Amplitude modulation and frequency modulation textures model based on medical image retrieval
Zhao Shuai, Lu Zhentai, Qianjin Feng, Wufan Chen · Journal of Circuits and Systems · 2010
This paper presents a new retrieval algorithm using Amplitude Modulation and Frequency Modulation (AM-FM) image model. First, the medical images are filtered by 2D Gabor, and the partial differentiation of the Gabor impulse response is computed. Second, the joint demodulations of AM and FM are performed using energy separation algorithm (ESA) for computing instantaneous amplitude and instantaneous frequency. We use the mean and the standard deviation of amplitude and frequency as texture features. We analyze the performance of the new algorithm, and compare this algorithm with the method which texture features are computed from Gabor filter bank. Experimental results show that the new algorithm achieves a significant improvement for medical image retrieval.