Specular Reflection Removal Using Morphological Filtering for Accurate Iris Recognition

Kumar, Sandeep; Raghavan, Nagarajan; Sani, Nidhin; Joseph, Abin John; Martin, Agath

doi:10.1109/icsss.2019.8882863

Cited by 13 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare the performance of the five types of methods with the data, the global and regional PSNR values of the methods were calculated and presented in Table 4, where the global PSNR values were calculated for the whole images after being treated by the methods of specularity removal; meanwhile, the regional values of PSNR were only calculated from the specular regions in the images [29,30]. The SA-RPCA and SCSA methods had higher regional PSNR values and preserved texture details and colour information.…”

Section: Comparisons Of Methodsmentioning

confidence: 99%

Effectiveness of specularity removal from hyperspectral images in the colour spectral measurement of wool fibres

Qiu

Shen

Chen

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Microscopic hyperspectral imaging technology is a potential non‐destructive and non‐contact method for colour measurement of micrometre‐sized textile fibres. However, specularity on the fibre surface can distort the accurate colour information and affect the accuracy of the colour measurement. This paper proposed a specular‐constrained sparse approximation (SCSA) for specular‐diffuse reflection separation from hyperspectral images of wool fibres. First, a specular prior map is generated based on the lightness dissimilarity. Then the SCSA model is used to decompose the processed hyperspectral image A into low‐rank data L, sparse specularity data S constrained by the specular prior map, sparse noise E, and Gaussian noise N. A non‐linear logistic sigmoid function and a sparse approximation of A – L – N to S are used to improve the performance of specularity removal during iterative optimization. The experimental results show that the proposed method significantly preserves diffuse reflectance and texture details in the specular highlight regions to obtain actual spectral reflectance and chromatic values from hyperspectral images of wool fibres.

show abstract

Section: Comparisons Of Methodsmentioning

confidence: 99%

Effectiveness of specularity removal from hyperspectral images in the colour spectral measurement of wool fibres

Qiu

Shen

Chen

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Under Near-Infrared (NIR) illuminations or visible wavelength (VW) light, the iris images are captured [17,18]. Various segmentation models were employed in the summary review.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Iris Segmentation and Classification of Drunk Person Using Modified Circle Hough Transform

Jayadev¹,

Bellary²

2022

Preprint

View full text Add to dashboard Cite

With various publications for Iris Recognition (IR) in the past few years, a more attractive research topic is Biometrics. Deformation in the iris pattern is created when the pupil dilates/constricts owing to alcohol consumption probably affecting IR performance. The eye's pupil region was not segmented by the prevailing segmentation schemes along with having low accuracy. An efficient iris segmentation model along with clustering the drunk person utilizing a Modified Circle Hough Transform (MCHT) was proposed in this scheme to tackle those issues. Noise reduction, iris segmentation, pupil segmentation and drink and no-drink person’s clustering are the steps comprised in the proposed model. The input images are gathered from the database initially. The noise is abated from the image by utilizing Median Filtering (MF). The Canny Mathematical Morphology (CMM) was employed to segment the iris part from the noise-free image. Subsequently, the MCHT executed the pupil segmentation as of the segmented iris image. The system’s accuracy along with robustness is elevated by performing this alteration. Consequently, the Matrix Based Clustering (MBC) clustered the drinker and the non-drinker person. The experiential outcomes exhibit that better performance was proved by the proposed method than the top-notch models.

show abstract

An iris quality evaluation method with pre-recognition screening function

Liu

Zhu

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

Specular Reflection Removal Using Morphological Filtering for Accurate Iris Recognition

Cited by 13 publications

References 9 publications

Effectiveness of specularity removal from hyperspectral images in the colour spectral measurement of wool fibres

Effectiveness of specularity removal from hyperspectral images in the colour spectral measurement of wool fibres

An Efficient Iris Segmentation and Classification of Drunk Person Using Modified Circle Hough Transform

An iris quality evaluation method with pre-recognition screening function

Contact Info

Product

Resources

About