Building an expert system for printer forensics: A new printer identification model based on niching genetic algorithm

Abstract

AbstractInside digital forensic science, expert systems are utilized to clarify suspicions where normally one or more human experts would need to be consulted. Expert systems‐based printer identification is provided with the objective of distinguishing the printer that produced a suspicious or questioned document. The arising problem is that the extraction of many features of the printed document for printer forensics sometimes increases the time and decreases the classification accuracy as many of the printed document descriptors may emanate to be recurring and non‐valuable. Therefore, the distinct combinatorial collection of features (knowledge base) will demand to be acquired in order to preserve the essence of operative features' fusion to accomplish the maximum accuracy. This paper presents a bio‐inspired expert system for printer forensics that integrates both texture features conveyed from the grey level co‐occurrence matrix of the printed letter ‘WOO’ and niching genetic search to select the good enough reduced feature set. This combination intends to realize high classification precision relies on a trivial collection of discriminative descriptors. Niching methods extend genetic algorithms to domains that require the location and maintenance of multiple solutions based on adjusting the crossover ratio and occurrence of mutation of each individual and employs the slope of the individuals to choose their mutation value. For categorization, the scheme exploits k‐nearest neighbours (KNN) to distinguish the brand of the printer for its simplicity. Results confirm that the suggested approach has high classification accuracy and needs less computation time.