Dual Directed Capsule Network for Very Low Resolution Image Recognition

by   Maneet Singh, et al.
IIIT Delhi

Very low resolution (VLR) image recognition corresponds to classifying images with resolution 16x16 or less. Though it has widespread applicability when objects are captured at a very large stand-off distance (e.g. surveillance scenario) or from wide angle mobile cameras, it has received limited attention. This research presents a novel Dual Directed Capsule Network model, termed as DirectCapsNet, for addressing VLR digit and face recognition. The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model. The architecture also incorporates two novel loss functions: (i) the proposed HR-anchor loss and (ii) the proposed targeted reconstruction loss, in order to overcome the challenges of limited information content in VLR images. The proposed losses use high resolution images as auxiliary data during training to "direct" discriminative feature learning. Multiple experiments for VLR digit classification and VLR face recognition are performed along with comparisons with state-of-the-art algorithms. The proposed DirectCapsNet consistently showcases state-of-the-art results; for example, on the UCCS face database, it shows over 95% face recognition accuracy when 16x16 images are matched with 80x80 images.


page 1

page 3

page 4

page 7


Homogeneous Low-Resolution Face Recognition Method based Correlation Features

Face recognition technology has been widely adopted in many mission-crit...

Image Resolution Susceptibility of Face Recognition Models

Face recognition approaches often rely on equal image resolution for ver...

Octuplet Loss: Make Face Recognition Robust to Image Resolution

Image resolution, or in general, image quality, plays an essential role ...

Enhancing Fine-Grained Classification for Low Resolution Images

Low resolution fine-grained classification has widespread applicability ...

Image Set Classification for Low Resolution Surveillance

This paper proposes a novel image set classification technique based on ...

Forensic License Plate Recognition with Compression-Informed Transformers

Forensic license plate recognition (FLPR) remains an open challenge in l...

Ring loss: Convex Feature Normalization for Face Recognition

We motivate and present Ring loss, a simple and elegant feature normaliz...

Please sign up or login with your details

Forgot password? Click here to reset