Decision-Making Approach Based on Bipolar Complex Fuzzy Uncertain Linguistic Aggregation Operators

There are many computer vision technologies available, each having advantages and disadvantages of its own. Effective visual data analysis requires choosing the best technology and giving its deployment top priority. A strong framework for decision-making (DM) is required, one that can manage the ambiguities, imprecision, dual aspects, and linguistic terms present in real-world computer vision applications. Thus, in this script, we investigate the DM framework under the structure of a bipolar complex fuzzy uncertain linguistic set (BCFULS). The theory of BCFULS is also devised in this manuscript, which can model the data that contains ambiguities, extra fuzzy information, dual aspects, and linguistic terms simultaneously. For this DM framework, we inaugurate averaging/geometric aggregation operators (AOs) within the structure of BCFULS and analyze the related properties. After that, we employ the inaugurated DM framework to prioritize the numerous types of computer vision by considering artificial data and achieve that "Feature Matching" is the finest computer vision. Finally, this script contains a comparative analysis of this work with numerous current works to depict the supremacy and advantages of the invented work.