Hybrid generative/discriminative classifier for unconstrained character recognition

Prévost, Lionel; Oudot, Loïc; Moises, A.; Michel-Sendis, C.; Milgram, Maurice

doi:10.1016/j.patrec.2005.03.005

Cited by 19 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main goal of this article is to show the complementarity between generative and discriminative classifiers. This complementarity was already proved-theoretically and experimentally-in [41][42][43]. This study demonstrates experimentally that the boosting process selects automatically in first place generative classifiers and then discriminative ones.…”

Section: Discussionsupporting

confidence: 67%

A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection

Negri

Clady

Hanif

et al. 2008

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

We present an algorithm for the on-board vision vehicle detection problem using a cascade of boosted classifiers. Three families of features are compared: the rectangular filters (Haar-like features), the histograms of oriented gradient (HoG), and their combination (a concatenation of the two preceding features). A comparative study of the results of the generative (HoG features), discriminative (Haar-like features) detectors, and of their fusion is presented. These results show that the fusion combines the advantages of the other two detectors: generative classifiers eliminate "easily" negative examples in the early layers of the cascade, while in the later layers, the discriminative classifiers generate a fine decision boundary removing the negative examples near the vehicle model. The best algorithm achieves good performances on a test set containing some 500 vehicle images: the detection rate is about 94% and the false-alarm rate per image is 0.0003.

show abstract

Section: Discussionsupporting

confidence: 67%

A Cascade of Boosted Generative and Discriminative Classifiers for Vehicle Detection

Negri

Clady

Hanif

et al. 2008

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In literature, discriminative training of generative models, as we propose here, has been shown as efficient learning methods in numerous applications as object or human detection (Holub et al, 2005; Negri et al, 2008; Wang et al, 2011), face or character recognition (Prevost et al, 2005; Grabner et al, 2007) or for medical purposes (Deselaers et al, 2008; Wang et al, 2015). The proposed classifier based on the training and the selection of generative models in a discriminative way, combines indeed the main characteristics of discriminative and generative approaches: discriminative power and generalization ability, respectively.…”

Section: Application To Gesture Recognitionmentioning

confidence: 99%

A Motion-Based Feature for Event-Based Pattern Recognition

et al. 2017

View full text Add to dashboard Cite

This paper introduces an event-based luminance-free feature from the output of asynchronous event-based neuromorphic retinas. The feature consists in mapping the distribution of the optical flow along the contours of the moving objects in the visual scene into a matrix. Asynchronous event-based neuromorphic retinas are composed of autonomous pixels, each of them asynchronously generating “spiking” events that encode relative changes in pixels' illumination at high temporal resolutions. The optical flow is computed at each event, and is integrated locally or globally in a speed and direction coordinate frame based grid, using speed-tuned temporal kernels. The latter ensures that the resulting feature equitably represents the distribution of the normal motion along the current moving edges, whatever their respective dynamics. The usefulness and the generality of the proposed feature are demonstrated in pattern recognition applications: local corner detection and global gesture recognition.

show abstract

“…Facing up to the complex problems of the handwriting recognition, the use of the multiple, hybrid and an association of classifier systems proves an increasing interest during the last years (Aksela and Laaksonen, 2005;Chiang and Gader, 1997;Hafsa et al, 2004;Hebert et al, 1998;Ianakiev and Govindaraju, 2000;Kittler et al, 1998;Lam and Suen, 1999;Prevost et al, 2005;Suen and Tan, 2005;Xu et al, 1992). Based on their complementarities, the association of classifiers increases the performance of the recognition system while limiting the error bound to the use of a unique classifier.…”

Section: On-line Recognition Of Handwritten Digitsmentioning

confidence: 99%