• Publications
  • Influence
A Light CNN for Deep Face Representation With Noisy Labels
TLDR
This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. Expand
  • 485
  • 107
  • PDF
Ordinal palmprint represention for personal identification [represention read representation]
TLDR
In this paper, we present a novel palmprint representation - ordinal measure, which unifies several major existing palmprint algorithms into a general framework. Expand
  • 403
  • 39
  • PDF
Deep Supervised Discrete Hashing
TLDR
In this paper, we develop a deep supervised discrete hashing algorithm based on the assumption that the learned binary codes should be ideal for classification. Expand
  • 120
  • 36
  • PDF
A Lightened CNN for Deep Face Representation
TLDR
This paper studies a lightened CNN framework to learn a compact embedding for face representation. Expand
  • 162
  • 26
  • PDF
Ordinal Measures for Iris Recognition
  • Z. Sun, T. Tan
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 December 2009
TLDR
We propose using ordinal measures for iris feature representation with the objective of characterizing qualitative relationships between iris regions rather than precise measurements of iris image structures. Expand
  • 262
  • 24
  • PDF
Toward Accurate and Fast Iris Segmentation for Iris Biometrics
TLDR
We present a novel algorithm for accurate and fast iris segmentation for iris biometrics. Expand
  • 364
  • 21
  • PDF
Fast Supervised Discrete Hashing
TLDR
We propose a new learning-based hashing method called “fast supervised discrete hashing” (FSDH) based on "supervised discrete hashing" (SDH). Expand
  • 109
  • 17
  • PDF
Discriminant sparse neighborhood preserving embedding for face recognition
TLDR
In this paper, a new sparse subspace learning algorithm called discriminant sparse neighborhood preserving embedding (DSNPE) is proposed by adding the discriminant information into sparse neighborhood preserves embedding. Expand
  • 222
  • 16
  • PDF
Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition
TLDR
In this paper, we present a novel iris segmentation algorithm, aiming at noisy iris images in non-cooperative environments. Expand
  • 246
  • 16
  • PDF
Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution
TLDR
We present a wavelet-based CNN approach that can ultra-resolve a very low resolution face image of 16 × 16 or smaller pixelsize to its larger version of multiple scaling factors (2×, 4×, 8×) in a unified framework. Expand
  • 124
  • 15
  • PDF