Computer vision based food grain classification: A comprehensive survey

Velesaca, Henry O.; Suárez, Patricia L.; Mira, Raúl; Sappa, Ángel D.

doi:10.1016/j.compag.2021.106287

Cited by 49 publications

(23 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cropping is a technique that splits a given image into small regions to obtain a more easily processed image representation. This splitting process allows unwanted parts of the images to be removed, leaving only the object of intere st [18]. In this work, the image is cropped to 240x240 pixels to remove the unwanted parts that appear in the image and influence the extraction process like threshold, contour drawing, and color detection.…”

Section: Croppingmentioning

confidence: 99%

Smart Robot Vision for a Pick and Place Robotic System

Mohammed¹,

AL-Khafaji²,

Abbas³

2023

ETJ

View full text Add to dashboard Cite

The movement of the 5 DOF robotic arm was controlled through the geometric approach in inverse kinematics analysis  HSV color space, a series of filters (M edian, Bilateral, and Gaussian), and the drawcontour method to discover objects' colors, shapes, and centroid were implemented.  The shapes and colors of the objects in different lighting conditions ranging from 5 to 7000 lux with an accuracy of 93.83% were discovered.The main contribution of this paper is to develop an innovative algorithm to accurately detect and identify the shape and color of objects under various light intensities and find their location to be manipulated by a pick-and-place robotic arm. Workpieces of various shapes and colors are dispersed on the robot's work plane and manipulated according to its specifications. The proposed algorithm utilizes the HSV color model to distinguish between different object colors and shapes. The S channel is used to detect the shapes of objects. After that, a series of filters (M edian, Bilateral, and Gaussian) are applied to reduce the noise of the segmented image to make the process of discovering the shap e and coordinates of the objects successful. The draw-contour method is used to discover the object's shapes. After the shape of the object is discovered, the centroid coordinates are calculated. After extensive testing on 354 images that are captured in various lighting conditions in the range of (5-7000 lux), the overall system performance of 93.83% is achieved, and the average execution time is 2.21s. Finally, we had a dependable flexible automatic pick and place system that could correctly detect and identify the objects based on their features.

show abstract

Section: Croppingmentioning

confidence: 99%

Smart Robot Vision for a Pick and Place Robotic System

Mohammed¹,

AL-Khafaji²,

Abbas³

2023

ETJ

View full text Add to dashboard Cite

show abstract

“…Research on automatic food grains classification has been active [8]. Several studies have developed machine vision systems for class and variety identification of grains.…”

Section: Related Workmentioning

confidence: 99%

Product Based Classification of Bulk Food Grains using Bag of Visual Words and Deep Features

Ali¹,

Mohammed²,

Nour³

2021

Kafrelsheikh Journal of Information Sciences

View full text Add to dashboard Cite

The goal of this research is to compare between the performance of the traditional machine learning classification algorithm using Bag of Visual Words (BoVW) method and off-the-shelf deep features extracted by VGG-19, and Inception-V3 models and trained SVMs using the extracted features. By comparing the AUC, sensitivity, and specificity of SVM with VGG-19 and Inception-V3, we can conclude that off-the-shelf deep features has an important impact on food grains image classification.

show abstract

“…The innovation of image pattern recognition methods promotes the development of computer vision technology [ 19 , 20 ]. The development of image pattern recognition technology has undergone a transformation from conventional machine learning methods to CNN methods [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Sun

Zhang

Tong

et al. 2022

Foods

View full text Add to dashboard Cite

This study aims to develop a high-speed and nondestructive mildewed rice grain detection method. First, a set of microscopic images of rice grains contaminated by Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea are acquired to serve as samples, and the mildewed regions are marked. Then, three YOLO-v5 models for identifying regions of rice grain with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in microscopic images are established. Finally, the relationship between the proportion of mildewed regions and the total number of colonies is analyzed. The results show that the proposed YOLO-v5 models achieve accuracy levels of 89.26%, 91.15%, and 90.19% when detecting mildewed regions with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in the microscopic images of the verification set. The proportion of the mildewed region area of rice grain with contamination of Aspergillus niger/Penicillium citrinum/Aspergillus cinerea is logarithmically correlated with the logarithm of the total number of colonies (TVC). The corresponding determination coefficients are 0.7466, 0.7587, and 0.8148, respectively. This study provides a reference for future research on high-speed mildewed rice grain detection methods based on MCV technology.

show abstract

Computer vision based food grain classification: A comprehensive survey

Cited by 49 publications

References 45 publications

Smart Robot Vision for a Pick and Place Robotic System

Smart Robot Vision for a Pick and Place Robotic System

Product Based Classification of Bulk Food Grains using Bag of Visual Words and Deep Features

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Contact Info

Product

Resources

About