论文部分内容阅读
研究了多灰度层次的特殊目标在复杂背景和噪声干扰下的多门限检测技术,该项技术考虑了视觉的灰度特性,空间特性以及噪声干扰引入的错误检测的统计特性。对多门限步级检测器作了理论上的分析和计算机实现,并将所研究的结果应用到 X 线片骨龄识别之中。实际测试结果表明:多门限步级检测器具有很好的检测性能。本文讨论的计算机自动目标检测技术在固定场景监测,工业无损探测以及生物医学工程中癌症、肿瘤、结核等病变的早期计算机诊断中有着十分广泛的应用。
The multi-threshold detection technique for multi-grayscale special targets under complex background and noise interference is studied. The technique considers the visual characteristics of gray scale, spatial characteristics and the statistical properties of error detection introduced by noise interference. The multi-threshold step detector is theoretically analyzed and computerized, and the results of the study are applied to the identification of bone age in X-ray films. The actual test results show that: multi-threshold step detector has good detection performance. The computer automatic target detection technology discussed in this paper has a very wide range of applications in the early computer diagnosis of cancer, cancer, tuberculosis and other lesions in fixed scene monitoring, industrial nondestructive detection and biomedical engineering.