Spectral filter optimization for the recovery of parameters which describe human skin

Preece, Stephen; Claridge, Ela

doi:10.1109/tpami.2004.36

Cited by 37 publications

(35 citation statements)

References 23 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Phong model, on the other hand, considers both diffuse and specular reflection in a simple analytical form. Optical studies usually model human skin as three layers: sebum layer (mixture of sebum, lipids, and sweat), epidermis layer (stratum corneum and malpighian), and dermis layer (papillary dermis and reticular dermis) [24], [25], [29], as shown in Fig. 1.…”

Section: Related Workmentioning

confidence: 99%

“…The rest of the incident light penetrates these layers and is scattered to diffuse lights with equal intensity in all directions. Diffuse reflection then occurs on epidermis or dermis whose reflectivity is mainly dependent on the amount of melanin pigment, the amount of blood-borne hemoglobin pigments, and the thickness of collagen [29]. Both of the thickness of the sebum layer and the amount of melanin pigments vary spatially along human face surfaces, which make both diffuse and specular reflection components heterogeneous as stated in [8].…”

Section: Related Workmentioning

confidence: 99%

“…To minimize the objective function (13) or (14), a genetic algorithm (GA) is utilized similar to [29]. GA is a stochastic optimization method, which guides randomly selected solutions to evolve through a number of generations towards the global optimum and avoids differentiations of cost functions.…”

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Heterogeneous Specular and Diffuse 3-D Surface Approximation for Face Recognition Across Pose

Zhang

Gao

2012

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Abstract-This paper proposes a novel heterogeneous specular and diffuse (HSD) 3-D surface approximation which considers spatial variability of specular and diffuse reflections in face modelling and recognition. Traditional 3-D face modelling and recognition methods constrain human faces with either the Lambertian assumption or the homogeneity assumption, resulting in suboptimal shape and texture models. The proposed HSD approach allows both specular and diffuse reflectance coefficients to vary spatially to better accommodate surface properties of real human faces. From a small number of face images of a person under different lighting conditions, 3-D shape and surface reflectivity property are estimated using a localized stochastic optimization method. The resultant personalized 3-D face model is used to render novel gallery views under different poses for recognition across pose. The proposed approach is evaluated on both synthetic and real face datasets and benchmarked against the state-of-the-art approaches. Experimental results demonstrated that it can achieve a higher level of performances in modelling accuracy, algorithm reliability, and recognition accuracy, which suggests that face modelling and recognition beyond the Lambertian and homogeneity assumptions is a feasible and better solution towards pose-invariant face recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneous Specular and Diffuse 3-D Surface Approximation for Face Recognition Across Pose

Zhang

Gao

2012

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…We can then propagate this through mapping i to give the errors in the image values computed by the model. Further information on this method, applied to skin imaging, can be found in Preece and Claridge (2004). We will denote the error (standard deviation) of the j'th image value as σ(i j ).…”

Section: Error In the Construction Of Fmentioning

confidence: 99%

Quantitative analysis of multi-spectral fundus images

Styles

Calcagni

Claridge

et al. 2006

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

This report summarises the work done during the EPSRC-funded project "Physics-based image interpretation to aid the detection of early signs of retinopathies", grant number GR/S09906/01. We have developed a new technique for extracting histological parameters from multispectral images of the ocular fundus. The new method uses a Monte Carlo simulation of the reflectance of the fundus to model how the colouration of the tissue varies with differing tissue histology. The model is parameterised by the concentrations of the five main absorbers found in the fundus: retinal haemoglobins, choroidal haemoglobins, choroidal melanin, RPE melanin and macular pigment. These parameters are shown to give rise to distinct variations in the tissue colouration. We use the results of the Monte Carlo simulations to construct an inverse model which maps tissue colouration onto the model parameters. This allows the concentration and distribution of the five main absorbers to be determined from suitable multispectral images. We propose the use of "image quotients" to allow this information to be extracted from uncalibrated image data. The filters used to acquire the images are selected to ensure a one-to-one mapping between model parameters and image quotients. To recover five model parameters uniquely, images must be acquired from six distinct spectral bands. Theoretical investigations suggest that retinal haemoglobins and macular pigment can be recovered with RMS errors of less than 10%. We present parametric maps showing the variation of these parameters across the posterior pole of the fundus. The results are in agreement with known tissue histology for normal healthy subjects. We also present an early result which suggests that, with further development, the technique could be used to successfully detect retinal haemorrhages.

show abstract

“…Skin chromophores and their influence on skin color perception are a major concern in dermatology and cosmetics in order to evaluate pigmentation issues [1][2][3]. Non-invasive imaging systems of the skin are used in a wide range of clinical applications in the last decades, in particular in order to get information on pigmentation disorders: melanin index, port wine vein, vitiligo, erythema [4][5]… Since pigmentation determines the spectral reflectance of the skin, the best way to observe it is to make images in different spectral bands, either in three wide spectral bands as in classical RGB imaging [6][7], or in more than 10 short spectral bands as in multispectral imaging [8][9].…”

Section: Introductionmentioning

confidence: 99%