From Colour to Tissue Histology: Physics Based Interpretation of Images of Pigmented Skin Lesions

Claridge, Ela; Cotton, Symon; Hall, Per; Moncrieff, Marc

doi:10.1007/3-540-45786-0_90

Cited by 35 publications

(41 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The facial skin has specific spectral characteristics determined by its chemical components [15] [16] , and their spectral absorption range may convey more information than other bands for face recognition. This paper proposes a feature band selection method by exploiting the intrinsic spectral absorption characteristics of the skin in vivo.…”

Section: Introductionmentioning

confidence: 99%

Studies on Hyperspectral Face Recognition in Visible Spectrum With Feature Band Selection

Wei

Zhang

et al. 2010

IEEE Trans. Syst., Man, Cybern. A

124

View full text Add to dashboard Cite

Abstract:This paper studies face recognition by using hyperspectral imagery in the visible light bands. The spectral measurements over the visible spectrum have different discriminatory information for the task of face identification, and it is found that the absorption bands related to hemoglobin are more discriminative than the other bands. Therefore, feature band selection based on the physical absorption characteristics of face skin is performed and two feature band subsets are selected. Then, three methods are proposed for hyperspectral face recognition, including whole band (2D) 2 PCA, single band (2D) 2 PCA with decision level fusion, and band subset fusion based (2D) 2 PCA. A simple yet efficient decision level fusion strategy is also proposed for the later two methods. To testify the proposed techniques, a hyperspectral face database was established, which contains 25 subjects and has 33 bands over the visible light spectrum (0.4μm -0.72μm).The experimental results demonstrated that multispectral face recognition with the selected feature bands outperforms that by using a single band, or using the whole bands, or, interestingly, using the conventional RGB color bands.

show abstract

Section: Introductionmentioning

confidence: 99%

Studies on Hyperspectral Face Recognition in Visible Spectrum With Feature Band Selection

Wei

Zhang

et al. 2010

IEEE Trans. Syst., Man, Cybern. A

124

View full text Add to dashboard Cite

show abstract

“…The transmittance through each colour layer is proportional to the exponential of the negative optical density for that layer. Such a simple model stands in contradistinction to a considerably more complex model based on Kubelka-Monk (KM) theory such as used in [2]. In the latter, full modelling of interreflection inside each layer is used to set up equations detailing light transport.…”

Section: Colour Space Image Formulationmentioning

confidence: 99%

“…KM theory has been found to be useful in tasks such as visualizing different components including surface and deep melanin etc. [2]. Here, we are simply focused on the classification task, and make use of the simpler model.…”

Section: Colour Space Image Formulationmentioning

confidence: 99%

“…In particular, the work of Claridge et al has figured prominently, with emphasis on the use of intermediate multispectral modelling to generate images disambiguating dermal and epidermal melanin, thickness of collagen, and blood [2]. At the same time, another stream of work has focused on using Independent Component Analysis (ICA) [3] in the context of 3-channel RGB images with no intermediate spectral-space model, aimed both at non-medical images and dermoscopic images of skin [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intrinsic Melanin and Hemoglobin Colour Components for Skin Lesion Malignancy Detection

Madooei

Drew

Sadeghi

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper we propose a new log-chromaticity 2-D colour space, an extension of previous approaches, which succeeds in removing confounding factors from dermoscopic images: (i) the effects of the particular camera characteristics for the camera system used in forming RGB images; (ii) the colour of the light used in the dermoscope; (iii) shading induced by imaging non-flat skin surfaces; (iv) and light intensity, removing the effect of light-intensity falloff toward the edges of the dermoscopic image. In the context of a blind source separation of the underlying colour, we arrive at intrinsic melanin and hemoglobin images, whose properties are then used in supervised learning to achieve excellent malignant vs. benign skin lesion classification. In addition, we propose using the geometric-mean of colour for skin lesion segmentation based on simple greylevel thresholding, with results outperforming the state of the art.

show abstract

“…It is based on the hypothesis that, because colours seen at the surface of a tissue reflect its internal structure and composition, it should be possible to recover this information from colour images of the tissue. This approach was successfully applied to skin imaging [2] and early clinical trials show its value in melanoma diagnosis [3].…”

Section: Introductionmentioning

confidence: 99%

An Inverse Method for the Recovery of Tissue Parameters from Colour Images

Claridge

Preece

2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. The interpretation of colour images is presented as an inverse problem in which a mapping is sought between image colour vectors and the physiological parameters characterizing a tissue. To ensure the necessary oneto-one correspondence between the image colours and the parameters, the mapping must be unique. This can be established through testing the sign of the determinant of the Jacobian matrix, a multi-dimensional equivalent of a discrete derivative, over the space of all parameter values. Furthermore, an optimisation procedure is employed to find the set of filters for image capture which generate image vectors minimizing the mapping error. This methodology applied to interpretation of skin images shows that the standard RGB system of filters provides for a unique mapping between image values and parameters characterizing the normal skin. It is further shown that an optimal set of filters reduces the error of quantification by a factor of 2, on average.

show abstract

From Colour to Tissue Histology: Physics Based Interpretation of Images of Pigmented Skin Lesions

Cited by 35 publications

References 14 publications

Studies on Hyperspectral Face Recognition in Visible Spectrum With Feature Band Selection

Studies on Hyperspectral Face Recognition in Visible Spectrum With Feature Band Selection

Intrinsic Melanin and Hemoglobin Colour Components for Skin Lesion Malignancy Detection

An Inverse Method for the Recovery of Tissue Parameters from Colour Images

Contact Info

Product

Resources

About