RESUMEN

Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by [Formula: see text] and [Formula: see text]. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to [Formula: see text] for the binary image segmentation approach.

Asunto(s)

RESUMEN

The application of deep learning to image and video processing has become increasingly popular nowadays. Employing well-known pre-trained neural networks for detecting and classifying objects in images is beneficial in a wide range of application fields. However, diverse impediments may degrade the performance achieved by those neural networks. Particularly, Gaussian noise and brightness, among others, may be presented on images as sensor noise due to the limitations of image acquisition devices. In this work, we study the effect of the most representative noise types and brightness alterations on images in the performance of several state-of-the-art object detectors, such as YOLO or Faster-RCNN. Different experiments have been carried out and the results demonstrate how these adversities deteriorate their performance. Moreover, it is found that the size of objects to be detected is a factor that, together with noise and brightness factors, has a considerable impact on their performance.

RESUMEN

Anomaly detection in sequences is a complex problem in security and surveillance. With the exponential growth of surveillance cameras in urban roads, automating them to analyze the data and automatically identify anomalous events efficiently is essential. This paper presents a methodology to detect anomalous events in urban sequences using pre-trained convolutional neural networks (CNN) and super-resolution (SR) models. The proposal is composed of two parts. In the offline stage, the pre-trained CNN model evaluated a large dataset of urban sequences to detect and establish the common locations of the elements of interest. Analyzing the offline sequences, a density matrix is calculated to learn the spatial patterns and identify the most frequent locations of these elements. Based on probabilities previously calculated from the offline analysis, the pre-trained CNN, now in an online stage, assesses the probability of anomalies appearing in the real-time sequence using the density matrix. Experimental results demonstrate the effectiveness of the presented approach in detecting several anomalies, such as unusual pedestrian routes. This research contributes to urban surveillance by providing a practical and reliable method to improve public safety in urban environments. The proposed methodology can assist city management authorities in proactively detecting anomalies, thus enabling timely reaction and improving urban safety.

RESUMEN

In this work we implement a COVID-19 infection detection system based on chest X-ray images with uncertainty estimation. Uncertainty estimation is vital for safe usage of computer aided diagnosis tools in medical applications. Model estimations with high uncertainty should be carefully analyzed by a trained radiologist. We aim to improve uncertainty estimations using unlabelled data through the MixMatch semi-supervised framework. We test popular uncertainty estimation approaches, comprising Softmax scores, Monte-Carlo dropout and deterministic uncertainty quantification. To compare the reliability of the uncertainty estimates, we propose the usage of the Jensen-Shannon distance between the uncertainty distributions of correct and incorrect estimations. This metric is statistically relevant, unlike most previously used metrics, which often ignore the distribution of the uncertainty estimations. Our test results show a significant improvement in uncertainty estimates when using unlabelled data. The best results are obtained with the use of the Monte Carlo dropout method.

RESUMEN

Self-organizing maps (SOMs) are aimed to learn a representation of the input distribution which faithfully describes the topological relations among the clusters of the distribution. For some data sets and applications, it is known beforehand that some regions of the input space cannot contain any samples. Those are known as forbidden regions. In these cases, any prototype which lies in a forbidden region is meaningless. However, previous self-organizing models do not address this problem. In this paper, we propose a new SOM model which is guaranteed to keep all prototypes out of a set of prespecified forbidden regions. Experimental results are reported, which show that our proposal outperforms the SOM both in terms of vector quantization error and quality of the learned topological maps.

RESUMEN

Image segmentation is a common goal in many medical applications, as its use can improve diagnostic capability and outcome prediction. In order to assess the wound healing rate in diabetic foot ulcers, some parameters from the wound area are measured. However, heterogeneity of diabetic skin lesions and the noise present in images captured by digital cameras make wound extraction a difficult task. In this work, a Deep Learning based method for accurate segmentation of wound regions is proposed. In the proposed method, input images are first processed to remove artifacts and then fed into a Convolutional Neural Network (CNN), producing a probability map. Finally, the probability maps are processed to extract the wound region. We also address the problem of removing some false positives. Experiments show that our method can achieve high performance in terms of segmentation accuracy and Dice index.

