Grassmannian learning mutual subspace method for image set recognition

11/08/2021
by   Lincon S. Souza, et al.
0

This paper addresses the problem of object recognition given a set of images as input (e.g., multiple camera sources and video frames). Convolutional neural network (CNN)-based frameworks do not exploit these sets effectively, processing a pattern as observed, not capturing the underlying feature distribution as it does not consider the variance of images in the set. To address this issue, we propose the Grassmannian learning mutual subspace method (G-LMSM), a NN layer embedded on top of CNNs as a classifier, that can process image sets more effectively and can be trained in an end-to-end manner. The image set is represented by a low-dimensional input subspace; and this input subspace is matched with reference subspaces by a similarity of their canonical angles, an interpretable and easy to compute metric. The key idea of G-LMSM is that the reference subspaces are learned as points on the Grassmann manifold, optimized with Riemannian stochastic gradient descent. This learning is stable, efficient and theoretically well-grounded. We demonstrate the effectiveness of our proposed method on hand shape recognition, face identification, and facial emotion recognition.

READ FULL TEXT

page 8

page 9

research
11/17/2016

Study on Feature Subspace of Archetypal Emotions for Speech Emotion Recognition

Feature subspace selection is an important part in speech emotion recogn...
research
02/12/2019

Improving Facial Emotion Recognition Systems Using Gradient and Laplacian Images

In this work, we have proposed several enhancements to improve the perfo...
research
07/14/2019

Compressed Subspace Learning Based on Canonical Angle Preserving Property

A standard way to tackle the challenging task of learning from high-dime...
research
09/29/2020

Micro-Facial Expression Recognition in Video Based on Optimal Convolutional Neural Network (MFEOCNN) Algorithm

Facial expression is a standout amongst the most imperative features of ...
research
08/06/2019

Multiple Riemannian Manifold-valued Descriptors based Image Set Classification with Multi-Kernel Metric Learning

The importance of wild video based image set recognition is becoming mon...
research
03/14/2019

Constrained Mutual Convex Cone Method for Image Set Based Recognition

In this paper, we propose a method for image-set classification based on...
research
01/31/2014

Hallucinating optimal high-dimensional subspaces

Linear subspace representations of appearance variation are pervasive in...

Please sign up or login with your details

Forgot password? Click here to reset