13 Result(s)
within
Luis Gustavo Nonato
-
Article
Mining Pareto-optimal counterfactual antecedents with a branch-and-bound model-agnostic algorithm
Mining counterfactual antecedents became a valuable tool to discover knowledge and explain machine learning models. It consists of generating synthetic samples from an original sample to achieve the desired outco...
-
Article
A river flooding detection system based on deep learning and computer vision
Although floods cause millions of dollars in economic and social losses each year, many people living in develo** countries, such as Brazil, do not have access to a flooding alert system because of its cost....
-
Chapter and Conference Paper
Extreme Learning Machine to Graph Convolutional Networks
Graph Convolutional Network (GCN) is a powerful model to deal with data arranged as a graph, a structured non-euclidian domain. It is known that GCN reaches high accuracy even when operating with just 2 layers...
-
Chapter and Conference Paper
Homicide Prediction Using Sequential Features from Graph Signal Processing
Crime prediction is challenging, especially homicide predictions due to the low-frequency and spatial sparsity of the occurrences. In this work, we made use of Laplacian of Gaussian spectral filtering on graph...
-
Chapter and Conference Paper
A New Multi-filter Framework with Statistical Dense SIFT Descriptor for Spoofing Detection in Fingerprint Authentication Systems
Fingerprint-based authentication systems represent what is most common in biometric authentication systems. Today’s simplest tasks, such as unlocking functions on a personal cell phone, may require its owner’s...
-
Chapter and Conference Paper
Interactive Image Colorization Using Laplacian Coordinates
Image colorization is a modern topic in computer vision which aims at manually adding colors to grayscale images. Techniques devoted to colorize images differ in many fundamental aspects as they often require ...
-
Article
Spectral Image Segmentation Using Image Decomposition and Inner Product-Based Metric
Image segmentation is an indispensable tool in computer vision applications, such as recognition, detection and tracking. In this work, we introduce a novel user-assisted image segmentation technique which com...
-
Article
Class-specific metrics for multidimensional data projection applied to CBIR
Content-based image retrieval is still a challenging issue due to the inherent complexity of images and choice of the most discriminant descriptors. Recent developments in the field have introduced multidimens...
-
Chapter
Consistent Approximation of Local Flow Behavior for 2D Vector Fields Using Edge Maps
Vector fields, represented as vector values sampled on the vertices of a triangulation, are commonly used to model physical phenomena. To analyze and understand vector fields, practitioners use derived propert...
-
Article
Editorial
-
Article
A topological approach for surface reconstruction from sample points
Most algorithms for surface reconstruction from sample points rely on computationally demanding operations to derive the reconstruction. In this paper we introduce an innovative approach for generating 3D piec...
-
Chapter and Conference Paper
An Edge-Preserving Multigrid-Like Technique for Image Denoising
Techniques based on the Well-Balanced Flow Equation have been employed as efficient tools for edge preserving noise removal. Although effective, this technique demands high computational effort, rendering it n...
-
Chapter and Conference Paper
Circulation and Topological Control in Image Segmentation
In this paper we present an image segmentation technique based on the concepts of circulation and topological control. Circulation is a mathematical tool widely used for engineering problems, but still little ...
