Taxonomy, state-of-the-art, challenges and applications of visual understanding: A review

• Published in: Computer science review 2021-05, Vol.40, p.100374, Article 100374
• Main Authors: Khanday, Nadeem Yousuf, Sofi, Shabir Ahmad
• Format: Article
• Language: English
• Subjects: Applications; Challenges; Computer vision; Developments; Trends; Visual learning
• ISSN: 1574-0137; 1876-7745
• DOI: 10.1016/j.cosrev.2021.100374

Since the dawn of Humanity, to communicate both abstract and concrete ideas, visualization through visual imagery has been an effective way. With the advancement of scientific technologies, vision has been imparted to machines like humans do. Computer vision give ability to machines, to receive and analyze visual data on its own, and then make decisions about it, hence computer vision is more than machine learning applied. So, visualization of computer models to learn without being explicitly programmed using machine learning algorithms is called Visual learning. This work aims to review the state-of-the-art in computer vision by highlighting the contributions, challenges and applications. We first provide an overview of important visual learning approaches and their recent developments, and then describes their applications in diverse vision tasks, such as image classification, object detection, object recognition, visual saliency detection, semantic and instance segmentation, human pose estimation and image retrieval. Hardware constraints are also highlighted for better understanding of model selection. Finally, some important challenges, trends and outlooks are also discussed for better design and training of learning modules, along with several directions that may be further explored in the future.