Object Recognition by Integrating Multiple Image Segmentations
Lecture notes in computer sciencePublished 1 January 2008Open access
Caroline Pantofaru, Cordelia Schmid, Martial Hebert
Citations129
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
By integrating the image partition hypotheses in an intuitive combined top-down and bottom-up recognition approach, this work improves object and feature support and explores possible extensions of the method and whether they provide improved performance.
Abstract
International audience
Keywords
Computer Science
International Journal of Computer VisionDistinctive Image Features from Scale-Invariant Keypoints
55,266 Citations2004David Lowe
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
ACM Transactions on Intelligent Systems and TechnologyLIBSVM
41,340 Citations2011Chih-Chung Chang, Chih‐Jen Lin
Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
IEEE Transactions on Pattern Analysis and Machine IntelligenceNormalized cuts and image segmentation
15,696 Citations2000Jianbo Shi, Jitendra Malik
IEEE Transactions on Pattern Analysis and Machine IntelligenceMean shift: a robust approach toward feature space analysis
11,282 Citations2002Dorin Comaniciu, Peter Meer
It is proved the convergence of a recursive mean shift procedure to the nearest stationary point of the underlying density function and, thus, its utility in detecting the modes of the density.
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
8,007 Citations2002David Martín, Charless C. Fowlkes +2 more
A database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes is presented and an error measure is defined which quantifies the consistency between segmentations of differing granularities.
IEEE Transactions on Pattern Analysis and Machine IntelligenceFast approximate energy minimization via graph cuts
6,987 Citations2001Yuri Boykov, Olga Veksler +1 more
The Annals of StatisticsAdditive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
6,842 Citations2000Jerome H. Friedman, Trevor Hastie +1 more
This work shows that this seemingly mysterious phenomenon of boosting can be understood in terms of well-known statistical principles, namely additive modeling and maximum likelihood, and develops more direct approximations and shows that they exhibit nearly identical results to boosting.
International Journal of Computer VisionEfficient Graph-Based Image Segmentation
6,198 Citations2004Pedro F. Felzenszwalb, Daniel P. Huttenlocher
An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.
International Journal of Computer VisionLabelMe: A Database and Web-Based Tool for Image Annotation
4,205 Citations2007Bryan Russell, Antonio Torralba +2 more
A web-based tool that allows easy image annotation and instant sharing of such annotations is developed and a large dataset that spans many object categories, often containing multiple instances over a wide variety of images is collected.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLearning to detect natural image boundaries using local brightness, color, and texture cues
2,424 Citations2004David R. Martin, Charless C. Fowlkes +1 more
The two main results are that cue combination can be performed adequately with a simple linear model and that a proper, explicit treatment of texture is required to detect boundaries in natural images.
Learning a classification model for segmentation
1,762 Citations2003Ren, Malik
A two-class classification model for grouping is proposed that defines a variety of features derived from the classical Gestalt cues, including contour, texture, brightness and good continuation, and trains a linear classifier to combine these features.
Journal of Machine Learning ResearchProbability Estimates for Multi-class Classification by Pairwise Coupling
1,479 Citations2004Tingfan Wu, Chih‐Jen Lin +1 more
Lecture notes in computer scienceTextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
1,153 Citations2006Jamie Shotton, John Winn +2 more
A new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently, is proposed, which is used for automatic visual recognition and semantic segmentation of photographs.
IEEE Transactions on Pattern Analysis and Machine IntelligenceToward Objective Evaluation of Image Segmentation Algorithms
800 Citations2007Ranjith Unnikrishnan, Caroline Pantofaru +1 more
It is demonstrated how a recently proposed measure of similarity, the normalized probabilistic rand (NPR) index, can be used to perform a quantitative comparison between image segmentation algorithms using a hand-labeled set of ground-truth segmentations.
Machine LearningLogistic Regression, AdaBoost and Bregman Distances
689 Citations2002Michael Collins, Robert E. Schapire +1 more
A unified account of boosting and logistic regression in which each learning problem is cast in terms of optimization of Bregman distances, and a parameterized family of algorithms that includes both a sequential- and a parallel-update algorithm as special cases are described, thus showing how the sequential and parallel approaches can themselves be unified.
International Journal of Computer VisionRecovering Surface Layout from an Image
685 Citations2007Derek Hoiem, Alexei A. Efros +1 more
This paper takes the first step towards constructing the surface layout, a labeling of the image intogeometric classes, to learn appearance-based models of these geometric classes, which coarsely describe the 3D scene orientation of each image region.
