Associative neural networks as means for low-resolution video-based recognition

Gorodnichy, Dmitry O.

doi:10.1109/ijcnn.2005.1556419

Cited by 14 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outputs of the network must also be post-processed over the multiple outputs per symbol in order to determine a single decision per symbol. This is similar to image detection using multiple frames of low-resolution video [16].…”

Section: Network Inputsmentioning

confidence: 95%

See 1 more Smart Citation

A Neural Network Receiver for EM-MWD Communication

Whitacre¹

View full text Add to dashboard Cite

Section: Network Inputsmentioning

confidence: 95%

“…Gorodnichy [16] introduced a neuro-associative approach to recognition, which can both learn and identify an object from low-resolution low-quality video sequences. The network was able to incrementally learn via the pseudo-inverse learning rule.…”

Section: Previous Workmentioning

confidence: 99%

A Neural Network Receiver for EM-MWD Communication

Whitacre¹

View full text Add to dashboard Cite

“…The other videos from IIT-NRC [7] contain relatively low quality image frames with abrupt changes in pose and size.…”

Section: Tracking On Standard Video Datasetsmentioning

confidence: 99%

Face tracking and recognition with visual constraints in real-world videos

Kim

Kumar

Pavlović

et al. 2008

2008 IEEE Conference on Computer Vision and Pattern Recognition

150

View full text Add to dashboard Cite

We address the problem of tracking and recognizing faces in real-world, noisy videos. We track faces using a tracker that adaptively builds a target model reflecting changes in appearance, typical of a video setting. However, adaptive appearance trackers often suffer from drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, our tracker introduces visual constraints using a combination of generative and discriminative models in a particle filtering framework. The generative term conforms the particles to the space of generic face poses while the discriminative one ensures rejection of poorly aligned targets. This leads to a tracker that significantly improves robustness against abrupt appearance changes and occlusions, critical for the subsequent recognition phase. Identity of the tracked subject is established by fusing pose-discriminant and person-discriminant features over the duration of a video sequence. This leads to a robust video-based face recognizer with state-of-the-art recognition performance. We test the quality of tracking and face recognition on realworld noisy videos from YouTube as well as the standard Honda/UCSD database. Our approach produces successful face tracking results on over 80% of all videos without video or person-specific parameter tuning. The good tracking performance induces similarly high recognition rates: 100% on Honda/UCSD and over 70% on the YouTube set containing 35 celebrities in 1500 sequences.

show abstract

“…8 (a) and 9, at 10fps and 320 × 240 pixel resolution (face size ≈ 60 pixels). -FaceVideoDB, freely available and described in [22]. Briefly, it contains 11 individuals and 2 sequences per person, little variation in illumination, but extreme and uncontrolled variations in pose and motion, acquired at 25fps and 160 × 120 pixel resolution (face size ≈ 45 pixels), see Fig.…”

Section: Empirical Evaluationmentioning

confidence: 99%

Face Recognition from Video Using the Generic Shape-Illumination Manifold

Arandjelović

Cipolla

2006

Computer Vision – ECCV 2006

View full text Add to dashboard Cite

Abstract. In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. In particular there are three areas of novelty: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation, learnt offline, to generalize in the presence of extreme illumination changes; (ii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve invariance to unseen head poses; and (iii) we introduce an accurate video sequence "reillumination" algorithm to achieve robustness to face motion patterns in video. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our system consistently demonstrated a nearly perfect recognition rate (over 99.7% on all three databases), significantly outperforming state-of-the-art commercial software and methods from the literature.

show abstract

Associative neural networks as means for low-resolution video-based recognition

Cited by 14 publications

References 22 publications

A Neural Network Receiver for EM-MWD Communication

A Neural Network Receiver for EM-MWD Communication

Face tracking and recognition with visual constraints in real-world videos

Face Recognition from Video Using the Generic Shape-Illumination Manifold

Contact Info

Product

Resources

About