基因芯片生物信号的自动识别

Automatic-Identification of Spots in Biochip Image

信号点自动识别是基因芯片信息自动提取的关键。为此,根据信号点、噪声和背景特征的关系提出一种新的自动识别方法:使用小波变换的方法实现图像的滤波增强;通过对功率谱的分析实现图像的信号点中心的网格定位;利用信号点边缘亮度特征实现信号点中心和半径的校正。仿真实验证明,该方法具有良好的抗噪声能力和弱信号辨识能力,能快速、准确地实现信号的点自动识别。

Automatic-identification of signal spots is the key for automatic-extracting information from genechip images. A new approach of automatic-identification is proposed based on the relations of spots, noises and backgrounds. Wavelet transform was used to filter and enforce images and estimate intensity of background. Spectrum of power was used to perform spots gridding automatically. Considering intensity of edge, a new technique to correct center and radius was introduced. The approach has been tested in a variety of biochip images, and better resistant performance of noises and identification of weak signals are realized. It can automatic-identify spots quickly and accurately.