A Robust Indoor Scene Recognition Method based on Sparse Representation

TL;DR

This paper introduces a robust indoor scene recognition method combining CNN features with sparse coding, capturing both global and local details to improve accuracy and robustness against image perturbations.

Contribution

The novel approach integrates CNN-based features with sparse coding to enhance scene recognition, especially under noisy or occluded conditions.

Findings

Outperforms previous methods on Scene15 and MIT67 datasets.

Shows high robustness to noise and occlusion.

Performs competitively on SUN397 dataset.

Abstract

In this paper, we present a robust method for scene recognition, which leverages Convolutional Neural Networks (CNNs) features and Sparse Coding setting by creating a new representation of indoor scenes. Although CNNs highly benefited the fields of computer vision and pattern recognition, convolutional layers adjust weights on a global-approach, which might lead to losing important local details such as objects and small structures. Our proposed scene representation relies on both: global features that mostly refers to environment's structure, and local features that are sparsely combined to capture characteristics of common objects of a given scene. This new representation is based on fragments of the scene and leverages features extracted by CNNs. The experimental evaluation shows that the resulting representation outperforms previous scene recognition methods on Scene15 and MIT67 datasets, and performs competitively on SUN397, while being highly robust to perturbations in the input image such as noise and occlusion.