Francisco Estrada - Academia.edu (original) (raw)

Francisco Estrada

Uploads

Papers by Francisco Estrada

Research paper thumbnail of Robust Boundary DetectionWith Adaptive Grouping

Research paper thumbnail of Stochastic Image Denoising

Research paper thumbnail of Salient Region Detection and Segmentation

Research paper thumbnail of Benchmarking Image Segmentation Algorithms

International Journal of Computer Vision, 2009

We present a thorough quantitative evaluation of four image segmentation algorithms on images fro... more We present a thorough quantitative evaluation of four image segmentation algorithms on images from the Berkeley Segmentation Database. The algorithms are evaluated using an efficient algorithm for computing precision and recall with regard to human ground-truth boundaries. We test each segmentation method over a representative set of input parameters, and present tuning curves that fully characterize algorithm performance over the complete image database. We complement the evaluation on the BSD with segmentation results on synthetic images. The results reported here provide a useful benchmark for current and future research efforts in image segmentation.

Research paper thumbnail of Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery

We address the problem of efficiently estimating the rotation of a camera relative to the canonic... more We address the problem of efficiently estimating the rotation of a camera relative to the canonical 3D Cartesian frame of an urban scene, under the so-called “Manhattan World” assumption [1,2]. While the problem has received considerable attention in recent years, it is unclear how current methods stack up in terms of accuracy and efficiency, and how they might best be improved. It is often argued that it is best to base estimation on all pixels in the image [2]. However, in this paper, we argue that in a sense, less can be more: that basing estimation on sparse, accurately localized edges, rather than dense gradient maps, permits the derivation of more accurate statistical models and leads to more efficient estimation. We also introduce and compare several different search techniques that have advantages over prior approaches. A cornerstone of the paper is the establishment of a new public groundtruth database which we use to derive required statistics and to evaluate and compare algorithms.

Research paper thumbnail of Controlling the Search for Convex Groups

Research paper thumbnail of Quantitative Evaluation of a Novel Image Segmentation Algorithm

Research paper thumbnail of Multi-Scale Contour Extraction Based on Natural Image Statistics

Research paper thumbnail of Perceptual Grouping for Contour Extraction

Research paper thumbnail of Spectral Embedding and Min-Cut for Image Segmentation

Research paper thumbnail of RAICES HISTORICAS

Research paper thumbnail of Robust Boundary DetectionWith Adaptive Grouping

Research paper thumbnail of Stochastic Image Denoising

Research paper thumbnail of Salient Region Detection and Segmentation

Research paper thumbnail of Benchmarking Image Segmentation Algorithms

International Journal of Computer Vision, 2009

We present a thorough quantitative evaluation of four image segmentation algorithms on images fro... more We present a thorough quantitative evaluation of four image segmentation algorithms on images from the Berkeley Segmentation Database. The algorithms are evaluated using an efficient algorithm for computing precision and recall with regard to human ground-truth boundaries. We test each segmentation method over a representative set of input parameters, and present tuning curves that fully characterize algorithm performance over the complete image database. We complement the evaluation on the BSD with segmentation results on synthetic images. The results reported here provide a useful benchmark for current and future research efforts in image segmentation.

Research paper thumbnail of Efficient Edge-Based Methods for Estimating Manhattan Frames in Urban Imagery

We address the problem of efficiently estimating the rotation of a camera relative to the canonic... more We address the problem of efficiently estimating the rotation of a camera relative to the canonical 3D Cartesian frame of an urban scene, under the so-called “Manhattan World” assumption [1,2]. While the problem has received considerable attention in recent years, it is unclear how current methods stack up in terms of accuracy and efficiency, and how they might best be improved. It is often argued that it is best to base estimation on all pixels in the image [2]. However, in this paper, we argue that in a sense, less can be more: that basing estimation on sparse, accurately localized edges, rather than dense gradient maps, permits the derivation of more accurate statistical models and leads to more efficient estimation. We also introduce and compare several different search techniques that have advantages over prior approaches. A cornerstone of the paper is the establishment of a new public groundtruth database which we use to derive required statistics and to evaluate and compare algorithms.

Research paper thumbnail of Controlling the Search for Convex Groups

Research paper thumbnail of Quantitative Evaluation of a Novel Image Segmentation Algorithm

Research paper thumbnail of Multi-Scale Contour Extraction Based on Natural Image Statistics

Research paper thumbnail of Perceptual Grouping for Contour Extraction

Research paper thumbnail of Spectral Embedding and Min-Cut for Image Segmentation

Research paper thumbnail of RAICES HISTORICAS

Log In