A Method of Apple Image Segmentation Based on Color-Texture Fusion Feature and Machine Learning

Abstract

<jats:p>Apples are one of the most kind of important fruit in the world. China has been the largest apple producing country. Yield estimating, robot harvesting, precise spraying are important processes for precise planting apples. Image segmentation is an important step in machine vision systems for precision apple planting. In this paper, an apple fruit segmentation algorithm applied in the orchard was studied. The effect of many color features in classifying apple fruit pixels from other pixels was evaluated. Three color features were selected. This color features could effectively distinguish the apple fruit pixels from other pixels. The GLCM (Grey-Level Co-occurrence Matrix) was used to extract texture features. The best distance and orientation parameters for GLCM were found. Nine machine learning algorithms had been used to develop pixel classifiers. The classifier was trained with 100 pixels and tested with 100 pixels. The accuracy of the classifier based on Random Forest reached 0.94. One hundred images of an apple orchard were artificially labeled with apple fruit pixels and other pixels. At the same time, a classifier was used to segment these images. Regression analysis was performed on the results of artificial labeling and classifier classification. The average values of Af (segmentation error), FPR (false positive rate) and FNR (false negative rate) were 0.07, 0.13 and 0.15, respectively. This result showed that this algorithm could segment apple fruit in orchard images effectively. It could provide a reference for precise apple planting management.</jats:p>

YOLOF-Snake: An Efficient Segmentation Model for Green Object Fruit

“…In previous research on object fruit segmentation and recognition, traditional machine learning has played a pivotal role in driving the development of intelligent agriculture ( Jha et al, 2019 ; Sharma et al, 2020 ; Benos et al, 2021 ; Tahaseen and Moparthi, 2021 ). For example, Zhang et al (2020) proposed a segmentation method combining color and texture features, using grayscale co-occurrence matrix (GLCM) to extract texture features. The recognition accuracy of the new method reached 0.94, but the process is affected by illumination and is not effective in segmenting the fruit of the object under uneven illumination.…”

Potato crop stress identification in aerial images using deep learning‐based object detection

“…Image segmentation is the process of partitioning an image into multiple segments, by delineating the edges of the objects of interest and separating them from the background. In the context of PA, DL‐based approaches were implemented for segmentation of crop and weed (Champ et al., 2020; Dyrmann et al., 2016; Gao et al., 2020; Mortensen et al., 2016; Sa et al., 2017), fruits (Zhang et al., 2020), and seeds (Toda et al., 2020). Object detection is a related image analysis task, where the goal is to determine whether particular objects of interest (e.g., diseased or otherwise stressed plants) are present in an image, identify the locations of all present objects of interest in the image, and determine the category (i.e., healthy vs. stressed, or specific stress type) for all found objects.…”

Detecting the Early Flowering Stage of Tea Chrysanthemum Using the F-YOLO Model

“…Feature fusion aims to transform features into common subspaces in which they can be combined linearly or nonlinearly. The latest development of deep learning shows that a CNN can estimate any complex function [23][24][25][26]. Therefore, we built a separate fusion CNN to fuse different function modules.…”