Human Emotion Recognition from Body Posture with Machine Learning Techniques

Vaijayanthi, S.; Arunnehru, J.

doi:10.1007/978-3-031-12638-3_20

Cited by 6 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9], Rosenfeld found that the field of digital topology has influenced a wide range of uses, including pattern recognition and image processing. The concept of digital continuity for 2D and 3D digital images is being further developed in [33,40]. In [19][20][21], Boxer studied a variety of continuous digital functions as well as the digital version of several topological concepts.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Digital Image Compression in Some Fixed Point Results on Complete G-metric Space Using Comparison Function

Thirumalai,

Thalapathiraj

2023

Int. J. Anal. Appl.

View full text Add to dashboard Cite

In the present time world, digital images are crucial for various applications, that includes the medical industry, aircraft and satellite imaging, underwater imaging and so on. For this huge quantities of digital images are produced and used by these applications. For a variety of reasons, these images also need to be transmitted and stored. Therefore, a technique known as compression is applied to resolve this storage issue while transmitting these images. In this article, by extending some unique fixed point theorem results for comparison function on a complete symmetric G-metric space are used and it is a new approach. Moreover, this paper focuses on a compression method using the new structure of extended G-contraction mapping as it assists in compressing the size of the image. Thus, grayscale images are compressed using extended G-contraction mapping. And thus, grayscale images can be represented as matrices in this structure (pixel values). Also, similar images of reduced size can be obtained using an appropriate matrix G-metric and extended G-contraction mapping. The size of the matrix can be substantially reduced without losing any quality by controlling the order of sub matrices. These images are easy to store and transmit, with little variation between the original and contracted image.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Digital Image Compression in Some Fixed Point Results on Complete G-metric Space Using Comparison Function

Thirumalai,

Thalapathiraj

2023

Int. J. Anal. Appl.

View full text Add to dashboard Cite

show abstract

“…Most studies mainly focus on a single modality, which may include facial expressions [6], [7], voice [8], [9], text [10], [11], body posture [12], gaits [13], or physiological signals [14]. Multimodal processing and recognition has demonstrated great potential in numerous practical emotion recognition applications such as combining speech and facial features [15], [16], electroencephalography signal (EEG) and eye gaze [17], audio and written text [18], [19], visual, audio and text [20], [21], and modalities' features and contextual information [21], [22], [23].…”

Section: Introductionmentioning

confidence: 99%

Cross-Modality Learning by Exploring Modality Interactions for Emotion Reasoning

Tran

Pant

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Even without hearing or seeing individuals, humans are able to determine subtle emotions from a range of indicators and surroundings. However, existing research on emotion recognition is mostly focused on recognizing the emotions of speakers across complete modalities. In real-world situations, emotion reasoning is an interesting field for inferring human emotions from a person's surroundings when neither the face nor voice can be observed. Therefore, in this paper, we propose a novel multimodal approach for predicting emotion from missing one or more modalities based on attention mechanisms. Specifically, we employ self-attention for each unimodal representation to extract the dominant features and utilize the compounded paired-modality attention (CPMA) among sets of modalities to identify the context of the considered individual, such as the interplay of modalities, and capture people's interactions in the video. The proposed model is trained on the Multimodal Emotion Reasoning (MEmoR) dataset, which includes multimedia inputs such as visual, audio, text, and personality. The proposed model achieves a weighted F1-score of 50.63% for the primary emotion group and 42.7% for the fine-grained one. According to the results, our proposed model outperforms the conventional approaches in terms of emotion reasoning.

show abstract

Deep neural network-based emotion recognition using facial landmark features and particle swarm optimization

Vaijayanthi,

Arunnehru

2024

Automatika

View full text Add to dashboard Cite

Human Emotion Recognition from Body Posture with Machine Learning Techniques

Cited by 6 publications

References 17 publications

A Novel Approach for Digital Image Compression in Some Fixed Point Results on Complete G-metric Space Using Comparison Function

A Novel Approach for Digital Image Compression in Some Fixed Point Results on Complete G-metric Space Using Comparison Function

Cross-Modality Learning by Exploring Modality Interactions for Emotion Reasoning

Deep neural network-based emotion recognition using facial landmark features and particle swarm optimization

Contact Info

Product

Resources

About