Asunto(s)

RESUMEN

One of the most important challenges in computer vision applications is the background modeling, especially when the background is dynamic and the input distribution might not be stationary, i.e. the distribution of the input data could change with time (e.g. changing illuminations, waving trees, water, etc.). In this work, an unsupervised learning neural network is proposed which is able to cope with progressive changes in the input distribution. It is based on a dual learning mechanism which manages the changes of the input distribution separately from the cluster detection. The proposal is adequate for scenes where the background varies slowly. The performance of the method is tested against several state-of-the-art foreground detectors both quantitatively and qualitatively, with favorable results.

Asunto(s)

RESUMEN

The growing neural gas (GNG) self-organizing neural network stands as one of the most successful examples of unsupervised learning of a graph of processing units. Despite its success, little attention has been devoted to its extension to a hierarchical model, unlike other models such as the self-organizing map, which has many hierarchical versions. Here, a hierarchical GNG is presented, which is designed to learn a tree of graphs. Moreover, the original GNG algorithm is improved by a distinction between a growth phase where more units are added until no significant improvement in the quantization error is obtained, and a convergence phase where no unit creation is allowed. This means that a principled mechanism is established to control the growth of the structure. Experiments are reported, which demonstrate the self-organization and hierarchy learning abilities of our approach and its performance for vector quantization applications.

RESUMEN

In this work, a novel self-organizing model called growing neural forest (GNF) is presented. It is based on the growing neural gas (GNG), which learns a general graph with no special provisions for datasets with separated clusters. On the contrary, the proposed GNF learns a set of trees so that each tree represents a connected cluster of data. High dimensional datasets often contain large empty regions among clusters, so this proposal is better suited to them than other self-organizing models because it represents these separated clusters as connected components made of neurons. Experimental results are reported which show the self-organization capabilities of the model. Moreover, its suitability for unsupervised clustering and foreground detection applications is demonstrated. In particular, the GNF is shown to correctly discover the connected component structure of some datasets. Moreover, it outperforms some well-known foreground detectors both in quantitative and qualitative terms.

Asunto(s)

Asunto(s)

RESUMEN

The original Self-Organizing Feature Map (SOFM) has been extended in many ways to suit different goals and application domains. However, the topologies of the map lattice that we can found in literature are nearly always square or, more rarely, hexagonal. In this paper we study alternative grid topologies, which are derived from the geometrical theory of tessellations. Experimental results are presented for unsupervised clustering, color image segmentation and classification tasks, which show that the differences among the topologies are statistically significant in most cases, and that the optimal topology depends on the problem at hand. A theoretical interpretation of these results is also developed.

Asunto(s)

RESUMEN

Growing hierarchical self-organizing models are characterized by the flexibility of their structure, which can easily accommodate for complex input datasets. However, most proposals use the Euclidean distance as the only error measure. Here we propose a way to introduce Bregman divergences in these models, which is based on stochastic approximation principles, so that more general distortion measures can be employed. A procedure is derived to compare the performance of networks using different divergences. Moreover, a probabilistic interpretation of the model is provided, which enables its use as a Bayesian classifier. Experimental results are presented for classification and data visualization applications, which show the advantages of these divergences with respect to the classical Euclidean distance.

Asunto(s)

RESUMEN

The estimation of multivariate probability density functions has traditionally been carried out by mixtures of parametric densities or by kernel density estimators. Here we present a new nonparametric approach to this problem which is based on the integration of several multivariate histograms, computed over affine transformations of the training data. Our proposal belongs to the class of averaged histogram density estimators. The inherent discontinuities of the histograms are smoothed, while their low computational complexity is retained. We provide a formal proof of the convergence to the real probability density function as the number of training samples grows, and we demonstrate the performance of our approach when compared with a set of standard probability density estimators.

RESUMEN

The quality of self-organizing maps is always a key issue to practitioners. Smooth maps convey information about input data sets in a clear manner. Here a method is presented to modify the learning algorithm of self-organizing maps to reduce the number of topology errors, hence the obtained map has better quality at the expense of increased quantization error. It is based on avoiding maps that self-intersect or nearly so, as these states are related to low quality. Our approach is tested with synthetic data and real data from visualization, pattern recognition and computer vision applications, with satisfactory results.

