Performance Evaluation of Infrared and Visible Image Fusion Algorithms for Face Recognition

Wang, Jing; Liang, Jinling; Hu, Hongping; Li, Yan

doi:10.2991/iske.2007.234

Cited by 13 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image fusion algorithm using Finite Ridgelet Transform (FRIT) is used to decompose the row images to low and high frequency components [5,6]. A fusion method based on SVD was applied to multispectral face recognition [7]. The face images are decomposed in to three layers according to the energy distribution.…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Modified SVD based Image Fusion

R¹,

Mohan²,

Kartha³

et al. 2012

IJCA

View full text Add to dashboard Cite

Image fusion produces a single composite image from a set of input images, which is more suitable for visual perception and computer processing. This paper proposes Singular Value Decomposition (SVD) based fusion, which yields better results. The variation of data can be captured by SVD and is used to perform the fusion by varying singular values. This approach is implemented and compared with image fusion based on PCA (Principal component analysis) and performance is evaluated using various image quality measures such as PSNR, Normalized cross correlation, Structured content, MSE, Normalized absolute error. Simulation results of proposed approach shows significant performance improvement when compared with PCA based fusion.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Modified SVD based Image Fusion

R¹,

Mohan²,

Kartha³

et al. 2012

IJCA

View full text Add to dashboard Cite

show abstract

“…However, on the other hand, moving leaves and grass, cooling winds, moving shadows with clouds, reflecting snow, etc., are challenging for IR imagery too. Thus, fusion of IR and visual image is a potential solution to improve person detection, tracking, recognition, and fusion performance (Wang et al, 2007). Tracking and recognition using the visual image is sensitive to variations in illumination conditions.…”

Section: Introductionmentioning

confidence: 99%

Fusion of Infrared and Visible Images for Robust Person Detection

Zin¹,

Takahashi²,

Takenaka³

et al. 2011

Image Fusion

View full text Add to dashboard Cite

“…Face to limitations of the use, at once, of visible or infrared spectrums, recent researches [14], [17], [19], [20] propose to use both Visible and Infrared sensors. A fusion between the information provided by VIS and IR cameras for moving object detection would offer complementary solutions: relying on visible images in sunny days, we achieve a good detection and can extract a rich content; while the use of infrared sensor seems to give better results for moving object detection in presence of darkness, limited levels of luminosity, shadows, light reflections, or some weather variations.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Fusion of Infrared and Visible Spectrum for Video Surveillance Application

Boukhriss

Fendri

Hammami

2015

Artificial Intelligence and Soft Computing

View full text Add to dashboard Cite

Abstract. In video surveillance, we can rely on either a visible spectrum or an infrared one. In order to profit from both of them, several fusion methods were proposed in literature: low-level fusion, middle-level fusion and high-level fusion. The first one is the most used for moving objects' detection. It consists in merging information from visible image and infrared one into a new synthetic image to detect objects. However, the fusion process may not preserve all relevant information. In addition, perfect correlation between the two spectrums is needed. In This paper, we propose an intelligent fusion method for moving object detection. The proposed method relies on one of the two given spectrum at once according to weather conditions (darkness, sunny days, fog, snow, etc.). Thus, we first extract a set of low-level features (visibility, local contrast, sharpness, hue, saturation and value), then a prediction model is generated by supervised learning techniques. The classification results on 15 sequences with different weather conditions indicate the effectiveness of the extracted features, by using C4.5 as classifier.

show abstract

Performance Evaluation of Infrared and Visible Image Fusion Algorithms for Face Recognition

Cited by 13 publications

References 22 publications

Performance Evaluation of Modified SVD based Image Fusion

Performance Evaluation of Modified SVD based Image Fusion

Fusion of Infrared and Visible Images for Robust Person Detection

Intelligent Fusion of Infrared and Visible Spectrum for Video Surveillance Application

Contact Info

Product

Resources

About