A Novel Fuzzy Optimized CNN-RNN Method for Facial Expression Recognition

Zhang, Dong; Tian, Qichuan

doi:10.5755/j02.eie.29648

Cited by 6 publications

(3 citation statements)

References 49 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Fuzzy optimized (CNN-RNN) method for facial expression recognition was proposed by Zhang and Tian [22]. The Fuzzy logic is used to reduce the suspicion in the activation map by recognizing the highly nonlinear relationship between the features.…”

Section: Related Workmentioning

confidence: 99%

Improving Facial Expression Recognition Using HOG with SVM and Modified Datasets Classified by Alexnet

Al-Atroshi,

Ali

2023

View full text Add to dashboard Cite

Facial expressions are one of the communication ways between humans and their behavior can be determined through their facial expressions. Recently computer technology has been used to identify the facial expressions of people in order to predict their intentions. It remains a challenge for facial expression recognition to extract discriminative features from training sets with few labels because most deep learning-based algorithms primarily rely on spatial information and large labels. In this paper, we propose a system to classify seven types of facial expressions (Angry, Sadness, Surprise, Happiness, Fear, Neutral, and Disgust) instead of six, as in most previous research. In the proposed system, machine learning algorithms with deep learning are used to increase classification accuracy based on removing some unimportant facial regions. The support vector machine (SVM) algorithm is trained to detect the eyes and mouth regions from the face depending on histogram-oriented gradient (HOG) which is used as a features extractor. Then, merge the eyes and mouth regions for each image to create a new form of an image. After that, five different types of images are generated from the merged image named (RGB, HSV, Gray, Binary, and YCbCr). The images are fed one by one into the convolution neural network (CNN) algorithm. Finally, the voting process is used to select the most predictive class. The proposed system has been tested on three different types of datasets (KDEF, JAFFE, and FER2013) and the prediction accuracy in the system has reached more than 98% in all used datasets. The conclusion is that eliminating unimportant regions impacts the results of the classification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Facial Expression Recognition Using HOG with SVM and Modified Datasets Classified by Alexnet

Al-Atroshi,

Ali

2023

View full text Add to dashboard Cite

show abstract

“…All models discussed require a good understanding of the cardiovascular system and individual parameters of the patients that the mathematical model performs correctly. Thus, a simpler mathematical model is required, which can support researchers in investigating the seismocardiogram or developing new devices for ensuring quality of life and safety in roads [39][40][41][42].…”

Section: R = 8lµmentioning

confidence: 99%

A Novel Seismocardiogram Mathematical Model for Simplified Adjustment of Adaptive Filter

et al. 2022

View full text Add to dashboard Cite

Nonclinical measurements of a seismocardiogram (SCG) can diagnose cardiovascular disease (CVD) at an early stage, when a critical condition has not been reached, and prevents unplanned hospitalization. However, researchers are restricted when it comes to investigating the benefits of SCG signals for moving patients, because the public database does not contain such SCG signals. The analysis of a mathematical model of the seismocardiogram allows the simulation of the heart with cardiovascular disease. Additionally, the developed mathematical model of SCG does not totally replace the real cardio mechanical vibration of the heart. As a result, a seismocardiogram signal of 60 beats per min (bpm) was generated based on the main values of the main artefacts, their duration and acceleration. The resulting signal was processed by finite impulse response (FIR), infinitive impulse response (IRR), and four adaptive filters to obtain optimal signal processing settings. Meanwhile, the optimal filter settings were used to manage the real SCG signals of slowly moving or resting. Therefore, it is possible to validate measured SCG signals and perform advanced scientific research of seismocardiogram. Furthermore, the proposed mathematical model could enable electronic systems to measure the seismocardiogram with more accurate and reliable signal processing, allowing the extraction of more useful artefacts from the SCG signal during any activity.

show abstract

“…The rapid development of computer equipment constantly enhances the conditions for using more complex measuring algorithms. This is the reason for the increase in the adoption of 3D processing methods in the field of particle assessment [4][5][6]. However, the use of this method is not always the most rational choice.…”

Section: Introductionmentioning

confidence: 99%

New Approach for Fertiliser Size Assessment Using Contactless Scanning

Laucka,

Andriukaitis,

Valinevicius

et al. 2023

Mathematics

View full text Add to dashboard Cite

The growing population and lack of change in resources of cultivated land have led to the search for more efficient farming solutions. The recovery of soil is facilitated by using chemicals designed for the enrichment of cultivated soil. Fertilisers are made of a combination of various substances that determine not only the chemical but also the shape characteristics of the fertiliser pellets. The effect of the quality of fertilisation on yield size is related to even distribution. Shape and size are closely related to the quality of the fertilisation process. The intense control of the production process would not be possible without automatised and quick measurements within the production line. Constant control is necessary to ensure that the products meet quality standards. The contactless assessment of pellet sizes allows a quick reaction to changes in production quality and reduces the costs arising from the reprocessing of defective pellets. The results of the assessment of pellet volume using their two-dimensional image are presented in this publication. Pellets must be analysed according to their most characteristic position, which can provide valuable information about their properties. The aim is to determine the placement positions of the equipment based on calculations and to compare the results with those of gold-standard equipment. Correctly calibrated equipment ensures that the measurement results match the results of the control equipment of fertiliser producers. Reliable non-contact measurements can reduce the reaction time to production changes.

show abstract

A Novel Fuzzy Optimized CNN-RNN Method for Facial Expression Recognition

Cited by 6 publications

References 49 publications

Improving Facial Expression Recognition Using HOG with SVM and Modified Datasets Classified by Alexnet

Improving Facial Expression Recognition Using HOG with SVM and Modified Datasets Classified by Alexnet

A Novel Seismocardiogram Mathematical Model for Simplified Adjustment of Adaptive Filter

New Approach for Fertiliser Size Assessment Using Contactless Scanning

Contact Info

Product

Resources

About