Abstract
In today’s fast-paced digital era, advertising design heavily depends on advanced visual communication techniques to capture and maintain consumer attention. By leveraging dynamic visuals, brands can effectively engage diverse audiences and create long-lasting connections with consumers. Traditional advertising design often lacks effectiveness due to subjective judgments. The challenge lies in combining aesthetics with audience engagement using algorithmic techniques for improved visual communication. The objective of this study is to explore the application of algorithm-driven visual communication strategies in advertising design, focusing on enhancing the effectiveness of visual content by aligning with audience preferences and behaviors. The collected data undergo preprocessing using the normalization technique. Feature extraction is performed using convolutional neural networks (CNNs) to analyze advertising background images, allowing for the selection of suitable visuals that resonate with the target audience. This study proposed an intelligent moth flame-optimized malleable-gated recurrent units (IMF-MGRU) method that synthesizes textual information to generate effective product taglines, enhancing the expressiveness of the advertising image. Malleable-gated recurrent units (MGRU) are utilized to create relevant taglines that align with the selected visuals, while the intelligent moth flame (IMF) optimizes the layout of elements within the image, minimizing overlap among key components. Experimental findings show that the suggested method enhances the appeal of advertising content, particularly highlighting considerable advantages in performance during the evaluation experiment. The proposed IMF-MGRU method represents a significant advancement in synthesizing visual and textual elements, resulting in cohesive and compelling advertising designs.
Published Version
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 call