one-vs-rest (OvR) classification and artificial neural network (ANN) and applied a soft voting scheme. The model achieved the highest accuracy of 98.56% at a learning rate of 0.001 on the ANN classifier.

show abstract

Section: Ensemble Cnnmentioning

confidence: 99%

Masked facial recognition using ensemble convolutional neural network and grey-level co-occurrence matrix

Gupta,

Agrawal,

Pal

2024

IJEECS

View full text Add to dashboard Cite

show abstract

Patch excitation network for boxless action recognition in still images

Liang,

Wang,

Zhuang

2023

Vis Comput

View full text Add to dashboard Cite

Human activity recognition from sensor data using spatial attention-aided CNN with genetic algorithm

Sarkar

Hossain

Sarkar

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Capturing time and frequency relationships of time series signals offers an inherent barrier for automatic human activity recognition (HAR) from wearable sensor data. Extracting spatiotemporal context from the feature space of the sensor reading sequence is challenging for the current recurrent, convolutional, or hybrid activity recognition models. The overall classification accuracy also gets affected by large size feature maps that these models generate. To this end, in this work, we have put forth a hybrid architecture for wearable sensor data-based HAR. We initially use Continuous Wavelet Transform to encode the time series of sensor data as multi-channel images. Then, we utilize a Spatial Attention-aided Convolutional Neural Network (CNN) to extract higher-dimensional features. To find the most essential features for recognizing human activities, we develop a novel feature selection (FS) method. In order to identify the fitness of the features for the FS, we first employ three filter-based methods: Mutual Information (MI), Relief-F, and minimum redundancy maximum relevance (mRMR). The best set of features is then chosen by removing the lower-ranked features using a modified version of the Genetic Algorithm (GA). The K-Nearest Neighbors (KNN) classifier is then used to categorize human activities. We conduct comprehensive experiments on five well-known, publicly accessible HAR datasets, namely UCI-HAR, WISDM, MHEALTH, PAMAP2, and HHAR. Our model significantly outperforms the state-of-the-art models in terms of classification performance. We also observe an improvement in overall recognition accuracy with the use of GA-based FS technique with a lower number of features. The source code of the paper is publicly available here.

show abstract

An ensemble approach for still image-based human action recognition

Cited by 5 publications

References 63 publications

Masked facial recognition using ensemble convolutional neural network and grey-level co-occurrence matrix

Masked facial recognition using ensemble convolutional neural network and grey-level co-occurrence matrix

Patch excitation network for boxless action recognition in still images

Human activity recognition from sensor data using spatial attention-aided CNN with genetic algorithm

Contact Info

Product

Resources

About