Cucumber appearance quality detection under complex background based on image processing

Abstract

Abstract:Cucumber fruit appearance quality is an important basis of growth status. In order to improve the quality detection accuracy and processing efficiency of cucumber color image under complicated background, an improved GrabCut algorithm was proposed to extract the cucumber boundary. Firstly, including pixel size normalization, rectangular box set and scale image resolution, pretreatments of cucumber image were adopted to reduce the iteration times and operation time of GrabCut algorithm. Then, the Gaussian mixture model was chosen to find out the possible prospect of target region and background region in the preprocessed rectangular frame on the preliminary modeling. Meanwhile, by the optimization of K-means cluster to the initial GMM model, the effective target area was extracted. Finally, the whole image noise and serrated boundary was removed by morphological operations to segment the outline of the complete target prospects with appropriate structure size. And then the cucumber appearance quality detection instrument was designed to extract the texture and shape features exactly, so that it could obtain cucumber appearance quality and evaluate its growth effectively. With the segmentation experiments by almost 300 cucumber original images from greenhouse in Shandong Province, the results showed that the improved GrabCut algorithm could effectively extract the complete and smooth boundary of cucumber. With relatively high segmentation evaluation index, the precision was 93.88%, the recall rate was 99.35%, the F-Measure reached 96.53%, and the misclassification error was controlled at minimum 5.84%. The average running time was shortened to 1.4023 s. The comparison results showed that the improved GrabCut algorithm was the best, followed by the SLIC and traditional GrabCut method. Cucumber appearance quality detection instrument could also extract more accurate feature parameters. And it could meet the basic growth condition assessment by automatic image processing. Keywords: cucumber, complicated background, quality detection, image processing, GrabCut DOI: 10.25165/j.ijabe.20181104.3090Citation: Ye H J, Liu C Q, Niu P Y. Cucumber appearance quality detection under complex background based on image processing. Int J Agric & Biol Eng, 2018; 11(4): 193-199.

Recognition of fruits and vegetables with similar‐color background in natural environment: A survey

“…Other segmentation methods based on the specific theories for image segmentation of fruits and vegetables with similar‐color backgrounds include the Rough set (Cucumber, Yang, et al, 2007), Adaboost (Litchi, He, et al, 2017), Chan–Vese (C–V) level set (Grape, Xiong, Liu, et al, 2018), and GrabCut (Cucumber, Ye, et al, 2018). Generally, the image segmentation methods based on specific theories have higher adaptability to complex plantation environments than other methods.…”

“…Ye et al (2018) adopted the pixel size normalization, rectangular box set, scale image resolution, and pretreatments of cucumber image to reduce the iteration times and operation time of the segmentation algorithm. Safren et al (2007) implemented the normalization and dimensionality reduction before image segmentation in the hyperspectral apples.…”

Métodos y proyectos transdigitales

“…La implementación del análisis de imágenes para la innovación en el seguimiento de la calidad de productos elaborados por microempresas es altamente eficiente y objetivo, ya que, puede medir diferentes factores físicos como el color, el tamaño, parámetros de forma, textura, etc., que se consideran características determinantes en la calidad de los productos alimenticios (Blasco et al, 2020;Ye et al, 2018). La innovación tanto en productos como en procesos, apoyada en el acceso a la tecnología y la reducción de costos es considerada como prioridad para incrementar la calidad en la micro, pequeñas y medianas empresas (Saavedra et al, 2017).…”

Method for segmentation of overlapping fish images in aquaculture

“…Several approaches have been developed to detect overlapping targets in gray-level images, and the main research focuses can be classified into the following categories: 1) morphological methods. The basic operations include expansion, corrosion (or erosion), opening and closing, and the image data were simplified to preserve the essential features [17][18][19] . 2) edge detection and concave matching.…”