João Marques de Carvalho

PLAYER – a European Project and a Game to Foster Entrepreneurship Education for Young People

Entrepreneurship is widely recognized as one of the basic skills to be acquired through a life-long learning. The European Union, under the guidance of the Oslo Agenda, promotes several initiatives to develop entrepreneurship culture in Europe. Education can make a significant contribution to entrepreneurship, encouraging the development of entrepreneurial attitudes and skills in young people. Serious Games are presently recognised as having an important role and potential in education and social networks emerged in the last years as the platform preferred by many, especially young people, to socialize, play games and even learn. This paper presents the PLAYER project, in which a game was developed and implemented as a Facebook application, to enable learning entrepreneurial skills progressively, by guiding users to develop a business idea in the form of a business plan.

Confusion matrix disagreement for multiple classifiers

We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the disagreement concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a Distance-based Disagreement (DbD) measure using an Euclidean distance computed between confusion matrices and a soft-correlation rule to indicate the most likely candidates to the best classifiers ensemble. As case study, we apply this strategy to two different handwritten recognition systems. Experimental results indicate that the method proposed can be used as a low-cost alternative to conventional approaches.

Integral Local Binary Patterns: A Novel Approach Suitable for Texture-Based Object Detection Tasks

This work is concerned with the proposition and empirical evaluation of a new feature extraction approach that combines two existing image descriptors, Integral Histograms and Local Binary Patterns (LBP), to achieve a representation that exhibits relevant properties to object detection tasks (such as face detection): fast constant time processing, rotation, and scale invariance. This novel approach is called the Integral Local Binary Patterns (INTLBP), which is based on an existing method for calculating Integral Histograms from LBP images. This paper empirically demonstrates the properties of INTLBP in a scenario of texture extraction for face/non-face classification. Experiments have shown that the new representation added robustness to scale variations in the test images - the proposed approach achieved a mean classification rate 92% higher than the standard Rotation Invariant LBP approach, when testing over images with scales different from the ones used for training. Moreover, the INTLBP dramatically reduced the required processing time when searching patterns in a face detection task.

Investigation of local and global features for face detection

This work is concerned with the empirical evaluation of a set of local and global features under the context of frontal (including semi-profile) and full profile face classification. Integral LBP, Integral Histograms, PCA and Optimized Face Ratios features have been evaluated using SVM classifiers. A data set of about 14,000 face and 300,000 non face images has been used in the experiments. Face images were obtained from well known public face research databases, such as BioID, Color Feret, CMU PIE, among others. The PCA-SVM classifier presented best overall results for both frontal and full profile faces whereas the classifier based on Face Ratios presented the lowest classification rates. A weighted combination of all classifiers yielded high True Positive (TPR) and True Negative (TNR) rates: 91.7% and 100%, respectively, for the frontal face experiments; 99.59% and 99.62%, respectively, for the profile face experiments. These results indicate that the evaluated features are very suitable to the problem of face detection and that a simple classifier combination improves individual classifiers performance.

Neural network classification of photogenic facial expressions based on fiducial points and Gabor features

This work reports a study about the use of Gabor coefficients and coordinates of fiducial (landmark) points to represent facial features and allow the discrimination between photogenic and non-photogenic facial images, using neural networks. Experiments have been performed using 416 images from the Cohn-Kanade AU-Coded Facial Expression Database [1]. In order to extract fiducial points and classify the expressions, a manual processing was performed. The facial expression classifications were obtained with the help of the Action Unit information available in the image database. Various combinations of features were tested and evaluated. The best results were obtained with a weighted sum of a neural network classifier using Gabor coefficients and another using only the fiducial points. These indicated that fiducial points are a very promising feature for the classification performed.

A table-form extraction with artefact removal

We present a novel methodology for extracting the structure of handwritten filled table-forms. The method identifies the table-form line intersections, detecting and correcting wrong intersections produced by faulty line segments or by table artefacts. Examples of artefacts are overlapping data, broken segments, and smudges. A novel method for artefact identification and deletion is also proposed. The last step performs the extraction of table-form cells. A database of 350 table-form images was used for evaluation, showing that the artefact identification method improves the performance of the table-forms structure extractor. The proposed approach reached a success rate of 85%.

Local Binary Patterns Applied to Breast Cancer Classification in Mammographies

Among all cancer types, breast cancer is the one with the second highest incidence rate for women. Mammography is the most used method for breast cancer detection, as it reveals abnormalities such as masses, calcifications, asymmetries and architectural distortions. In this paper, we propose a classification method for breast cancer that has been tested for six different cancer types: CALC, CIRC, SPIC, MISC, ARCH, ASYM. The proposed approach is composed of a SVM classifier trained with LBP features. The MIAS image database was used in the experiments and ROC curves were generated. To the best of our knowledge, our approach is the first to handle those six different cancer types using the same technique. One important result of the proposed approach is that it was tested over six different breast cancer types proving to be generic enough to obtain high classification results in all cases.

An Improved Face Verification Approach Based on Speedup Robust Features and Pairwise Matching

Human faces are known to present large variability due to factors like pose and facial expression variations, changes in illumination and occlusion, among others, thus making face verification a very challenging problem. In this paper we address the problem of face verification with special interest on how to reduce degradation usually associated with face images acquired under uncontrolled environments. The approach we propose in this paper starts with a preprocessing step to correct in-plane face orientation and to compensate for illumination changes. SURF features are then extracted, which adds to the method a certain degree of invariance to pose, facial expression and other sources of variation. Taking the SURF features as input, an original pair wise face matching procedure is performed. The resulting matching scores are stored in a similarity matrix, which is then evaluated. An experimental study has revealed that the proposed approach produced the best ROC curve when compared to published work regarding the unsupervised setup of the Labeled Faces in the Wild (LFW) [1] face database.

Handwritten Word Recognition Using Multi-view Analysis

This paper brings a contribution to the problem of efficiently recognizing handwritten words from a limited size lexicon. For that, a multiple classifier system has been developed that analyzes the words from three different approximation levels, in order to get a computational approach inspired on the human reading process. For each approximation level a three-module architecture composed of a zoning mechanism (pseudo-segmenter), a feature extractor and a classifier is defined. The proposed application is the recognition of the Portuguese handwritten names of the months, for which a best recognition rate of 97.7% was obtained, using classifier combination.

Distance-based Disagreement Classifiers Combination

We present a methodology to analyze multiple classifiers systems (MCS) performance, using the diversity concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a distance-based disagreement (DbD) measure using an Euclidean distance computed between confusion matrices and a soft-correlation rule to indicate the most likely candidates to the best classifiers ensemble. As case study, we apply this strategy to two different handwritten recognition systems. Experimental results indicate that the method proposed can be used as a low-cost alternative to conventional approaches.