Assessinginclusion content in aluminum melts is essential for ensuring product qualityin aluminum production. Traditional methods such as Porous Disk FiltrationApparatus (PoDFA) provide detailed cleanliness assessments but rely on manualanalysis, limiting throughput and introducing subjectivity. Deterministic imageanalysis provides a fast and transparent alternative. We present an expansionof the Automated Metal Cleanliness Analyzer (AMCA), building on previous workthat demonstrated strong correlation with PoDFA-derived total inclusion counts(TIC). The updated classification logic enables automatic detection of fiveTIC-relevant inclusion groups—carbides, grain refiners, refractory, spinel, andmixed oxides—alongside three non-TIC categories: filter grain, aluminum bulk,and intermetallic phases or artifacts. AMCA’s classification logic utilizesstatistical analyses of manually annotated inclusions for derivingdeterministic rulesets. Our results demonstrate strong agreement withPoDFA-derived cleanliness metrics. This advancement positions AMCA as ascalable, transparent, and cost-effective alternative for process monitoringand quality control in aluminum production.