Francisco Estrada - Academia.edu (original) (raw)
Uploads
Papers by Francisco Estrada
This paper presents a perceptual grouping algorithm that performs boundary extraction on natural ... more This paper presents a perceptual grouping algorithm that performs boundary extraction on natural images. Our grouping method maintains and updates a model of the appearance of the image regions on either side of a growing contour. This model is used to change grouping behaviour at run-time, so that, in addition to following the traditional Gestalt grouping principles of proximity and good continuation, the grouping procedure favours the path that best separates two visually distinct parts of the image. The resulting algorithm is computationally efficient and robust to clutter and texture. We present experimental results on natural images from the Berkeley Segmentation Database and compare our results to those obtained with three alternate grouping methods.
Detection of salient image regions is useful for applications like image segmentation, adaptive c... more Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image. We demonstrate the use of the algorithm in the segmentation of semantically meaningful whole objects from digital images.
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.
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.
This paper describes an efficient algorithm for the perceptual grouping of line segments. The met... more This paper describes an efficient algorithm for the perceptual grouping of line segments. The method uses a geometry-based measure of affinity between pairs of lines to guide group formation, and implements a search control procedure that is intended to reduce search complexity when image characteristics lead to a combinatorially large number of possible groups. We also present a ranking system that identifies the polygons that offer the most plausible explanation for the observed image data. The method is applied in the context of finding convex groups, and is experimentally shown to outperform existing algorithms, particularly in images with significant clutter, strong texture, and long, curved contours.
We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectr... more We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley Segmentation Database as ground truth and propose suitable measures to evaluate segmentation quality. With these measures we generate precision/recall curves for SE-MinCut and three of the leading segmentation algorithms: Mean-Shift, Normalized Cuts, and the Local Variation algorithm. These curves characterize the performance of each algorithm over a range of input parameters. We compare the precision/recall curves for the four algorithms and show segmented images that support the conclusions obtained from the quantitative evaluation.
Perceptual grouping of the complete boundaries of objects in natural images remains an unsolved p... more Perceptual grouping of the complete boundaries of objects in natural images remains an unsolved problem in computer vision. The computational complexity of the problem and difficulties capturing global constraints limit the performance of current algorithms. In this paper we develop a coarse-to-fine Bayesian algorithm which addresses these constraints. Candidate contours are extracted at a coarse scale and then used to generate spatial priors on the location of possible contours at finer scales. In this way, a rough estimate of the shape of an object is progressively refined. The coarse estimate provides robustness to texture and clutter while the refinement process allows for the extraction of detailed object contours. The grouping algorithm is probabilistic and uses multiple grouping cues derived from natural scene statistics. We present a quantitative evaluation of grouping performance on the Berkeley Segmentation Database, and show that the multi-scale approach outperforms several single-scale contour extraction algorithms.
This paper describes an algorithm that efficiently groups line segments into perceptually salient... more This paper describes an algorithm that efficiently groups line segments into perceptually salient contours in complex images. A measure of affinity between pairs of lines is used to guide group formation and limit the branching factor of the contour search procedure. The extracted contours are ranked, and presented as a contour hierarchy. Our algorithm is able to extract salient contours in the presence of texture, clutter, and repetitive or ambiguous image structure. We show experimental results on a complex line-set.
Recently it has been shown that min-cut algorithms can provide perceptually salient image segment... more Recently it has been shown that min-cut algorithms can provide perceptually salient image segments when they are given appropriate proposals for source and sink regions. Here we explore the use of random walks and associated spectral embedding techniques for the automatic generation of suitable proposal regions. To do this, we first derive a mathematical connection between spectral embedding and anisotropic image smoothing kernels. We then use properties of the spectral embedding and the associated smoothing kernels to select multiple pairs of source and sink regions for min-cut. This typically provides an over-segmentation, and therefore region merging is used to form the final image segmentation. We demonstrate this process on several sample images.
Es necesario enseñarlos primero a ser hombres y después cristianos" José de Acosta Los franciscan... more Es necesario enseñarlos primero a ser hombres y después cristianos" José de Acosta Los franciscanos fueron los primeros frailes en arribar a la Nueva España entre los años de 1523 y 1536. Su preocupación principal fue la de evangelizar a los nativos de estos nuevos territorios, fueron los primeros que se interesaron por introducir un nuevo conocimiento. Así elaboraron y empezaron a poner en práctica un proyecto educativo, cuyo objetivo central estuvo dirigido a contribuir en la reorganización social de los pueblos indios, asegurando su autosuficiencia económica, además de su autonomía social y política. Su ideal de conquista era ganar almas entre los indios, de acuerdo a la ideología del retorno a un cristianismo primigenio por el que habían luchado en Europa desde el siglo XIII y ahora se presentaba la ocasión para llevarlo a cabo en el Nuevo Mundo.
