Developing an Image Processing Model in Augmented Reality Marketing Advertisements Using an Interpretive Structural Approach

Abstract

Objective: The objective of this study is to develop a structural-interpretive model for image processing in augmented reality (AR) marketing advertisements using a system analysis approach. Methodology: This mixed-method study utilized both qualitative and quantitative methodologies. In the qualitative phase, data were gathered through semi-structured interviews with 35 marketing experts and scholars. Ten key components of image processing were identified through thematic coding. In the quantitative phase, MATLAB software was used to construct an Interpretive Structural Modeling (ISM). MICMAC analysis was subsequently employed to evaluate the influence and dependence of the components. Findings: The results indicated that the proposed model consists of three hierarchical levels. The first level includes core components such as depth estimation, machine learning integration, semantic content, and image composition. The second level encompasses color, texture, real-time tracking and registration, and feature matching. The third level comprises smart object recognition and low-latency rendering techniques. MICMAC analysis categorized the components into six types: risk variables, target variables, influencing variables, influenced variables, secondary leverage, and independent variables. Conclusion: Advanced image processing techniques such as depth estimation, real-time tracking, and machine learning significantly enhance user experience in AR-based advertising. The proposed model can help businesses and marketers design more engaging and immersive advertising strategies using AR technologies. It offers strategic insights into optimizing consumer interaction by integrating key visual elements effectively.