RESUMEN

Background modeling and foreground detection are key parts of any computer vision system. These problems have been addressed in literature with several probabilistic approaches based on mixture models. Here we propose a new kind of probabilistic background models which is based on probabilistic self-organising maps. This way, the background pixels are modeled with more flexibility. On the other hand, a statistical correlation measure is used to test the similarity among nearby pixels, so as to enhance the detection performance by providing a feedback to the process. Several well known benchmark videos have been used to assess the relative performance of our proposal with respect to traditional neural and non neural based methods, with favourable results, both qualitatively and quantitatively. A statistical analysis of the differences among methods demonstrates that our method is significantly better than its competitors. This way, a strong alternative to classical methods is presented.

Asunto(s)

RESUMEN

Since the introduction of the growing hierarchical self-organizing map, much work has been done on self-organizing neural models with a dynamic structure. These models allow adjusting the layers of the model to the features of the input dataset. Here we propose a new self-organizing model which is based on a probabilistic mixture of multivariate Gaussian components. The learning rule is derived from the stochastic approximation framework, and a probabilistic criterion is used to control the growth of the model. Moreover, the model is able to adapt to the topology of each layer, so that a hierarchy of dynamic graphs is built. This overcomes the limitations of the self-organizing maps with a fixed topology, and gives rise to a faithful visualization method for high-dimensional data.

Asunto(s)

RESUMEN

Kernel regression is a non-parametric estimation technique which has been successfully applied to image denoising and enhancement in recent times. Magnetic resonance 3D image denoising has two features that distinguish it from other typical image denoising applications, namely the tridimensional structure of the images and the nature of the noise, which is Rician rather than Gaussian or impulsive. Here we propose a principled way to adapt the general kernel regression framework to this particular problem. Our noise removal system is rooted on a zeroth order 3D kernel regression, which computes a weighted average of the pixels over a regression window. We propose to obtain the weights from the similarities among small sized feature vectors associated to each pixel. In turn, these features come from a second order 3D kernel regression estimation of the original image values and gradient vectors. By considering directional information in the weight computation, this approach substantially enhances the performance of the filter. Moreover, Rician noise level is automatically estimated without any need of human intervention, i.e. our method is fully automated. Experimental results over synthetic and real images demonstrate that our proposal achieves good performance with respect to the other MRI denoising filters being compared.

Asunto(s)

RESUMEN

We present a self-organizing map model to study qualitative data (also called categorical data). It is based on a probabilistic framework which does not assume any prespecified distribution of the input data. Stochastic approximation theory is used to develop a learning rule that builds an approximation of a discrete distribution on each unit. This way, the internal structure of the input dataset and the correlations between components are revealed without the need of a distance measure among the input values. Experimental results show the capabilities of the model in visualization and unsupervised learning tasks.

Asunto(s)

RESUMEN

The original self-organizing feature map did not define any probability distribution on the input space. However, the advantages of introducing probabilistic methodologies into self-organizing map models were soon evident. This has led to a wide range of proposals which reflect the current emergence of probabilistic approaches to computational intelligence. The underlying estimation theories behind them derive from two main lines of thought: the expectation maximization methodology and stochastic approximation methods. Here, we present a comprehensive view of the state of the art, with a unifying perspective of the involved theoretical frameworks. In particular, we examine the most commonly used continuous probability distributions, self-organization mechanisms, and learning schemes. Special emphasis is given to the connections among them and their relative advantages depending on the characteristics of the problem at hand. Furthermore, we evaluate their performance in two typical applications of self-organizing maps: classification and visualization.

Asunto(s)

RESUMEN

Robustness against outliers is a desirable property of any unsupervised learning scheme. In particular, probability density estimators benefit from incorporating this feature. A possible strategy to achieve this goal is to substitute the sample mean and the sample covariance matrix by more robust location and spread estimators. Here we use the L1-median to develop a nonparametric probability density function (PDF) estimator. We prove its most relevant properties, and we show its performance in density estimation and classification applications.

Asunto(s)