Employing Image Analysis for Predicting the Sense of Sameness
39 Pages Posted: 12 Dec 2013
Date Written: December 11, 2013
Abstract
From the late 19th century on, psychological research is interested in humans’ sense of sameness, since perceived similarity between objects is fundamental for cognitive processes like object recognition and categorization. Product designers continuously emphasize how important yet difficult it is to create new products with designs similar enough for brand recognition, yet dissimilar enough for a unique positioning. Advancing the understanding of perceived design similarity would greatly help to systematically manage this balance. Design literature provides several concepts, which assess how much a new design deviates from the status quo based on consumers’ holistic similarity judgments. For management practice, however, tests of numerous design alternatives with consumers throughout the NPD process are time-consuming, costly and threaten confidentiality. In addition, holistic judgments cannot provide any insights about the design elements that explain perceived similarity. For designers it thus remains unclear which elements should be modified to increase or decrease perceived similarity between new and existing designs. It also prohibits predictions about similarities of alternative product designs, which have not been explicitly tested with consumers. To overcome these drawbacks, we introduce an objective, component-based measurement approach of design similarity. Based on standardized product images, we identify a set of objective measures for all relevant design elements. The results of an empirical study demonstrate that similarity judgments of consumers can be reproduced with these measures. Our approach, thus, makes measurement of design similarity more efficient, uncovers the design elements that drive holistic similarity judgments, and enables managers to predict the positioning of alternative product designs in the perceptual space.
Keywords: Product Design, Similarity, Perception, Cognition, Information Retrieval
Suggested Citation: Suggested Citation