DEFECT REFERENCE SYSTEM AUTOMATIC PATTERN CLASSIFICATION

A methodology is provided for qualitatively identifying features of an article, such as defects on the surface of a semiconductor substrate, with a string of symbols, such as numbers, according to relevant defect characteristics and information relating to the processing tools visited by the wafer, including reliability information. Embodiments include generalizing, after a defect on a wafer is discovered and inspected (as by optical review, SEM, EDS, AFM, etc.), each quantitative attribute of the defect such as the defect's size, material composition, color, position on the surface of the wafer, etc. into a qualitative category, assigning a numerical symbol to each attribute for identification, and sequencing the symbols in a predetermined manner. The identification sequences of all defects are stored in a database, where they are easily compared with other correspondingly identified defects. The identification sequence also includes a number representative of the wafer's last-visited processing tool, thereby associating the defect with a tool. After the defect is investigated and determined as being caused by a particular fault of the tool, this information is stored and linked to the defect's identification sequence. Thereafter, if a similar defect occurs in another wafer, the later defect's identification sequence is matched to that of the previous defect by searching the defect database, indicating the same cause for the later defect, thereby enabling ready identification of the root causes of defects, and enabling early corrective action to be taken.