Sorting of rice grains using Zernike moments

Abstract

Two important factors that determine the efficiency and reliability of a rice sorting machine are the overall processing speed and the classification accuracy. In this paper, an efficient rice sorting process which uses a subset of Zernike moments (ZM) and a multilayer perceptron is presented. Since the falling rice grains during sorting process can be in any orientation, a rotational invariant feature set is crucial in this application. Hence, the set of ZM with its inherent rotational invariance property is chosen in this context. Nevertheless, one of the main drawbacks of ZM in real-time application is its long computation time. To overcome this, a subset of ZM is selected from its original full set of 12 orders, using the combination of fuzzy ARTMAP and genetic algorithm. To further reduce the computation time, the combination of q-recursive method and Zernike polynomials' inherent symmetry property is utilized. Hence, the processing time of the subset of ZM is significantly reduced by almost 67% while maintaining the classification accuracy as compared to computing the original full set of ZMs.

A Survey of the State of the Art in Sensor-Based Sorting Technology and Research

“…Other research is even concerned with estimating seed vigor during grading [13]. Comparable studies have also been published in the context of corn seed [14], for rice grading [15]- [17], and sunflower seed [18].…”

Motion-based visual inspection of optically indiscernible defects on the example of hazelnuts

“…The main fields of application of sensor-based sorting are recycling, for instance the preparation of glass [9] by removing materials harmful to the melting process such as stones and ceramic glass [10], mining, mainly to remove unwanted gangue from ore, e.g., copper-gold ore [11], as well as agricultural products and foodstuff. Regarding the latter, examples of applications are diverse, including the removal of fungusinfected wheat kernels [12], low-quality rice grains [13], and sunflower seeds [14], or quality insurance in bulgur The turquoise objects represent particles to be accepted, typically the product, and the red ones those to be removed, for instance foreign particles. The field of view by the sensor is denoted by the yellow ray.…”

Specified Target Detection and Tracking on Complex Infrared Background

“…Invariant features of infrared target include area, gray value, location and shape feature, etc. There are many methods to describe shape features, such as multi-layer eigenvector (MLEV) shape descriptor [9], invariant moments [10] and Zernike moments [10,11]. The description of the above method is in better performance, but the computation of these methods is too complex to meet the requirements of real-time in tracking.…”