Joint Haar-like features for face detection

Mita, Takeshi; Kaneko, T.; Hori, Osamu

doi:10.1109/iccv.2005.129

Cited by 254 publications

(129 citation statements)

References 10 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…In this section, following [58] and [55], we briefly present a generalized version of AdaBoost algorithm, usually referred to as RealBoost. It has been advocated in various works [59,60,61,62] that RealBoost yields better performance than the original AdaBoost algorithm.…”

Section: Adaboost Learningmentioning

confidence: 99%

“…In the original face detection paper by Viola and Jones [17], the standard AdaBoost algorithm [56] was adopted. In a number of follow-up works [59,60,61,62], researchers advocated the use of RealBoost, which was explained in detail in Section 2.1.2. In [107] and [66] comparisons between three boosting algorithms: AdaBoost, RealBoost and GentleBoost were performed.…”

Section: Variations Of the Boosting Learning Algorithmmentioning

confidence: 99%

“…In [62] joint Haar-like features were proposed, which are based on the co-occurrence of multiple Haar-like features. It was claimed that feature co-occurrence can better capture the characteristics of human faces, making it possible to construct a more powerful classifier.…”

Section: Feature Extractionmentioning

confidence: 99%

“…7, the joint Haar-like feature uses a similar feature computation and thresholding scheme, however, only the binary outputs of the Haar-like features are concatenated into an index for 2 F possible combinations, where F is the number of combined features. To find distinctive feature co-occurrences with limited computational complexity, the suboptimal sequential forward selection scheme was used in [62]. The number F was also heuristically limited to avoid statistical unreliability.…”

Section: Feature Extractionmentioning

confidence: 99%

“…A number of follow-up works showed that there is indeed information in the results from the previous nodes, and it is best to reuse them [80,19] etc. Spectral histogram [86] Spatial histogram (LBP-based) [87] HoG and LBP [88] Region covariance [89] SURF [102,103] Composite Joint Haar-like features [62] features Sparse feature set [90] LGB, BHOG [22] Integral Channel Features on HoG and LUV (Headhunter) [26] HoG, HSV, RGB, LUV, Grayscale, Gradient Magnitude [105] Shape features Boundary/contour fragments [94,95] Edgelet [96] Shapelet [97] instead of starting from scratch at each new node. For instance, in [110], the use of a "chain" structure was proposed to integrate historical knowledge into successive boosting learning.…”

Section: Variations Of the Boosting Learning Algorithmmentioning

confidence: 99%

See 4 more Smart Citations

A survey on face detection in the wild: Past, present and future

Zafeiriou

Cha

Zhang

2015

Computer Vision and Image Understanding

379

167

View full text Add to dashboard Cite

Section: Adaboost Learningmentioning

confidence: 99%

Section: Variations Of the Boosting Learning Algorithmmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Variations Of the Boosting Learning Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

A survey on face detection in the wild: Past, present and future

Zafeiriou

Cha

Zhang

2015

Computer Vision and Image Understanding

379

167

View full text Add to dashboard Cite

Robust Face Detection Using One‐Class Estimation and Real AdaBoost

Miwa

Hirai

Kim

2014

Elect Comm in Japan

View full text Add to dashboard Cite

SUMMARY We propose a robust face detection algorithm using one‐class estimation and Real AdaBoost. Inspired by the first practical face detection algorithm by Viola and Jones, many varieties of face detection algorithms have been proposed. The common feature of their algorithm is a cascaded structure of combined Haar‐like features trained by a boosting algorithm. Of course this framework has achieved a successful result of high detection rate and low false positive rate in a short time and has been applied to many imaging products. But because the nonface class includes multiple subclasses and their variations are too many to be collected and covered in training data, unexpected false positives inevitably happen in the real world data. That is a problem of self‐printing systems for digital cameras, because they need to handle all kinds of pictures in the real world. Furthermore, because they use detected face regions for image enhancement before printing, to suppress false positives is a big issue of self‐printing systems. To solve the problem of false positives in the real world, we model a nonface class using one‐class estimation of faces, and developed a new face detection algorithm combining one‐class estimation and a cascaded face detection by Real AdaBoost. As a result of the experiment using pictures of digital cameras, we achieved face detection about twice as fast with eight times lower false positives than a conventional cascaded face detector, and also more precise face size detection.

show abstract

State of the art and perspectives on traditional and emerging biometrics: A survey

Traoré

Alshahrani

Obaidat

2018

Security and Privacy

View full text Add to dashboard Cite

The last three decades have seen a shift and impressive progress in the biometric technologies landscape. Several major real‐world applications of biometrics have been released and are currently being used around the world. At the same time, several new biometrics modalities have emerged and have started making an impact in securing sensitive data, information, and systems. We present in this paper a survey of traditional and emerging biometrics by emphasizing their connection to human body parts, behavior, and cognition. A review of the state of the art in the key technologies is carried out along with a discussion of major applications currently available in the real world.

show abstract

Joint Haar-like features for face detection

Cited by 254 publications

References 10 publications

A survey on face detection in the wild: Past, present and future

A survey on face detection in the wild: Past, present and future

Robust Face Detection Using One‐Class Estimation and Real AdaBoost

State of the art and perspectives on traditional and emerging biometrics: A survey

Contact Info

Product

Resources

About