Dual Directed Capsule Network for Very Low Resolution Image Recognition

TL;DR

This paper introduces DirectCapsNet, a novel dual directed capsule network architecture that leverages high-resolution auxiliary data and new loss functions to improve very low resolution image recognition, achieving state-of-the-art results.

Contribution

The paper proposes a new capsule network architecture with two novel loss functions that utilize high-resolution images during training for better VLR recognition.

Findings

Achieves over 95% face recognition accuracy on UCCS database with 16x16 images.

Outperforms existing algorithms in VLR digit and face recognition tasks.

Demonstrates effectiveness of high-resolution auxiliary data and novel losses.

Abstract

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.