Optimizing feature-vector extraction algorithm from grayscale images for robust medical radiograph analysis
Optimizing feature-vector extraction algorithm from grayscale images for robust medical radiograph analysis
复制标题
优化灰度图像的特征向量提取算法，以实现稳健的医学放射线分析
DOI：
10.1109/wac.2002.1049553
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
K. Takada
中科院分区：
文献类型：
--
作者：
M. Yagi;T. Shibata;K. Takada
为稳健的图像表示而开发的主轴投影 (PAP) 技术已针对精细的灰度图像识别进行了优化。 PAP技术利用图像中四个主要方向的边缘信息，并生成一个特征向量，该特征向量很好地保留了人类对相似性的感知，并大幅降低了维数。对算法在确定边缘检测阈值、将边缘标志投影到主轴上以及平滑矢量元素方面进行了优化。图像识别模板的数量也利用广义劳埃德算法进行了优化。由此，牙科正畸学中最重要的临床实践之一——头影测量标志识别得以成功开展。
The principal axis projection (PAP) technique developed for robust image representation has been optimized for delicate grayscale image recognition. The PAP technique utilizes the edge information in four principal directions in an image, and generates a feature vector very well preserving the human-perception of the similarity with a great dimensionality reduction. The optimization was carried out for the algorithm in determining the edge-detection threshold, projecting edge flags onto principal axes, and smoothing vector elements. The number of templates for image recognition was also optimized utilizing the generalized Lloyd algorithm. As a result, the cephalometric landmark identification, one of the most important clinical practices in orthodontics of dentistry, was successfully carried out.