Abstract
In recent years, scene semantic recognition has become the most exciting and fastest growing research topic. Lots of scene semantic analysis methods thus have been proposed for better scene content interpretation. By using latent Dirichlet allocation (LDA) to deduce the effective topic features, the accuracy of image semantic recognition has been significantly improved. Besides, the method of extracting deep features by layer-by-layer iterative computation using convolutional neural networks (CNNs) has achieved great success in image recognition. The paper proposes a method called DF-LDA, which is a hybrid supervised–unsupervised method combined CNNs with LDA to extract image topics. This method uses CNNs to explore visual features that are more suitable for scene images, and group the features of salient semantics into visual topics through topic models. In contrast to the LDA as a tool for simply extracting image semantics, our approach achieves better performance on three datasets that contain various scene categories.
Highlights
As one of the most basic and important forms of multimedia information, images have been widely used in the fields of image classification, target detection, geographical annotation, and so on, because of its intuitive appearance and rich content
The latent Dirichlet allocation (LDA) model is the best probabilistic topic model for statistical text classification [21], so we model the features of the image as words of
Model isThrough the best probabilistic from the traditional topic model based on low-level features, we propose DF-LDA, which means that topic model for statistical text classification so we model the features ofthe the best image as words of topic the image topic, the hidden visual topic can be[21], obtained
Summary
As one of the most basic and important forms of multimedia information, images have been widely used in the fields of image classification, target detection, geographical annotation, and so on, because of its intuitive appearance and rich content. The model of latent Dirichlet allocation [1] has been successfully and rapidly applied to many fields by processing the texts or images to obtain thematic variables, and use them as a basis of classification or other processing, such as processing of texts [2], image retrieval [3], remote sensing images [4], data mining [5], and so on. In order to overcome these shortcomings, the work in this paper considers the use of a deep network model to extract the features of an image, and deduces the topic distribution in combination with LDA. Based on these motivations, a DF-LDA strategy is proposed. Based on latent Dirichlet allocation of deep features, a strategy called DF-LDA effectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
