Rapid object detection using a boosted cascade of simple features

By Paul A. Viola, Michael J. Jones. 2001

957 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Object Detection Networks on Convolutional Feature Maps (2015, neutral): “The pioneering work of Viola and Jones [28] uses simple Haar-like features and boosted classiﬁers.”
Soft-NMS — Improving Object Detection with One Line of Code (2017, neutral): “In face detection [29], NMS is performed by partitioning boundingboxes into disjoint subsets using an overlap criterion.”
Recurrent Models of Visual Attention (2014, neutral): “[7, 24]), removing image regions from consideration via a branch and bound approach on the classifier output (e.”
Deep learning for detecting robotic grasps (2013, neutral): “These are computed after the image is aligned to the gripper so that they are always relative to the gripper plates.”
CNP: An FPGA-based processor for Convolutional Networks (2009, neutral): “Face detection systems based on ConvNets have been shown to outperform the popular boosted cascades of Haar wavelets method [15], both in speed and accuracy [6, 7].”
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts (2012, neutral): “This trend led to the current prevalence of bounding box detectors operating on sliding windows [9], [22].”
Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting (2015, positive): “In the experiments below, we use Haar-like features [38], randomly sampled in a patch around the current point, as they have been found to be effective for a range of applications and can be calculated efficiently from integral images.”
Constrained parametric min-cuts for automatic object segmentation (2010, neutral): “This trend led to the curre nt prevalence of bounding box detectors operating on sliding windows [8], [21].”
A Practical Approach to Recognizing Physical Activities (2006, positive): “The [1-12] data point Figure 2 also corresponds very closely to the results we saw in row two of Table 5 as they both represent very similar tests.”
Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam (2011, positive): “We utilized the Open Computer Vision library [14] to automatically identify the coordinates of the face location in the first frame of the video recording using a boosted cascade classifier [15].”
On the Binding Problem in Artificial Neural Networks (2020, neutral): “A classifier can then be trained to determine which window contains an object (Rowley et al., 1998; Viola and Jones, 2001; Harzallah et al., 2009).”
Analysing Domain Shift Factors between Videos and Images for Object Detection (2015, neutral): “Traditionally, training an object detector requires gathering a large, diverse set of still images, in which objects are manually annotated by a bounding-box [8], [15], [17], [28], [42], [44], [46].”
Collecting Large, Richly Annotated Facial-Expression Databases from Movies (2012, positive): “For extracting the face, we computed the Viola-Jones detector [17] over the CK+ sequences.”
Machine learning and deep learning (2021, neutral): “…histograms of oriented gradients (HOG) (Dalal and Triggs 2005), scale-invariant feature transform (SIFT) (Lowe 2004), and the Viola-Jones method (Viola and Jones 2001); and in NLP, it is common to use term frequency-inverse document frequency (TF-IDF) vectors (Salton and Buckley 1988),…”
Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking (2018, positive): “As the first contribution, we introduce a novel multistage tracking framework, the Siamese Cascaded RPN (CRPN), to solve the problem of class imbalance by performing hard negative sampling [40, 48].”
Scene Text Recognition using Higher Order Language Priors (2009, neutral): “Sliding window based detectors have been very successful for challenging tasks, such as face [19] and pedestrian [7] detection.”
Deep Learning for Generic Object Detection: A Survey (2018, positive): “e Scale Invariant Feature Transform (SIFT) feature [178], and the progress on various visual recognition tasks was based substantially on the use of local descriptors [187] such as Haar-like features [276], SIFT [179], Shape Contexts [12], Histogram of Gradients (HOG) [52] Local Binary Patterns (LBP”
Volumetric Semantic Segmentation Using Pyramid Context Features (2013, neutral): “From a computer vision perspective, the problem at hand is that of volumetric semantic segmentation, in which we must predict a tissue label for each voxel in a volume.”
Person Re-identification by Descriptive and Discriminative Classification (2011, positive): “In the second stage of our system we apply a discriminative model, which is estimated by Boosting for Feature Selection [19, 21].”