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
634 Citations2006Bryan Russell, William T. Freeman +3 more
This work compute multiple segmentations of each image and then learns the object classes and chooses the correct segmentations, demonstrating that such an algorithm succeeds in automatically discovering many familiar objects in a variety of image datasets, including those from Caltech, MSRC and LabelMe.
IEEE Transactions on Pattern Analysis and Machine IntelligenceImage segmentation by data-driven markov chain monte carlo
567 Citations2002Zhuowen Tu, Song-Chun Zhu
The DDMCMC paradigm provides a unifying framework in which the role of many existing segmentation algorithms are revealed as either realizing Markov chain dynamics or computing importance proposal probabilities and generalizes these segmentation methods in a principled way.
International Journal of Computer VisionImage Parsing: Unifying Segmentation, Detection, and Recognition
515 Citations2005Zhuowen Tu, Xiang-Rong Chen +2 more
A Bayesian framework for parsing images into their constituent visual patterns that optimizes the posterior probability and outputs a scene representation as a “parsing graph”, in a spirit similar to parsing sentences in speech and natural language is presented.
Peekaboom
515 Citations2006Luis von Ahn, Ruoran Liu +1 more
Peekaboom is an entertaining web-based game that can help computers locate objects in images and is an example of a new, emerging class of games, which not only bring people together for leisure purposes, but also exist to improve artificial intelligence.
LOCUS: learning object classes with unsupervised segmentation
507 Citations2005John Winn, Nebojša Jojić
LOCUS (learning object classes with unsupervised segmentation) is introduced which uses a generative probabilistic model to combine bottom-up cues of color and edge with top-down cues of shape and pose, allowing for significant within-class variation.
Lecture notes in computer scienceColoring Local Feature Extraction
432 Citations2006Joost van de Weijer, Cordelia Schmid
The results show that color descriptors remain reliable under photometric and geometrical changes, and with decreasing image quality, and for all experiments a combination of color and shape outperforms a pure shape-based approach.
OBJ CUT
326 Citations2005Manish Kumar, Philip H. S. Torr +1 more
A principled Bayesian method for detecting and segmenting instances of a particular object category within an image, providing a coherent methodology for combining top down and bottom up cues and developing an efficient method, OBJ CUT, to obtain segmentations using this model.
Improving Spatial Support for Objects via Multiple Segmentations
282 Citations2007Tomasz Malisiewicz, Anatoly Efros
The multiple segmentation approach is used to evaluate how close can real segments approach the ground-truth for real objects, and at what cost.
Lecture notes in computer scienceWeak Hypotheses and Boosting for Generic Object Detection and Recognition
265 Citations2004Andreas Opelt, Michael Fussenegger +2 more
The first stage of a new learning system for object detection and recognition using Boosting as the underlying learning technique and the inclusion of features from segmented re- gions and even spatial relationships leads us a significant step towards generic object recognition.
The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects
251 Citations2006John Winn, Jamie Shotton
This paper addresses the problem of detecting and segmenting partially occluded objects of a known category by defining a part labelling which densely covers the object and imposing asymmetric local spatial constraints on these labels to ensure the consistent layout of parts whilst allowing for object deformation.
Region Classification with Markov Field Aspect Models
189 Citations2007Jakob Verbeek, Bill Triggs
Combining spatial and aspect models significantly improves the region-level classification accuracy, and models trained with image-level labels outperform PLSA trained with pixel-level ones.
Learning affinity functions for image segmentation: combining patch-based and gradient-based approaches
132 Citations2003Charless C. Fowlkes, David Martín +1 more
A large database of manually segmented images is employed in order to learn an optimal affinity function between pairs of pixels, and it is found that for brightness, the gradient cue outperforms the patch similarity; in contrast, using color patch similarity yields better results than using color gradients.
Shape Guided Object Segmentation
100 Citations2006Eran Borenstein, Jitendra Malik
A Bayesian model is constructed that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant and robust to changes in appearance since the matching component depends on shape criteria alone.
Spectral Methods for Automatic Multiscale Data Clustering
68 Citations2006Arik Azran, Zoubin Ghahramani
This paper provides new insights into how the method works and uses these to derive new algorithms which given the data alone automatically learn different plausible data partitionings.
Combining Regions and Patches for Object Class Localization
28 Citations2006Caroline Pantofaru, Gyuri Dorkó +2 more
A method for object class detection and localization which combines regions generated by image segmentation with local patches, and applies Region-based Context Features in a semi-supervised learning framework for object Detection and localization.