David Delgado Gomez's research while affiliated with University Carlos III de Madrid and other places

Publications (16)

Conference Paper
In this work, the effect of introducing Sparse Principal Component Analysis within the Similarity-based Fisherfaces algorithm is examined. The technique aims at mimicking the human ability to discriminate faces by projecting the faces in a highly discriminative and easy interpretative way. Pixel intensities are used by Sparse Principal Component An...
Article
In this article, an expert system based on support vector machines is developed to predict the sale performance of some insurance company candidates. The system predicts the performance of these candidates based on some scores, which are measurements of cognitive characteristics, personality, selling skills and biodata. An experiment is conducted t...
Conference Paper
This paper addresses the main difficulty in adopting Viola-Jones-type object detection systems: their training time. Large training times are the result of having to repeatedly evaluate thousands of Haar-like features (HFs) in a database of object and clutter class images. The proposed object detector is fast to train mainly because of three reason...
Article
Advanced parental age has been shown to increase offspring risk for a number of neuropsychiatric disorders including schizophrenia and Down's syndrome. Other psychiatric disorders have been less studied with respect to the effect of parental age on offspring risk. In this study we examine if advanced parental age increased risk for ICD-10 diagnoses...
Conference Paper
This paper proposes Gaussian weak classifiers (GWCs) for use in real-time face detection systems. GWCs are based on Haar-like features (HFs) with four rectangles (HF4s), which constitute the majority of the HFs used to train a face detector. To label an image as face or clutter (non-face), GWC uses the responses of the two HF2s in a HF4 to compute...
Article
In this paper, an unsupervised algorithm, called the Independent Histogram Pursuit (IHP), for segmenting dermatological lesions is proposed. The algorithm estimates a set of linear combinations of image bands that enhance different structures embedded in the image. In particular, the first estimated combination enhances the contrast of the lesion t...
Article
Change monitoring in skin lesion analysis has proven to be a useful adjunct in their assessment. This article presents a comparative study of the available change detection techniques applied to change visualization and quantification in bi-temporal psoriasis images. The chosen methods are evaluated on a time series of psoriasis images and results...
Conference Paper
Full-text available
The accuracy of data classification methods depends con- siderably on the data representation and on the selected features. In this work, the elastic net model selection is used to identify meaningful and important features in face recognition. Modelling the characteristics which distinguish one person from another using only subsets of features wi...
Article
In this work, an integrated imaging system to obtain accurate and reproducible multi-spectral images and a novel multi-spectral image segmentation algorithm are proposed. The system collects up to 20 different spectral bands within a range that vary from 395 nm to 970 nm. The system is designed to acquire geometrically and chromatically corrected i...
Article
In this article, an integrated imaging system for acquisition of accurate standardized images is proposed. The system also aims at making highly reproducible images over time, so images taken at different times can be compared. The system is made up of an integrating intensity sphere illumination together with a high resolution 3CCD color camera. T...
Article
Full-text available
In this paper, a novel algorithm for facial recogni- tion is proposed. The technique combines the color texture and geometrical configuration provided by face images. Landmarks and pixel intensities are used by Principal Component Analysis and Fisher Linear Discriminant Analysis to associate a one dimensional projection to each person belonging to...
Conference Paper
Nowadays, the medical tracking of dermatological diseases is imprecise, mainly due to the lack of suitable objective methods to evaluate the lesion. The severity of the disease is currently scored by doctors merely by means of visual examination. In this work, multiset canonical correlation analysis over registered images is proposed to track the e...
Conference Paper
The multi-variate alteration detection transform is applied to pairs of within and between time varying registered psoriasis image patterns. Color band contribution to the variates explaining maximal change is analyzed.
Conference Paper
Nowadays the medical tracking of dermatological diseases is imprecise. The main reason is the lack of suitable objective methods to evaluate the lesion. The severity of the disease is scored by doctors just through their visual examination. In this work, a system to take accurate images of dermatological lesions has been developed. Mathematical met...
Article
Full-text available
One of the most important tasks in the treatment of psoriasis is to evaluate the degree of the illness. Each doctor usually treats a high num-ber of patients. This together with the fact that the time between visits can be weeks or even months makes the monitoring of the treatment dif-ficult. Each time that a patient goes to the hospital, doctors t...

