Wavelets in the analysis of seed image similarity: an approach using the Hurst directional exponent

Modernization is present in all fields of knowledge. The wavelet transform and the Hurst exponent are tools that have fundamental importance many these advances. In study, decomposition technique was combined with calculation to analyze X-ray images seeds thus classify them as full, slightly damaged or damaged. To calculate mean median were used measurements position. A support vector machine validate proposed method. For seed groups, average accuracy method, using measure position, 74.5%, 57.05%. full 99.76%, 80.93%. accuracy, 99.26%, 76.22%. When analyzing slight damage, we observed a decrease because classification X-rays subjective. Therefore, for image database this methodology efficient automatic classification.