Moacir Ponti

Image quantization as a dimensionality reduction procedure in color and texture feature extraction

The image-based visual recognition pipeline includes a step that converts color images into images with a single channel, obtaining a color-quantized image that can be processed by feature extraction methods. In this paper we explore this step in order to produce compact features that can be used in retrieval and classification systems. We show that different quantization methods produce very different results in terms of accuracy. While compared with more complex methods, this procedure allows the feature extraction in order to achieve a significant dimensionality reduction, while preserving or improving system accuracy. The results indicate that quantization simplify images before feature extraction and dimensionality reduction, producing more compact vectors and reducing system complexity.

Improving accuracy and speed of optimum-path forest classifier using combination of disjoint training subsets

The Optimum-Path Forest (OPF) classifier is a recent and promising method for pattern recognition, with a fast training algorithm and good accuracy results. Therefore, the investigation of a combining method for this kind of classifier can be important for many applications. In this paper we report a fast method to combine OPF-based classifiers trained with disjoint training subsets. Given a fixed number of subsets, the algorithm chooses random samples, without replacement, from the original training set. Each subset accuracy is improved by a learning procedure. The final decision is given by majority vote. Experiments with simulated and real data sets showed that the proposed combining method is more efficient and effective than naive approach provided some conditions. It was also showed that OPF training step runs faster for a series of small subsets than for the whole training set. The combining scheme was also designed to support parallel or distributed processing, speeding up the procedure even more.

A markov random field model for combining optimum-path forest classifiers using decision graphs and game strategy approach

The research on multiple classifiers systems includes the creation of an ensemble of classifiers and the proper combination of the decisions. In order to combine the decisions given by classifiers, methods related to fixed rules and decision templates are often used. Therefore, the influence and relationship between classifier decisions are often not considered in the combination schemes. In this paper we propose a framework to combine classifiers using a decision graph under a random field model and a game strategy approach to obtain the final decision. The results of combining Optimum-Path Forest (OPF) classifiers using the proposed model are reported, obtaining good performance in experiments using simulated and real data sets. The results encourage the combination of OPF ensembles and the framework to design multiple classifier systems.

A decision cognizant Kullback-Leibler divergence

In decision making systems involving multiple classifiers there is the need to assess classifier (in)congruence, that is to gauge the degree of agreement between their outputs. A commonly used measure for this purpose is the Kullback–Leibler (KL) divergence. We propose a variant of the KL divergence, named decision cognizant Kullback–Leibler divergence (DC-KL), to reduce the contribution of the minority classes, which obscure the true degree of classifier incongruence. We investigate the properties of the novel divergence measure analytically and by simulation studies. The proposed measure is demonstrated to be more robust to minority class clutter. Its sensitivity to estimation noise is also shown to be considerably lower than that of the classical KL divergence. These properties render the DC-KL divergence a much better statistic for discriminating between classifier congruence and incongruence in pattern recognition systems.

Better than counting seconds: Identifying fallers among healthy elderly using fusion of accelerometer features and dual-task Timed Up and Go

Devices and sensors for identification of fallers can be used to implement actions to prevent falls and to allow the elderly to live an independent life while reducing the long-term care costs. In this study we aimed to investigate the accuracy of Timed Up and Go test, for fallers’ identification, using fusion of features extracted from accelerometer data. Single and dual tasks TUG (manual and cognitive) were performed by a final sample (94% power) of 36 community dwelling healthy older persons (18 fallers paired with 18 non-fallers) while they wear a single triaxial accelerometer at waist with sampling rate of 200Hz. The segmentation of the TUG different trials and its comparative analysis allows to better discriminate fallers from non-fallers, while conventional functional tests fail to do so. In addition, we show that the fusion of features improve the discrimination power, achieving AUC of 0.84 (Sensitivity = Specificity = 0.83, 95% CI 0.62-0.91), and demonstrating the clinical relevance of the study. We concluded that features extracted from segmented TUG trials acquired with dual tasks has potential to improve performance when identifying fallers via accelerometer sensors, which can improve TUG accuracy for clinical and epidemiological applications.

Ensembles of Optimum-Path Forest Classifiers Using Input Data Manipulation and Undersampling

The combination of multiple classifiers was proven to be useful in many applications to improve the classification task and stabilize results. In this paper we used the Optimum-Path Forest (OPF) classifier to investigate input data manipulation techniques in order to use less data from the training set without hampering the classification accuracy. The data undersampling can be useful to speed-up the classification task, and could be specially useful with large datasets. The results indicate that the OPF-based ensemble methods allow a significant reduction on the size of the training set, while maintaining or slightly improving accuracy. We provide intuition for a case of failure and report the results of synthetic and real datasets.

Deep Convolutional Neural Networks and Noisy Images.

The presence of noise represent a relevant issue in image feature extraction and classification. In deep learning, representation is learned directly from the data and, therefore, the classification model is influenced by the quality of the input. However, the ability of deep convolutional neural networks to deal with images that have a different quality when compare to those used to train the network is still to be fully understood. In this paper, we evaluate the generalization of models learned by different networks using noisy images. Our results show that noise cause the classification problem to become harder. However, when image quality is prone to variations after deployment, it might be advantageous to employ models learned using noisy data.

Precision Agriculture: Using Low-Cost Systems to Acquire Low-Altitude Images.

Low cost remote sensing imagery has the potential to make precision farming feasible in developing countries. In this article, the authors describe image acquisition from eucalyptus, bean, and sugarcane crops acquired by low-cost and low-altitude systems. They use different approaches to handle low-altitude images in both the RGB and NIR (near-infrared) bands to estimate and quantify plantation areas.

Color description of low resolution images using fast bitwise quantization and border-interior classification

Image classification often require preprocessing and feature extraction steps that are directly related to the accuracy and speed of the whole task. In this paper we investigate color features extracted from low resolution images, assessing the influence of the resolution settings on the final classification accuracy. We propose a border-interior classification extractor with a logarithmic distance function in order to maintain the discrimination capability in different resolutions. Our study shows that the overall computational effort can be reduced in 98%. Besides, a fast bitwise quantization is performed for its efficiency on converting RGB images to one channel images. The contributions can benefit many applications, when dealing with a large number of images or in scenarios with limited network bandwidth and concerns with power consumption.

Microscope Volume Segmentation Improved through Non-Linear Restoration

An efficient segmentation technique based on the use of a modified k-Means algorithm and the Otsu’s thresholding method is improved through a non-linear restoration of microscope volumes. An algorithm is proposed to automatically compute the k value for the clustering k-Means method. The unsupervised algorithm is used in the context of segmentation by considering regions as clusters. A comparison between the segmentation results before and after restoration is presented. The evaluation of the region segmentation included the root mean squared error and a normalized uniformity measure. Results showed significant improvement of segmentation when using the non-linear restoration method based on prior known information, such as the imaging system and the noise statistics.