grey level
5.Calculation of grey-level co-occurrence matrices (GLCM) helps mathematically describe the distribution of pixel values within a subregion of data, and effectively quantify the spatial structures of seismic reflections.
7.This paper studies the possibility of buiding pattern clssifiers for text/picture segmentation and text detection problems with convolutional neural networks (CNNs). Using CNN, explicit feature extraction can be avoided. More importantly, CNN can directly operate on grey level images, making its application straightforward.
8.Compared with the multiscale fractal signature, it does not have singular values and can be computed easily. For this reason, a natural scenery image matching method is proposed. Experimental results show that the δ net fractal fingerprint signature is a robust fractal feature of the images of natural scenery and the matching method proposed is more efficient than those in common use based on the grey level and edges, such as the mean absolute difference (MAD) algorithm and the multiscale fractal signature matching method.