This paper presents a perceptual grouping algorithm that performs boundary extraction on natural ... more This paper presents a perceptual grouping algorithm that performs boundary extraction on natural images. Our grouping method maintains and updates a model of the appearance of the image regions on either side of a growing contour. This model is used to change grouping behaviour at run-time, so that, in addition to following the traditional Gestalt grouping principles of proximity and good continuation, the grouping procedure favours the path that best separates two visually distinct parts of the image. The resulting algorithm is computationally efficient and robust to clutter and texture. We present experimental results on natural images from the Berkeley Segmentation Database and compare our results to those obtained with three alternate grouping methods.
Detection of salient image regions is useful for applications like image segmentation, adaptive c... more Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image. We demonstrate the use of the algorithm in the segmentation of semantically meaningful whole objects from digital images.
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.
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.
This paper describes an efficient algorithm for the perceptual grouping of line segments. The met... more This paper describes an efficient algorithm for the perceptual grouping of line segments. The method uses a geometry-based measure of affinity between pairs of lines to guide group formation, and implements a search control procedure that is intended to reduce search complexity when image characteristics lead to a combinatorially large number of possible groups. We also present a ranking system that identifies the polygons that offer the most plausible explanation for the observed image data. The method is applied in the context of finding convex groups, and is experimentally shown to outperform existing algorithms, particularly in images with significant clutter, strong texture, and long, curved contours.
We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectr... more We present a quantitative evaluation of SE-MinCut, a novel segmentation algorithm based on spectral embedding and minimum cut. We use human segmentations from the Berkeley Segmentation Database as ground truth and propose suitable measures to evaluate segmentation quality. With these measures we generate precision/recall curves for SE-MinCut and three of the leading segmentation algorithms: Mean-Shift, Normalized Cuts, and the Local Variation algorithm. These curves characterize the performance of each algorithm over a range of input parameters. We compare the precision/recall curves for the four algorithms and show segmented images that support the conclusions obtained from the quantitative evaluation.
Perceptual grouping of the complete boundaries of objects in natural images remains an unsolved p... more Perceptual grouping of the complete boundaries of objects in natural images remains an unsolved problem in computer vision. The computational complexity of the problem and difficulties capturing global constraints limit the performance of current algorithms. In this paper we develop a coarse-to-fine Bayesian algorithm which addresses these constraints. Candidate contours are extracted at a coarse scale and then used to generate spatial priors on the location of possible contours at finer scales. In this way, a rough estimate of the shape of an object is progressively refined. The coarse estimate provides robustness to texture and clutter while the refinement process allows for the extraction of detailed object contours. The grouping algorithm is probabilistic and uses multiple grouping cues derived from natural scene statistics. We present a quantitative evaluation of grouping performance on the Berkeley Segmentation Database, and show that the multi-scale approach outperforms several single-scale contour extraction algorithms.
This paper describes an algorithm that efficiently groups line segments into perceptually salient... more This paper describes an algorithm that efficiently groups line segments into perceptually salient contours in complex images. A measure of affinity between pairs of lines is used to guide group formation and limit the branching factor of the contour search procedure. The extracted contours are ranked, and presented as a contour hierarchy. Our algorithm is able to extract salient contours in the presence of texture, clutter, and repetitive or ambiguous image structure. We show experimental results on a complex line-set.
Recently it has been shown that min-cut algorithms can provide perceptually salient image segment... more Recently it has been shown that min-cut algorithms can provide perceptually salient image segments when they are given appropriate proposals for source and sink regions. Here we explore the use of random walks and associated spectral embedding techniques for the automatic generation of suitable proposal regions. To do this, we first derive a mathematical connection between spectral embedding and anisotropic image smoothing kernels. We then use properties of the spectral embedding and the associated smoothing kernels to select multiple pairs of source and sink regions for min-cut. This typically provides an over-segmentation, and therefore region merging is used to form the final image segmentation. We demonstrate this process on several sample images.
Es necesario enseñarlos primero a ser hombres y después cristianos" José de Acosta Los franciscan... more Es necesario enseñarlos primero a ser hombres y después cristianos" José de Acosta Los franciscanos fueron los primeros frailes en arribar a la Nueva España entre los años de 1523 y 1536. Su preocupación principal fue la de evangelizar a los nativos de estos nuevos territorios, fueron los primeros que se interesaron por introducir un nuevo conocimiento. Así elaboraron y empezaron a poner en práctica un proyecto educativo, cuyo objetivo central estuvo dirigido a contribuir en la reorganización social de los pueblos indios, asegurando su autosuficiencia económica, además de su autonomía social y política. Su ideal de conquista era ganar almas entre los indios, de acuerdo a la ideología del retorno a un cristianismo primigenio por el que habían luchado en Europa desde el siglo XIII y ahora se presentaba la ocasión para llevarlo a cabo en el Nuevo Mundo.