Indoor image representation by high-level semantic features

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.

arXiv commentThis paper has been accepted in IEEE Access

References in corpus (4)

• A Discriminative Representation of Convolutional Features for Indoor Scene Recognition
• Locally-Supervised Deep Hybrid Model for Scene Recognition
• Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition
• Hierarchical Deep Learning Architecture For 10K Objects Classification

Cited by in corpus (6)

• Scene Image Representation by Foreground, Background and Hybrid Features
• Content and Context Features for Scene Image Representation
• HDF: Hybrid Deep Features for Scene Image Representation
• Unsupervised Deep Features for Privacy Image Classification
• Recent Advances in Scene Image Representation and Classification
• Tag-based Semantic Features for Scene Image Classification