Simple and Robust Facial Portraits Recognition under Variable Lighting Conditions Based on Two-Dimensional Orthogonal Transformations

Forczmański, Paweł; Kukharev, Georgy; Shchegoleva, Nadezhda

doi:10.1007/978-3-642-41181-6_61

Cited by 14 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because it should be an interactive process, it does not include off-line solutions that involve human computation; whether they are based on expert knowledge or crowdsourcing techniques, all calculations must be performed by automated algorithms (Chen et al , 2016). Though there are various approaches, e. g. LDA (Lotte et al , 2007), SVM (Oskoei et al , 2009)(Walczak and Wojciechowski, 2016)(Eswaramoorthy et al , 2016), 2-D orthogonal transformations (Forczmański et al , 2013) or Bayesian classifiers (Duda et al , 2000), the neural networks are well established frameworks for signal classification problems and are often used in BCI systems. Among many types of neural networks are some that are already proved to be successful in terms of EEG signal analysis for selected pattern-recognition situations.…”

Section: Related Workmentioning

confidence: 99%

LSTM multichannel neural networks in mental task classification

Opałka

Szajerman

Wojciechowski

2019

COMPEL

View full text Add to dashboard Cite

Purpose The purpose of this paper is to apply recurrent neural networks (RNNs) and more specifically long-short term memory (LSTM)-based ones for mental task classification in terms of BCI systems. The authors have introduced novel LSTM-based multichannel architecture model which proved to be highly promising in other fields, yet was not used for mental tasks classification. Design/methodology/approach Validity of the multichannel LSTM-based solution was confronted with the results achieved by a non-multichannel state-of-the-art solutions on a well-recognized data set. Findings The results demonstrated evident advantage of the introduced method. The best of the provided variants outperformed most of the RNNs approaches and was comparable with the best state-of-the-art methods. Practical implications The approach presented in the manuscript enables more detailed investigation of the electroencephalography analysis methods, invaluable for BCI mental tasks classification. Originality/value The new approach to mental task classification, exploiting LSTM-based RNNs with multichannel architecture, operating on spatial features retrieving filters, has been adapted to mental tasks with noticeable results. To the best of the authors’ knowledge, such an approach was not present in the literature before.

show abstract

Section: Related Workmentioning

confidence: 99%

LSTM multichannel neural networks in mental task classification

Opałka

Szajerman

Wojciechowski

2019

COMPEL

View full text Add to dashboard Cite

show abstract

“…The manifold structure is modelled by an adjacency graph which describes the local structure of the image space [6]. Multi‐dimensional orthogonal transformations have also been used to reduce the implementation complexity [17, 18].…”

Section: Related Workmentioning

confidence: 99%

Fast matching pursuit for sparse representation‐based face recognition

2018

View full text Add to dashboard Cite

Even though face recognition is one of the most studied pattern recognition problems, most existing solutions still lack efficiency and high speed. Here, the authors present a new framework for face recognition which is efficient, fast, and robust against variations of illumination, expression, and pose. For feature extraction, the authors propose extracting Gabor features in order to be resilient to variations in illumination, facial expressions, and pose. In contrast to the related literature, the authors then apply supervised locality‐preserving projections (SLPP) with heat kernel weights. The authors’ feature extraction approach achieves a higher recognition rate compared to both traditional unsupervised LPP and SLPP with constant weights. For classification, the authors use the recently proposed sparse representation‐based classification (SRC). However, instead of performing SRC using the computationally expensive ℓ1 minimisation, the authors propose performing SRC using fast matching pursuit, which considerably improves the classification performance. The authors’ proposed framework achieves ∼99% recognition rate using four benchmark face databases, significantly faster than related frameworks.

show abstract

“…By determining the difference from 1D transforms, the collection of 2D transforms was enriched with hybrid transforms, born through a combination of two or more already known transforms. For example, one can find a joint Cosine and Karhunen-Loève Transform in [27], a joint Cosine and Hadamard Transform in [28], and a joint Walsh and fractional Fourier Transform in [29].…”

Section: Introductionmentioning

confidence: 99%

John von Neumann’s Space-Frequency Orthogonal Transforms

Stefanoiu,

Culita

2024

Mathematics

View full text Add to dashboard Cite

Among the invertible orthogonal transforms employed to perform the analysis and synthesis of 2D signals (especially images), the ones defined by means of John von Neumann’s cardinal sinus are extremely interesting. Their definitions rely on transforms similar to those employed to process time-varying 1D signals. This article deals with the extension of John von Neumann’s transforms from 1D to 2D. The approach follows the manner in which the 2D Discrete Fourier Transform was obtained and has the great advantage of preserving the orthogonality property as well as the invertibility. As an important consequence, the numerical procedures to compute the direct and inverse John von Neumann’s 2D transforms can be designed to be efficient thanks to 1D corresponding algorithms. After describing the two numerical procedures, this article focuses on the analysis of their performance after running them on some real-life images. One black and white and one colored image were selected to prove the transforms’ effectiveness. The results show that the 2D John von Neumann’s Transforms are good competitors for other orthogonal transforms in terms of compression intrinsic capacity and image recovery.

show abstract

Simple and Robust Facial Portraits Recognition under Variable Lighting Conditions Based on Two-Dimensional Orthogonal Transformations

Cited by 14 publications

References 19 publications

LSTM multichannel neural networks in mental task classification

LSTM multichannel neural networks in mental task classification

Fast matching pursuit for sparse representation‐based face recognition

John von Neumann’s Space-Frequency Orthogonal Transforms

Contact Info

Product

Resources

About