Detecting object boundaries using low-, mid-, and high-level information

Zheng, Songfeng; Yuille, Alan; Tu, Zhuowen

doi:10.1016/j.cviu.2010.07.004

Cited by 51 publications

(36 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead this alternative view suggests that the bottom-up activation of a loose collection of hardwired feature detectors via a hierarchy of increasing complex processing stages may provide a coarse initial visual representation for more complex routines and several feedforward/feedback iterations to solve specific tasks including edge detection, grouping, figure segregation, and the computation of spatial relations between parts, among others, and more generally the parsing and interpretation of complex visual scenes (see for instance, Hochstein and Ahissar, 2002; Bar, 2004; Zheng et al, 2007; Epshtein et al, 2008; Serre and Poggio, 2010 for a recent review).…”

Section: Discussionmentioning

confidence: 99%

What are the visual features underlying rapid object recognition?

Crouzet¹

2011

Front. Psychology

View full text Add to dashboard Cite

Research progress in machine vision has been very significant in recent years. Robust face detection and identification algorithms are already readily available to consumers, and modern computer vision algorithms for generic object recognition are now coping with the richness and complexity of natural visual scenes. Unlike early vision models of object recognition that emphasized the role of figure-ground segmentation and spatial information between parts, recent successful approaches are based on the computation of loose collections of image features without prior segmentation or any explicit encoding of spatial relations. While these models remain simplistic models of visual processing, they suggest that, in principle, bottom-up activation of a loose collection of image features could support the rapid recognition of natural object categories and provide an initial coarse visual representation before more complex visual routines and attentional mechanisms take place. Focusing on biologically plausible computational models of (bottom-up) pre-attentive visual recognition, we review some of the key visual features that have been described in the literature. We discuss the consistency of these feature-based representations with classical theories from visual psychology and test their ability to account for human performance on a rapid object categorization task.

show abstract

Section: Discussionmentioning

confidence: 99%

What are the visual features underlying rapid object recognition?

Crouzet¹

2011

Front. Psychology

View full text Add to dashboard Cite

show abstract

“…Biological insight is also considered to obtain invariance under various viewing conditions [10]. Other studies propose combining different levels (low -mid -high) of information [11]. The second step of the object recognition pipeline has also been widely addressed.…”

Section: A Image Classificationmentioning

confidence: 99%

“…In that study, scene-level matching with global image descriptors is followed by SP level matching of mid-level features. The study in [11] addresses the low-, mid-, and high-level cues. Individual classifiers are trained on different levels of descriptors and classification outputs are combined for the final decision.…”

Section: B Mid-level Cuesmentioning

confidence: 99%

SuperPixel Based Angular Differences as a Mid-level Image Descriptor

Sicre

Taşlı

Gevers

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

This paper focuses on the object recognition task and aims at improving the accuracy with an emphasis on the feature extraction step. Feature extraction is widely used in image classification as an initial step in the pipeline. In this paper, we propose a method to explore the conventional feature extraction techniques from the perspective that mid-level information could be incorporated in order to obtain a superior scene description. We hypothesize that the commonly used pixel based low-level descriptions are useful but can be improved with the introduction of mid-level region information. Hence, we investigate superpixel based image representation to acquire such mid-level information in order to improve the classification accuracy. Detailed experimental evaluations on classification and retrieval tasks are performed in order to validate the proposed hypothesis. A consistent increase is observed in the mean average precision (MAP) score for different experimental scenarios and image categories.

show abstract

“…Hence, the area under the precision-recall curve (AUC-PR) and performance measures approximating the AUC-PR including R-precision, average precision, and 11-point interpolated average precision also gained increasing attention [9], [10]. These performance measures have been widely used in diverse fields such as computer vision [11], computational biology [12], [13], information retrieval [14], medicine [15], and natural language processing [16], [17].…”

Section: Introductionmentioning

confidence: 99%

Area under Precision-Recall Curves for Weighted and Unweighted Data

2014

View full text Add to dashboard Cite

Precision-recall curves are highly informative about the performance of binary classifiers, and the area under these curves is a popular scalar performance measure for comparing different classifiers. However, for many applications class labels are not provided with absolute certainty, but with some degree of confidence, often reflected by weights or soft labels assigned to data points. Computing the area under the precision-recall curve requires interpolating between adjacent supporting points, but previous interpolation schemes are not directly applicable to weighted data. Hence, even in cases where weights were available, they had to be neglected for assessing classifiers using precision-recall curves. Here, we propose an interpolation for precision-recall curves that can also be used for weighted data, and we derive conditions for classification scores yielding the maximum and minimum area under the precision-recall curve. We investigate accordances and differences of the proposed interpolation and previous ones, and we demonstrate that taking into account existing weights of test data is important for the comparison of classifiers.

show abstract

Detecting object boundaries using low-, mid-, and high-level information

Abstract: Object boundary detection and segmentation is a central problem in computer vision. The importance of combining low-level, mid-level, and high-level

Cited by 51 publications

References 28 publications

What are the visual features underlying rapid object recognition?

What are the visual features underlying rapid object recognition?

SuperPixel Based Angular Differences as a Mid-level Image Descriptor

Area under Precision-Recall Curves for Weighted and Unweighted Data

Contact Info

Product

Resources

About