Emotion recognition using Principal Component Analysis with Singular Value Decomposition

Gosavi, Ajit P.; Khot, S. R.

doi:10.1109/ecs.2014.6892683

Cited by 14 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[150] in a comprehensive study of facial expression with PCA reported from their research that PCA conducted on facial shape information produced a better result and a better method for FER than the PCA uses facial identities. [152] also enhanced the performance of PCA with Singular Value Decomposition (PCA-SVD) to extract unique features which provided better performance than both ordinary PCA and LBP + Adaboost. PCA has shown an impressive performance in expression recognition when compared with other Appearance-based features.…”

Section: A: Gabor Waveletmentioning

confidence: 99%

Facial Expression Recognition: A Review of Trends and Techniques

Ekundayo

Viriri

2021

IEEE Access

View full text Add to dashboard Cite

Facial Expression Recognition (FER) is presently the aspect of cognitive and affective computing with the most attention and popularity, aided by its vast application areas. Several studies have been conducted on FER, and many review works are also available. The existing FER review works only give an account of FER models capable of predicting the basic expressions. None of the works considers intensity estimation of an emotion; neither do they include studies that address data annotation inconsistencies and correlation among labels in their works. This work first introduces some identified FER application areas and provides a discussion on recognised FER challenges. We proceed to provide a comprehensive FER review in three different machine learning problem definitions: Single Label Learning (SLL)-which presents FER as a multiclass problem, Multilabel Learning (MLL)-that resolves the ambiguity nature of FER, and Label Distribution Learning-that recovers the distribution of emotion in FER data annotation. We also include studies on expression intensity estimation from the face. Furthermore, popularly employed FER models are thoroughly and carefully discussed in handcrafted, conventional machine learning and deep learning models. We finally itemise some recognise unresolved issues and also suggest future research areas in the field.

show abstract

Section: A: Gabor Waveletmentioning

confidence: 99%

Facial Expression Recognition: A Review of Trends and Techniques

Ekundayo

Viriri

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Metode PCA sering digunakan dalam pengenalan wajah, prediksi, dan lain-lain [18]. Metode ini berfokus untuk mereduksi data [19]. PCA akan mencari pola dan mengambil ciri dari data citra yang berdimensi tinggi dari sebuah dataset latih yang kemudian direduksi dari citra yang berdimensi tinggi menjadi citra berdimensi rendah [20].…”

Section: A Metode Pcaunclassified

Deteksi Kantuk pada Pengemudi Berdasarkan Penginderaan Wajah Menggunakan PCA dan SVM

Ramadhani

Aulia

Suhartono

et al. 2021

JRE

View full text Add to dashboard Cite

Salah satu faktor penyebab dari berkurangnya konsentrasi dari pengemudi adalah rasa kantuk. Rasa kantuk dapat membuat konsentrasi pengemudi menjadi menurun, terutama ketika jalanan sedang padat karena kemacetan yang panjang. Banyak pengemudi yang lebih memilih mengabaikan rasa kantuknya dan meneruskan perjalanannya hingga sampai ketujuan, padahal hal ini dapat mengancam keselamatan pengemudi. Beberapa tahun terakhir ini, konsentrasi yang kurang saat sedang mengemudi menjadi salah satu penyebab terjadinya banyak kecelakaan [1].Sehingga pada penelitian ini diusulkan deteksi kantuk melalui ekspresi wajah pada pengendara sebagai pencegahan kecelakaan. Ada beberapa metode yang biasa digunakan pada sistem pengenalan ekspresi wajah. Pada tahun 2015, penelitian yang dilakukan oleh Siddiqi, dkk.[2], melokalisasi ekspresi wajah menggunakan metode stepwise linear discriminant analysis dan hidden conditional random field dengan nilai akurasi 96,37%, namun dari hasil yang dicapai tersebut masih memiliki keterbatasan yaitu belum direalisasikan dengan real environtment karena baru menggunakan 6 citra wajah. Pada tahun 2017, penelitian yang dilakukan oleh Qayyum, dkk. [3], menggunakan stationary wavelet transform sebagai ekstraksi ciri dan neural network sebagai klasifikasi antara wajah normal dan wajah berekspresi berdasarkan perubahan otot pada wajah, dengan nilai akurasi 94,28%. Azmi, dkk. [4] menggunakan metode local

show abstract

“…In this paper, we introduce the subspace decomposition to improve the robustness to the aspect sensitivity instead. As an effective approach for subspace decomposition, singular value decomposition (SVD) can realize signal denoising by separating the noised data into the signal subspace and the noise subspace [ 33 , 34 , 35 , 36 , 37 ]. The SVD operation projects the HRRP profile matrix onto orthogonal basis spaces decoupled in the range and angle domain [ 36 ], in which the range-space singular vectors are referred to constitute the “optimal” features in the range domain [ 38 ], while the angle-space singular vectors are not considered in many ATR applications.…”

Section: Introductionmentioning

confidence: 99%

Robust Automatic Target Recognition via HRRP Sequence Based on Scatterer Matching

Jiang

Cai

et al. 2018

Sensors

View full text Add to dashboard Cite

High resolution range profile (HRRP) plays an important role in wideband radar automatic target recognition (ATR). In order to alleviate the sensitivity to clutter and target aspect, employing a sequence of HRRP is a promising approach to enhance the ATR performance. In this paper, a novel HRRP sequence-matching method based on singular value decomposition (SVD) is proposed. First, the HRRP sequence is decoupled into the angle space and the range space via SVD, which correspond to the span of the left and the right singular vectors, respectively. Second, atomic norm minimization (ANM) is utilized to estimate dominant scatterers in the range space and the Hausdorff distance is employed to measure the scatter similarity between the test and training data. Next, the angle space similarity between the test and training data is evaluated based on the left singular vector correlations. Finally, the range space matching result and the angle space correlation are fused with the singular values as weights. Simulation and outfield experimental results demonstrate that the proposed matching metric is a robust similarity measure for HRRP sequence recognition.

show abstract

Emotion recognition using Principal Component Analysis with Singular Value Decomposition

Abstract: Emotion recognition plays vital role in HumanComputer Interface. This paper focuses on facial expression to identify seven universal human emotions such as, happy, disgust,

Cited by 14 publications

References 4 publications

Facial Expression Recognition: A Review of Trends and Techniques

Facial Expression Recognition: A Review of Trends and Techniques

Deteksi Kantuk pada Pengemudi Berdasarkan Penginderaan Wajah Menggunakan PCA dan SVM

Robust Automatic Target Recognition via HRRP Sequence Based on Scatterer Matching

Contact Info

Product

Resources

About