scispace - formally typeset
Topic

Feature extraction

About: Feature extraction is a(n) research topic. Over the lifetime, 111837 publication(s) have been published within this topic receiving 2155699 citation(s). The topic is also known as: feature analysis.

...read more

Papers
  More

Open accessProceedings ArticleDOI: 10.1109/CVPR.2005.177
Navneet Dalal1, Bill Triggs1Institutions (1)
20 Jun 2005-
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.

...read more

Topics: Histogram of oriented gradients (62%), Local binary patterns (57%), GLOH (56%) ...read more

28,803 Citations


Journal ArticleDOI: 10.1145/358669.358692
Martin A. Fischler1, Robert C. Bolles1Institutions (1)
Abstract: A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing

...read more

Topics: RANSAC (69%), Smoothing (55%), Image processing (54%) ...read more

20,503 Citations


Open accessProceedings ArticleDOI: 10.1109/CVPR.2001.990517
Paul A. Viola1, Michael JonesInstitutions (1)
01 Dec 2001-
Abstract: This paper describes a machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work is distinguished by three key contributions. The first is the introduction of a new image representation called the "integral image" which allows the features used by our detector to be computed very quickly. The second is a learning algorithm, based on AdaBoost, which selects a small number of critical visual features from a larger set and yields extremely efficient classifiers. The third contribution is a method for combining increasingly more complex classifiers in a "cascade" which allows background regions of the image to be quickly discarded while spending more computation on promising object-like regions. The cascade can be viewed as an object specific focus-of-attention mechanism which unlike previous approaches provides statistical guarantees that discarded regions are unlikely to contain the object of interest. In the domain of face detection the system yields detection rates comparable to the best previous systems. Used in real-time applications, the detector runs at 15 frames per second without resorting to image differencing or skin color detection.

...read more

17,417 Citations


Proceedings ArticleDOI: 10.1109/ICCV.1999.790410
David G. Lowe1Institutions (1)
20 Sep 1999-
Abstract: An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

...read more

Topics: 3D single-object recognition (67%), Haar-like features (63%), Scale space (59%) ...read more

15,597 Citations


Open accessProceedings ArticleDOI: 10.1109/CVPR.2014.81
23 Jun 2014-
Abstract: Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

...read more

Topics: Object detection (56%), Feature (computer vision) (54%), Convolutional neural network (53%) ...read more

15,107 Citations


Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2022187
20218,592
20209,785
201910,026
20189,098
20177,886

Top Attributes

Show by:

Topic's top 5 most impactful authors

David Zhang

162 papers, 16.3K citations

Licheng Jiao

121 papers, 2.3K citations

Xuelong Li

111 papers, 7.9K citations

Jon Atli Benediktsson

93 papers, 6K citations

Liangpei Zhang

88 papers, 6.5K citations

Network Information
Related Topics (5)
Feature vector

48.8K papers, 954.4K citations

97% related
Image segmentation

79.6K papers, 1.8M citations

97% related
Object detection

46.1K papers, 1.3M citations

96% related
Convolutional neural network

74.7K papers, 2M citations

96% related
Image texture

29.1K papers, 736.4K citations

95% related