Francisco J. Galdames

An accurate skull stripping method based on simplex meshes and histogram analysis for magnetic resonance images

Skull stripping methods are designed to eliminate the non-brain tissue in magnetic resonance (MR) brain images. Removal of non-brain tissues is a fundamental step in enabling the processing of brain MR images. The aim of this study is to develop an automatic accurate skull stripping method based on deformable models and histogram analysis. A rough-segmentation step is used to find the optimal starting point for the deformation and is based on thresholds and morphological operators. Thresholds are computed using comparisons with an atlas, and modeling by Gaussians. The deformable model is based on a simplex mesh and its deformation is controlled by the image local gray levels and the information obtained on the gray level modeling of the rough-segmentation. Our Simplex Mesh and Histogram Analysis Skull Stripping (SMHASS) method was tested on the following international databases commonly used in scientific articles: BrainWeb, Internet Brain Segmentation Repository (IBSR), and Segmentation Validation Engine (SVE). A comparison was performed against three of the best skull stripping methods previously published: Brain Extraction Tool (BET), Brain Surface Extractor (BSE), and Hybrid Watershed Algorithm (HWA). Performance was measured using the Jaccard index (J) and Dice coefficient (κ). Our method showed the best performance and differences were statistically significant (p<0.05): J=0.904 and κ=0.950 on BrainWeb; J=0.905 and κ=0.950 on IBSR; J=0.946 and κ=0.972 on SVE.

Fusion of local normalization and Gabor entropy weighted features for face identification

Face recognition is one of the most extensively studied topics in image analysis because of its wide range of possible applications such as in surveillance, access control, content-based video search, human-computer interaction, electronic advertisement and more. Face identification is a one-to-n matching problem where a captured face is compared to n samples in a database. In this work we propose two new methods for face identification. The first one combines entropy-like weighted Gabor features with the local normalization of Gabor features. The second fuses the entropy-like weighted Gabor features at the score level with the local binary pattern (LBP) applied to the magnitude (LGBP) and phase (LGXP) components of the Gabor features. We used the FERET, AR, and FRGC 2.0 databases to test and compare our results with those previously published. Results on these databases show significant improvement relative to previously published results, reaching the best performance on the FERET and AR databases. Our methods also showed significant robustness to slight pose variations. We tested the proposed methods assuming noisy eye detection to check their robustness to inexact face alignment. Results show that the proposed methods are robust to errors of up to 3 pixels in eye detection. HighlightsWe propose an entropy weighted strategy over selected Gabor features.We fuse local normalization with Gabor features to improve face identification.Fusion of different features improve face identification relative to cases with no fusion.Our results are compared advantageously on several international face databases.We tested our methods with variable illumination, gesticulation, pose and occlusion.

Face recognition under pose variation with local Gabor features enhanced by Active Shape and Statistical Models

Face recognition is one of the most active areas of research in computer vision. Gabor features have been used widely in face identification because of their good results and robustness. However, the results of face identification strongly depend on how different are the test and gallery images, as is the case in varying face pose. In this paper, a new Gabor-based method is proposed which modifies the grid from which the Gabor features are extracted using a mesh to model face deformations produced by varying pose. Also, a statistical model of the scores computed by using the Gabor features is used to improve recognition performance across pose. Our method incorporates blocks for illumination compensation by a Local Normalization method, and entropy weighted Gabor features to emphasize those features that improve proper identification. The method was tested on the FERET and CMU-PIE databases. Our literature review focused on articles with face identification with wide pose variation. Our results, compared to those of the literature review, achieved the highest classification accuracy on the FERET database with 2D face recognition methods. The performance obtained in the CMU-PIE database is among those obtained by the best methods published. HighlightsA local matching Gabor method is improved with an Active Shape and a Statistical Model.The enhanced model is applied to recognize faces with significant pose variation.Comprehensive tests were performed on the FERET and CMU-PIE databases.Results improved from 31.1% to 70.57% in the extreme poses of the databases.We reached the highest results with pose variation compared to any previous 2D method.

Linear versus nonlinear neural modeling for 2-D pattern recognition

This paper compares the classification performance of linear-system- and neural-network-based models in handwritten-digit classification and face recognition. In inputs to a linear classifier, nonlinear inputs are generated based on linear inputs, using different forms of generating products. Using a genetic algorithm, linear and nonlinear inputs to the linear classifier are selected to improve classification performance. Results show that an appropriate set of linear and nonlinear inputs to the linear classifier were selected, improving significantly its classification performance in both problems. It is also shown that the linear classifier reached a classification performance similar to or better than those obtained by nonlinear neural-network classifiers with linear inputs.

Real-time SPECT and 2D ultrasound image registration

In this paper we present a technique for fully automatic, real-time 3D SPECT (Single Photon Emitting Computed Tomography) and 2D ultrasound image registration. We use this technique in the context of kidney lesion diagnosis. Our registration algorithm allows a physician to perform an ultrasound exam after a SPECT image has been acquired and see in real time the registration of both modalities. An automatic segmentation algorithm has been implemented in order to display in 3D the positions of the acquired US images with respect to the organs.

Face recognition under pose variation with active shape model to adjust Gabor filter kernels and to correct feature extraction location

Gabor features have been used widely in face identification because of their good results and robustness. However, face identification is strongly affected when the test images are very different from those of the gallery, as is the case in varying face pose. In this paper, a new 2D Gabor-based method is proposed that modifies the grid from which the Gabor features are extracted using a mesh to model face deformations produced by varying pose. Also the Gabor filter kernels are modified by the deformation field computed using the active shape model adjusted to the face. Therefore, the position of the Gabor jets with respect to the face features (eyes, nose, mouth, etc.) is closer to the original position in the frontal face and the modified Gabor filter kernel adjusts to the varying pose. Our method incorporates blocks for illumination compensation by a Local Normalization method, and entropy-weighted Gabor features to emphasize those features that yield proper identification. The method was assessed on the FERET database including pose variations for ±60°, ±40°, ±25°, ±15°, and 0°. We compared our results to those previously published for 2D methods. Our proposed method achieved the highest classification accuracy on the FERET database.

Real Time Cardiac SPECT and 2D Ultrasound Image Registration

In this paper we present a technique for fully automatic, real-time cardiac SPECT (Single Photon Emitting Computed Tomography) and 2D ultrasound image registration. Our registration algorithm allows a physician to perform an ultrasound exam after a series of ECG-gated SPECT images has been acquired and see in real time the registration of both modalities. A specific ECG segmentation algorithm has been developed in order to associate each US image acquired on the fly with the appropriate SPECT volume representing a heart-beat instant.