本文研究了用于定量测量复合材料表面波纹度的机器视觉技术。提出了两种基于计算机视觉的波浪度长期和短期测量算法。所提出的算法计算的波纹度指数对复合材料外表面的整体质量进行排序。一个自动波纹度排序系统使用稳健的统计模式分类程序将表面样本分类为单独的质量类别。实验结果表明，计算机对波浪度进行排序的性能与人类检查员相当。

THIS PAPER INVESTIGATES MACHINE VISION TECHNOLOGIES FOR QUANTITATIVELY MEASURING COMPOSITES SURFACE WAVINESS. TWO ALGORITHMS BASED UPON COMPUTER VISION METHODS ARE PRESENTED FOR MEASURING THE LONG-TERM AND THE SHORT-TERM WAVINESS. THE WAVINESS INDICES COMPUTED BY THE PROPOSED ALGORITHMS RANK THE OVERALL QUALITY OF COMPOSITES EXTERIOR SURFACES. AN AUTOMATIC WAVINESS RANKING SYSTEM USED ROBUST STATISTICAL PATTERN CLASSIFICATION PROCEDURES TO CLASSIFY SURFACE SAMPLES INTO SEPARATE QUALITY CATEGORIES. EXPERIMENTAL RESULTS SHOW THAT THE PERFORMANCE OF THE COMPUTER RANKING OF WAVINESS IS COMPARABLE TO THAT OF HUMAN INSPECTORS.