# Indoor image representation by high-level semantic features

## TL;DR

This paper introduces high-level semantic features for indoor image representation, improving classification performance by capturing semantic object relationships more effectively than traditional pixel-based methods.

## Contribution

The paper proposes a novel high-level semantic feature extraction method that enhances indoor image classification accuracy and reduces feature dimensionality.

## Key findings

- Outperforms state-of-the-art methods on MIT-67, Scene15, and NYU V1 datasets.
- Achieves higher classification accuracy with lower-dimensional features.
- Demonstrates the effectiveness of semantic features in capturing image semantics.

## Abstract

Indoor image features extraction is a fundamental problem in multiple fields such as image processing, pattern recognition, robotics and so on. Nevertheless, most of the existing feature extraction methods, which extract features based on pixels, color, shape/object parts or objects on images, suffer from limited capabilities in describing semantic information (e.g., object association). These techniques, therefore, involve undesired classification performance. To tackle this issue, we propose the notion of high-level semantic features and design four steps to extract them. Specifically, we first construct the objects pattern dictionary through extracting raw objects in the images, and then retrieve and extract semantic objects from the objects pattern dictionary. We finally extract our high-level semantic features based on the calculated probability and delta parameter. Experiments on three publicly available datasets (MIT-67, Scene15 and NYU V1) show that our feature extraction approach outperforms state-of-the-art feature extraction methods for indoor image classification, given a lower dimension of our features than those methods.