A unified learning framework for object detection and classification using nested cascades of boosted classifiers

Verschae, Rodrigo; Ruiz‐del‐Solar, Javier; Correa, Mauricio

doi:10.1007/s00138-007-0084-0

Cited by 42 publications

(38 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Until now, a large number of face recognition methods, such as appearance-based methods [1][2][3][4], Gabor wavelet methods [5][6][7]35,38], and machine learning-based methods [8,9], have been developed for still images. Zhao et al [10] provided a comprehensive survey of the studies of machine recognition of faces, categorized existing recognition techniques, and presented a detailed description of a number of representative methods.…”

Section: Introductionmentioning

confidence: 99%

Face recognition using decimated redundant discrete wavelet transforms

Tang

Pedrycz

2011

Machine Vision and Applications

View full text Add to dashboard Cite

As discrete wavelet transform (DWT) is sensitive to the translation/shift of input signals, its effectiveness could be lessened for face recognition, particularly when the face images are translated. To alleviate drawbacks resulted from this translation effect, we propose a decimated redundant DWT (DRDWT)-based face recognition method, where the decimation-based DWTs are performed on the original signal and its 1-stepshift, respectively. Even though the DRDWT realizes the decimation, it enables us to explore the translation invariant DWT representation for the periodic shifts of the probe image that is the most similar to the gallery images. Therefore, it can solve the problem of translation sensitivity of the original DWT and address the translation effect occurring between the probe image and the gallery image. To further improve the recognition performance, we combine the global wavelet features obtained from the entire face and the local wavelet features obtained from face patches to represent both holistic and detail facial features, apply separate classifiers to global and local features and combine the resulted global and local classifiers to form an ensemble classifier. Experimental results reported for the FERET and FRGCv2.0

show abstract

Section: Introductionmentioning

confidence: 99%

Face recognition using decimated redundant discrete wavelet transforms

Tang

Pedrycz

2011

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…To speed up the training, we used feature sampling and we consider rectangular features in the first two layers, and mLBP in the subsequent layers, as done in [7]. Note that using these feature types imposes an important difference between the problems of 1, 2 and 4 classes with the one of 8 classes (see Table 2), because the problems with 8 classes considers also diagonal rotations (45, 135, 225 and 315 degrees), which are more difficult to detect using the employed features.…”

Section: Resultsmentioning

confidence: 99%

“…Examples of other features that have been used in similar systems are edgelets [10], modified Local Binary Patterns (mLBP) [7], and granular features [2]. For the weak classifiers h t , families of functions H that have been used include decision stumps (binary [8] and real outputs [6]) , domain partitioning classifiers [9] [7], and CART classifiers.…”

Section: T T=0ĥ T (X) By Iteratively Minimizing An Upper Bound Of Thementioning

confidence: 99%

“…The training procedure of a nested cascade is not trivial and different procedures have been proposed [1] [7].…”

Section: T T=0ĥ T (X) By Iteratively Minimizing An Upper Bound Of Thementioning

confidence: 99%

“…This kind of classifier has two important advantages: a) if the partition is defined as equally sized intervals, the classifier can be evaluated in O(1) thanks to the use of look-up-tables, and b) it can be used even when the features do not lie on a Euclidean space [7] (like in the case of mLBP features).…”

Section: Proposed Multiclass Nested Cascadementioning

confidence: 99%

See 2 more Smart Citations

Multiclass Adaboost and Coupled Classifiers for Object Detection

Verschae

Ruiz‐del‐Solar

2008

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Building robust and fast multiclass object detection systems is a important goal of computer vision. In the present paper we extend the well-known work of Viola and Jones on boosted cascade classifiers to the multiclass case with the goal of building multiclass and multiview object detectors. We propose to use nested cascades of multiclass boosted classifiers and we introduce the concept of coupled components in multiclass classifiers. We evaluate the system by building several multiview face detectors, each one built to detect a different number of classes. Thus, we present results showing how well the system scales. Promising results are obtained in the BioID database, showing the potentiality of the proposed methods for building object detectors.

show abstract

Gender Classification of Faces Using Adaboost

Verschae

Ruiz‐del‐Solar

Correa

2006

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In this work it is described a framework for classifying face images using Adaboost and domain-partitioning based classifiers. The most interesting aspect of this framework is the capability of building classification systems with high accuracy in dynamical environments, which achieve, at the same time, high processing and training speed. We apply this framework to the specific problem of gender classification. We built several gender classification systems under the proposed framework using different features (LBP, wavelets, rectangular, etc.). These systems are analyzed and evaluated using standard face databases (FERET and BioID), and a new gender classification database of real-world images.

show abstract

A unified learning framework for object detection and classification using nested cascades of boosted classifiers

Cited by 42 publications

References 28 publications

Face recognition using decimated redundant discrete wavelet transforms

Face recognition using decimated redundant discrete wavelet transforms

Multiclass Adaboost and Coupled Classifiers for Object Detection

Gender Classification of Faces Using Adaboost

Contact Info

Product

Resources

About