Edge-enhanced bi-dimensional empirical mode decomposition-based emotion recognition using fusion of feature set

Bhattacharya, Arghya; Choudhury, Dwaipayan; Dey, Debangshu

doi:10.1007/s00500-016-2395-4

Cited by 9 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this purpose, we can use the so-called "multi-point masks". Individual points on this mask represent the extracted areas from which the classification of the emotional state is performed [7]. Because of the amount of individual parts on this mask that can be scanned simultaneously and the amount of output data thus produced, there have been developed various methods for detecting, extracting and subsequently classifying the emotional state either in real time or using stored face images.…”

Section: Introductionmentioning

confidence: 99%

Are Instructed Emotional States Suitable for Classification? Demonstration of How They Can Significantly Influence the Classification Result in An Automated Recognition System

Magdin¹,

Prikler²

2019

IJIMAI

View full text Add to dashboard Cite

At the present time, various freely available or commercial solutions are used to classify the subject's emotional state. Classification of the emotional state helps us to understand how the subject feels and what he is experiencing in a particular situation. Classification of the emotional state can thus be used in various areas of our life from neuromarketing, through the automotive industry (determining how emotions affect driving), to implementing such a system into the learning process. The learning process, which is the (mutual) interaction between the teacher and the learner, is an interesting area in which individual emotional states can be explored. In this pedagogical-psychological area several research studies were realized. These studies in some cases demonstrated the important impact of the emotional state on the results of the students. However, for comparison and unambiguous classification of the emotional state most of these studies used the instructed (even constructed) stereotypical facial expressions of the most well-known test databases (Jaffe is a typical example). Such facial expressions are highly standardized, and the software can recognize them with a fairly big percentage, but this does not necessarily point to the actual success rate of the subject's emotional classification in such a test because the similarity to real emotional expression remains unknown. Therefore, we examined facial expressions in real situations. We have subsequently compared these examined facial expressions with the instructed expressions of the same emotions (the Jaffe database). The overall average classification score in real facial expressions was 94.58%.

show abstract

Section: Introductionmentioning

confidence: 99%

Are Instructed Emotional States Suitable for Classification? Demonstration of How They Can Significantly Influence the Classification Result in An Automated Recognition System

Magdin¹,

Prikler²

2019

IJIMAI

View full text Add to dashboard Cite

show abstract

“…After it was proposed, the empirical mode decomposition (EMD) method was also introduced into image fusion as the same as preceding conventional transform methods, including medical image fusion [27]- [30]. EMD can decompose source image into a residue to present the approximate representation and a set of intrinsic mode functions (IMFs) to describe the details of the image.…”

mentioning

confidence: 99%

Brain Medical Image Fusion Using L2-Norm-Based Features and Fuzzy-Weighted Measurements in 2-D Littlewood–Paley EWT Domain

Jin

Jiang

Chu

et al. 2020

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Computational imaging provides comprehensive and reliable information about human tissue for medical diagnosis and treatment, with medical image fusion as one of the most important technologies in the field. Empirical mode decomposition (EMD), a promising model for image processing, has been used for image fusion in some methods. However, the varying number of decomposed layers leads to problems using EMD for image fusion. In this article, we propose a fusion method for medical images incorporating L2-norm-based features, a match/salience/fuzzy-weighted measure, and the 2-D Littlewood-Paley empirical wavelet transform (2-D LPEWT) as new version of EMD. We first decompose medical images with LPEWT to obtain the residual component (residue) and detailed sub-images that are named as intrinsic mode functions (IMFs). Then we extract the regional features of residue with an L2norm-based model to fuse the residue while simultaneously fusing IMFs using a method combining a fuzzy membership function with a match/salience measurement. Finally, we reconstruct the comprehensive image by applying inverse LPEWT to the fused residue and IMFs. We evaluated our method using a frequentlyused data set of brain images. The results show that our proposed method is more effective than conventional methods by fusing more information into the final images. We also show a feasible scheme for applying EMD to image fusion.

show abstract

Design of a hierarchy modular neural network and its application in multimodal emotion recognition

Chu

Qiao

2019

Soft Comput

View full text Add to dashboard Cite

Edge-enhanced bi-dimensional empirical mode decomposition-based emotion recognition using fusion of feature set

Cited by 9 publications

References 35 publications

Are Instructed Emotional States Suitable for Classification? Demonstration of How They Can Significantly Influence the Classification Result in An Automated Recognition System

Are Instructed Emotional States Suitable for Classification? Demonstration of How They Can Significantly Influence the Classification Result in An Automated Recognition System

Brain Medical Image Fusion Using L2-Norm-Based Features and Fuzzy-Weighted Measurements in 2-D Littlewood–Paley EWT Domain

Design of a hierarchy modular neural network and its application in multimodal emotion recognition

Contact Info

Product

Resources

About