Browsing by Author "Harvey, Carlo"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Exploring the Impact of Synthetic Data Generation on Texture-based Image Classification Tasks
    (The Eurographics Association, 2023) Yordanov, Borislav; Harvey, Carlo; Williams, Ian; Ashley, Craig; Fairbrass, Paul; Pelechano, Nuria; Liarokapis, Fotis; Rohmer, Damien; Asadipour, Ali
    In this study, we introduce a novel pipeline for synthetic data generation of textured surfaces, motivated by the limitations of conventional methods such as Generative Adversarial Networks (GANs) and Computer-Aided Design (CAD) models in our specific context. We also investigate the pipeline's role in an image classification task. The primary objective is to determine the impact of synthetic data generated by our pipeline on classification performance. Using EfficientNetV2-S as our image classifier and a dataset of three texture classes, we find that synthetic data can significantly enhance classification performance when the amount of real data is scarce, corroborating previous research. However, we also observe that the balance between synthetic and real data is crucial, as excessive synthetic data can negatively impact performance when sufficient real data is available. We theorize that this might stem from imperfections in the synthetic data generation process that distort fine details essential for accurate classification, and propose possible improvements to the synthetic data generation pipeline. Furthermore, we acknowledge the potential limitations of our study and provide several promising avenues for future research. This work illuminates the advantages and potential drawbacks of synthetic data in image classification tasks, emphasizing the importance of high-quality, realistic synthetic data that complements, rather than undermines, the use of real data.
  • No Thumbnail Available
    Item
    Olfaction and Selective Rendering
    (© 2018 The Eurographics Association and John Wiley & Sons Ltd., 2018) Harvey, Carlo; Bashford‐Rogers, Thomas; Debattista, Kurt; Doukakis, Efstratios; Chalmers, Alan; Chen, Min and Benes, Bedrich
    Accurate simulation of all the senses in virtual environments is a computationally expensive task. Visual saliency models have been used to improve computational performance for rendered content, but this is insufficient for multi‐modal environments. This paper considers cross‐modal perception and, in particular, if and how olfaction affects visual attention. Two experiments are presented in this paper. Firstly, eye tracking is gathered from a number of participants to gain an impression about where and how they view virtual objects when smell is introduced compared to an odourless condition. Based on the results of this experiment a new type of saliency map in a selective‐rendering pipeline is presented. A second experiment validates this approach, and demonstrates that participants rank images as better quality, when compared to a reference, for the same rendering budget.Accurate simulation of all the senses in virtual environments is a computationally expensive task. Visual saliency models have been used to improve computational performance for rendered content, but this is insufficient for multi‐modal environments. This paper considers cross‐modal perception and, in particular, if and how olfaction affects visual attention. Two experiments are presented in this paper. Firstly, eye tracking is gathered from a number of participants to gain an impression about where and how they view virtual objects when smell is introduced compared to an odourless condition.
  • Thumbnail Image
    Item
    VR Video Storytelling for Intangible Cultural Heritage Preservation
    (The Eurographics Association, 2018) Selmanovic, Elmedin; Rizvic, Selma; Harvey, Carlo; Boskovic, Dusanka; Hulusic, Vedad; Chahin, Malek; Sljivo, Sanda; Sablatnig, Robert and Wimmer, Michael
    Interactive digital storytelling has become a popular method for virtual cultural heritage presentations. Combinations of stories and 3D virtual reconstructions are attractive for the audience and have high edutainment values. In this paper we investigate if 360 degrees VR videos further contribute to user immersion in the preservation of intangible cultural heritage. It describes a case study of the Mostar bridge diving project, aimed to present and preserve the bridge diving tradition from the Old Bridge in Mostar, Bosnia and Herzegovina. It is a virtual reality application which enables the user to virtually jump off the bridge after watching 360 degrees video stories about its history and the bridge diving tradition and upon successfully completing the quiz evaluation of the knowledge gained from the stories. The user experience evaluation study shows that our method was successful in preserving a form of intangible heritage and posits suggestions that can be used in developing an intangible heritage preservation framework.