Sum and Difference Histograms for Texture Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Morphological methods in image and signal processing
Morphological methods in image and signal processing
Size distribution estimation of stone fragments via digital image processing
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part III
Hi-index | 0.08 |
Dynamic speckle patterns are generated by laser light scattering on surfaces that exhibit some kind of activity, due to physical or biological processes. The characterization of this process is carried out by studying the texture changes of auxiliary images: temporal history of the speckle pattern (THSP). The drying process of water borne paint is studied through a method based on mathematical morphology applied to the THSP image processing. It is based on obtaining the granulometry of these images and their characteristic granulometric spectrum. From the granulometric size distribution of each THSP image four parameters are obtained: mean length, standard deviation, asymmetry and kurtosis. These parameters are found to be suitable as texture features. The Mahalanobis distance is calculated between the texture features of the THSP images representative of the temporary stages of the drying process and the features of the final stage or pattern texture. The behavior of the distance function describes satisfactorily the drying process of the water borne paint. The results are compared with other methods. Compared with others, the granulometric method reported in this paper distinguished by its simplicity and easy implementation and can be used to characterize the evolution of any process recorded through dynamic speckles.