Development of a new machine vision algorithm to estimate potato's shape and size based on support vector machine

Abstract Development of a new machine vision‐based algorithm, to estimate potato's shape and size, will have great significance to agricultural industry in developing countries. Machine vision, one of hot technique, uses machines to execute measurement, calculating, and judgment instead of human eyes. In this study, a new machine vision algorithm, based on support vector machine, was proposed for estimating potato's shape and size. After captured the square RGB image with 512 × 512 pixels, the original image was processed by gray scale and linear transformation, filtering, entity, and boundary detecting. Then, geometric characteristics, image wavelet moment, and fractal dimension of boundary were extracted for marking the potato's characteristic. In addition, the effect of four kind of support vector machine (SVM) kernel function was comparing by several experiments with 64 potato samples. By experimental confirmation, SVM based on the polynomial kernel is more suitable for discriminating potato's shape with an accuracy of 88.89%; SVM based on the linear kernel is more suitable for estimating potato's size with an accuracy of 87.41%. Practical applications Potato is a high‐yield, nutrient‐rich crop with high nutritional value. This study proposes a potato shape and size estimation algorithm based on machine vision. Through experimental verification, the detection accuracy of the algorithm initially meets the actual engineering application. The shape and size of potatoes can be detected to classify potatoes. In the process of food processing such as potato chips, the classification of potatoes is conducive to improving the quality of food processing.