Citations

... However, this method does not discriminate eyes, lips or hair from the rest of the body surface. In the study by Delgado Gomez et al. (2002), the Gabor filter was used, but it was unable to detect plaques covered with white scales. In the two studies mentioned above, plaques covered by hair were also not detected. ...
... A test person was recognized as one of the enrolled users if the distance of his/her corresponding one-dimensional projection on the member's projection line with respect to the mean of the available member projections was lower than a given threshold. Later, Fagertun et al. (2005) adopted a similar approach which included geometry. However, as it is indicated by Bishop (2006), the reduction onto a single dimension leads to a considerable loss of information, and classes that are well separated in the original space may become overlapping in the one-dimensional space. ...
... Computeraided analysis has been introduced into the area of psoriasis severity diagnosis for a number of decades, but only a very few systems have been implemented that focus on analysing the changes in psoriasis lesions. The only system so far is given in [2], where lesion changes are analysed through lesion image subtraction after registering images of the same lesion. The registration is implemented based on an assumption that in the treatment the psoriatic lesion boundaries do not change and the changes only happen inside the lesion. ...
... The purpose of radiometric calibration is to eliminate problems with uneven intensities and vignetting so that the pixel values represent actual measurement of light (Hamey, 2008). The geometric calibration is performed to ensure that geometric distortions do not affect the accuracy of the images, providing pixel correspondence for all spectra bands (Hansen, 1999;Gomez et al., 2007). ...
... The software applications and the computerbased systems, that support the medical experts in diagnosis and choosing of the adequate therapy according to the clinical form and status of the disorder, represent a real need and have the role to improve the quality of medical services and assistance. There are only few attempts in this field, through the research work performed by several teams in Poland [7][8], Denmark [9][10] and Malaysia [11][12] [13]. However, those individual studies did not converge to a computer-based system and software application, commonly accepted as a standard. ...
... Most common approach towards face recognition problem is done through dimension reduction by Eigen spaces [1-3, 6, 9, 18, 19, 23, 25, 37, 38]. Face recognition without Eigen spaces, namely, pairwise face recognition, has been extensively studied during past decay [7,8,10,11,13,[20][21][22]. Nevertheless, it is still an on-going in terms of state-of-the-arts complex nature as well as several practical factors such as illumination, pose, expression, and so on. ...
... Our research is focused on the development of a pattern recognition scheme that does not rely heavily on geometry and calculus as deformable templates. The use of Fisherfaces seems to be a suitable method for face recognition, due to its capacity, simplicity, speed and learning ( Delgado-Gomez et al., 2009). The agents in charge of classifying into age groups, interact with agents in charge of the pre-processing of images and the database for training. ...
... To demonstrate that the IHP is not limited to melanoma or RGB images and that it can be also successfully applied to other dermatological images as well as multispectral images, two psoriasis datasets have been chosen. The first dataset is a 35-image subset of the database introduced in Delgado et al. [26]. The second dataset is composed of nine multispectral images [13]. ...
... In contrast to rule-based methods, machine-learning-based methods have been widely applied in human performance modeling and have exhibited better performance. Delgado-Gómez et al. [2] developed an expert system based on support vector machines to predict the future performance of the salesmen candidates in an insurance company, which could help to reduce direct or indirect spending of organizations. Valle et al. [3] used a naive Bayesian classifier to predict the future performance of sales agents in a call center. ...
... Concerning parental age at delivery, there is a significant number of studies supporting its value as a risk factor for the development of schizophrenia [10,13,14,31,38,44,45,54,76,77,80,81,101,112,118,120,128]. One meta-analysis concluded that higher paternal age doubles or triples the risk for schizophrenia in the offspring of men above 40 years of age but also of younger fathers (< 25) [89]. ...