Domenec Puig

Breast Masses Identification through Pixel-Based Texture Classification

Mammographic image analysis plays an important role in computer-aided breast cancer diagnosis. To improve the existing knowledge, this paper proposes a new efficient pixel-based methodology for tumor vs non-tumor classification. The proposed method firstly computes a Gabor feature pool from the mammogram. This feature set is calculated through multi-sized evaluation windows applied to the probabilistic distribution moments, in order to improve the accuracy of the whole system. To deal with a high dimensional data space and a large amount of features, we apply both a linear and non-linear pixel classification stage by using Support Vector Machines (SVMs). The randomness is encoded when training each SVM using randomly sample sets and, in consequence, randomly selected features from the whole feature bank obtained in the first stage. The proposed method has been validated using real mammographic images from well-known databases and its effectiveness is demonstrated in the experimental section.

PIXEL-BASED TEXTURE CLASSIFICATION BY INTEGRATION OF MULTIPLE FEATURE EXTRACTION METHODS EVALUATED OVER MULTISIZED WINDOWS

This paper presents a pixel-based texture classifier oriented to the identification of texture models that can be present in an input image, given a set of models known in advance. The proposed methodology is based on the integration of texture features generated by texture methods that belong to different families, which are evaluated over multiple windows of different sizes. This is a novelty with respect to the current texture classifiers, which are based on specific families of texture methods evaluated over single windows of a size defined empirically. Experiments show that this integration strategy produces better results than classical texture classifiers based on specific families of texture methods.

Instant Measurement of the Difficulty Level of Exergames with Simple Uni-dimensional Level Goals for Cerebral Palsy Players

In this paper we propose a solution to introduce a function for difficulty degree of achieving a simple, uni-dimensional goal of a level of an exergame. This solution, takes advantage of a statistical method built upon the results of the specific cerebral palsy (CP) player under study, inspired from normal distribution. It is appropriate for CPs, since it favors a content-based approach which is formed upon each player’s personal results. Using a population of 20 CP patients trying to achieve the goals of games, we arrived to an 85% correlation between number of goal achievement failures and our introduced difficulty function.