A multi-scale and rotation-invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with preprocessing for facial expression classification

Alphonse, A. Sherly; Shankar, K.; Rakkini, M. J. Jeyasheela; Ananthakrishnan, Sankaranarayanan; Athisayamani, Suganya; Singh, Anshuman; Gobi, R.

doi:10.1007/s12652-020-02517-7

Cited by 25 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Durga et al [23] proposed LBP with Adaptive Window (LBP-AW) for noise robust facial feature extraction. Alphonse et al [2] proposed Multi-Scale and Rotation-Invariant Phase Pattern (MRIPP) for extracting blur-insensitive and rotation invariant facial features. Kumar et al [26] proposed Weighted Full binary Tree-Sliced Binary Pattern (WFBT-SBP) for analyzing an RGB image based on inter-pixel similarity patterns.…”

Section: Related Workmentioning

confidence: 99%

Modified chess patterns: handcrafted feature descriptors for facial expression recognition

Kartheek

Prasad

Bhukya

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Facial expressions are predominantly important in the social interaction as they convey the personal emotions of an individual. The main task in Facial Expression Recognition (FER) systems is to develop feature descriptors that could effectively classify the facial expressions into various categories. In this work, towards extracting distinctive features, Radial Cross Pattern (RCP), Chess Symmetric Pattern (CSP) and Radial Cross Symmetric Pattern (RCSP) feature descriptors have been proposed and are implemented in a 5 $$\times $$ × 5 overlapping neighborhood to overcome some of the limitations of the existing methods such as Chess Pattern (CP), Local Gradient Coding (LGC) and its variants. In a 5 $$\times $$ × 5 neighborhood, the 24 pixels surrounding the center pixel are arranged into two groups, namely Radial Cross Pattern (RCP), which extracts two feature values by comparing 16 pixels with the center pixel and Chess Symmetric Pattern (CSP) extracts one feature value from the remaining 8 pixels. The experiments are conducted using RCP and CSP independently and also with their fusion RCSP using different weights, on a variety of facial expression datasets to demonstrate the efficiency of the proposed methods. The results obtained from the experimental analysis demonstrate the efficiency of the proposed methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Modified chess patterns: handcrafted feature descriptors for facial expression recognition

Kartheek

Prasad

Bhukya

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…The CD algorithm enhances the learning effect of the RBM, which encourages more people to focus on the research and application of the RBM. The RBM has been successfully applied to classification (Alphonse et al, 2020;Chen, 2015), image transformation (Liu et al, 2015), time series prediction (Kou and He, 2016), personalized search (Bao et al, 2020) and collaborative filtering (Chen et al, 2019;Salakhutdinov et al, 2007).…”

Section: 2mentioning

confidence: 99%

Personalized news recommendation based on an improved conditional restricted Boltzmann machine

Zhong¹,

Wei

2021

View full text Add to dashboard Cite

Purpose Because of the extensive user coverage of news sites and apps, greater social and commercial value can be realized if users can access their favourite news as easily as possible. However, news has a timeliness factor; there are serious cold start and data sparsity in news recommendation, and news users are more susceptible to recent topical news. Therefore, this study aims to propose a personalized news recommendation approach based on topic model and restricted Boltzmann machine (RBM). Design/methodology/approach Firstly, the model extracts the news topic information based on the LDA2vec topic model. Then, the implicit behaviour data are analysed and converted into explicit rating data according to the rules. The highest weight is assigned to recent hot news stories. Finally, the topic information and the rating data are regarded as the conditional layer and visual layer of the conditional RBM (CRBM) model, respectively, to implement news recommendations. Findings The experimental results show that using LDA2vec-based news topic as a conditional layer in the CRBM model provides a higher prediction rating and improves the effectiveness of news recommendations. Originality/value This study proposes a personalized news recommendation approach based on an improved CRBM. Topic model is applied to news topic extraction and used as the conditional layer of the CRBM. It not only alleviates the sparseness of rating data to improve the efficient in CRBM but also considers that readers are more susceptible to popular or trending news.

show abstract

“…26 In the determined local directional maximum edge patterns, only the dominant magnitude and orientation are considered to detect strong edges. A multi-scale and rotation-invariant phase pattern (MRIPP) is proposed 27 which incorporates a rotation invariant, scale invariant and robust feature extraction technique. The calculation of stability indices by determining the normalized distance and shape signatures for facial expression recognition is presented.…”

Section: Related Work In Literaturementioning

confidence: 99%

Enhanced global and local face feature extraction for effective recognition of facial emotions

Retnamony¹,

Sundaram²,

Stanley³

2021

Concurrency and Computation

View full text Add to dashboard Cite

Emotion recognition is a challenging task in the field of human computer interaction.For a successful human emotion recognition system, a robust, discriminative, and sensitive feature extraction is an essential need. In this article, the extraction of global features is done by the proposed frequency decoded lifting wavelet pattern descriptor (FDLWP) and extraction of local features is done by the proposed local gradient difference zig-zag pattern descriptor (LGDZP). The face parts are detected using viola jones algorithm and the selection of optimal face active regions is accomplished by the calculation of structural similarity index measure. Eventually the local spatial zig-zag structure of the face region is utilized to attain LGDZP descriptor. The fusion of local and global features is accomplished using canonical correlation analysis. The classification made using bank of restricted Boltzmann machine (RBM) classifiers yields promising results for the proposed method. Furthermore, the proposed recognition method delivers a promising accuracy in varying illumination, occlusion, and noise. The accuracy of the method is analyzed by doing experiments with the databases such as JAFFE, CK+, MMI, Oulu-CASIA, and SFEW. The obtained results of the proposed method yield better accuracy than the existing state of art methods in this field. K E Y W O R D Scanonical correlation analysis (CCA), facial emotion recognition, frequency decoded lifting wavelet pattern descriptor (FDLWP), local gradient difference zigzag pattern descriptor (LGDZP), restricted Boltzmann machine (RBM), zig zag pattern descriptor INTRODUCTIONHuman emotion recognition is very essential for machines while making customized interactions with a human in human-computer interaction.Humans could get better assistance from machines only if machines understand human emotion. Emotions can be expressed by human verbally and non-verbally. Facial expression is a very common natural way to express the emotion by a human to observer. Normally 55% of human emotions are expressed through facial expressions, 38% through voice, and 7% through spoken words. 1 Retrieving emotion information from face image has come across a wide range of application such as biometric identification, behavioral analysis, stress evaluation, sentiment analysis, intelligent learning, human computer interaction, automated access control and surveillance. 2,3 The motion of face muscles beneath the skin plays a vital role in facial expression, and it is concluded by various researches that, facial expressions conveys emotion well than any other means. 4 Ekman and Friesen suggested six emotions as universal which includes anger, fear, disgust, happy, sad, and surprise. 5 Recent researches in the field of affect computing have made the facial expression recognition a feasible resource for intelligent interactive applications. 6 An automated facial expression recognition system normally has four stages, namely preprocessing and face detection, feature extraction from detected face, dimension red...

show abstract

A multi-scale and rotation-invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with preprocessing for facial expression classification

Cited by 25 publications

References 45 publications

Modified chess patterns: handcrafted feature descriptors for facial expression recognition

Modified chess patterns: handcrafted feature descriptors for facial expression recognition

Personalized news recommendation based on an improved conditional restricted Boltzmann machine

Enhanced global and local face feature extraction for effective recognition of facial emotions

Contact Info

Product

Resources

About