Abstract
Background: Most techniques that adopt the BOW model in annotating images declined favorable information that can be mined from image categories to build discriminative visual vocabularies. We introduce a detailed framework for automatically annotating natural scene images with local semantic labels from a predefined vocabulary.
Methods: The proposed framework is based on a hypothesis that assumes that, in natural scenes, intermediate semantic concepts are correlated with the local keypoints. Based on this hypothesis, image regions can be efficiently represented by BOW model and using a machine learning approach, such as SVM, to label image regions with semantic annotations. Another objective of this paper is to address the implications of generating visual vocabularies from image halves, instead of producing them from the whole image, on the performance of annotating image regions with semantic labels.
Results: The reported results have shown the plausibility of using the BOW model to represent the semantic information of image regions and thus to automatically annotate image regions with semantic labels.
Conclusion: Our experimental results shows the plausibility of local from global approach for image region annotation as well as the discriminative power of using visual vocabularies from image halves. It showed an improved annotation results using integrated bag of visual words combined with low-level features.
Keywords: Image annotation, natural scenes, bag of visual words, visual vocabulary, semantic modelling, semantic concepts.
Graphical Abstract
Call for Papers in Thematic Issues
Federated learning for biomedical applications
Federated learning, also known as distributed AI/machine learning, is a method that enables cooperative learning from big datasets owned by several parties without compromising the privacy of each person's raw data. FL is especially helpful when the needed information is not open source or easily accessible due to tactical or ...read more
Information, Trust, and Risk: Exploring the Intersection of Sensing, Wireless Communications, and Control
Sensing technologies, wireless communications, and control systems are becoming ubiquitous in our daily lives, with the potential to enhance and streamline many aspects of modern society. However, this also creates new challenges in terms of ensuring trust and managing risks associated with the use of these technologies. The sheer volume ...read more
Machine Learning for Industry 4.0 manufacturing applications
This thematic issue will focus on the intersection of Machine Learning and the manufacturing industry within the context of Industry 4.0. Industry 4.0 involves the use of smart sensors, devices, and machines to enable the creation of smart factories that constantly collect data related to production. Machine Learning techniques can ...read more
Next-Generation Network Architecture, Algorithms, and Security
Design of new network architectures, algorithms and protocols is one of the fundamental challenges in next-generation networking. To this end, novel networking techniques and applications are required for advancing today?s complex communication networks. This thematic issue provides researchers, industry professionals and practitioners with a forum to present the latest research ...read more
Related Books
IoT-enabled Sensor Networks: Architecture, Methodologies, Security, and Futuristic Applications
AIoT and Big Data Analytics for Smart Healthcare Applications
Research Trends in Artificial Intelligence: Internet of Things
Artificial Intelligence and Multimedia Data Engineering
Basics of Python Programming: A Quick Guide for Beginners
Blockchain Technology in Healthcare - Concepts, Methodologies, and Applications
Artificial Intelligence and Knowledge Processing: Methods and Applications
Handbook of Artificial Intelligence
Amazon Web Services: the Definitive Guide for Beginners and Advanced Users
The Role of AI in Enhancing IoT-Cloud Applications
14