2020
DOI: 10.1080/10942912.2020.1778724
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning approach for the classification of corn seed using hybrid features

Abstract: Seed purity is an important indicator of crop seed quality. On the other side, corn is an important crop of the modern agricultural industry with more than 40% grain Worldwide production. The purpose of this study was to examine the feasibility of a machine learning (ML) approach for classifying different types of corn seeds. The seed digital images (DI) of six corn varieties were Desi Makkai, Sygenta ST-6142, Kashmiri Makkai, Pioneer P-1429, Neelam Makkai, and ICI 339. This was achieved through a digital came… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
23
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
3

Relationship

2
6

Authors

Journals

citations
Cited by 59 publications
(24 citation statements)
references
References 23 publications
0
23
0
1
Order By: Relevance
“…The classification models used in their study included random forest (RF), BayesNet (BN), LogitBoost (LB) and multilayer perceptron (MLP), along with optimised multi-feature using the (10-fold) cross-validation approach. Among these classifiers, MLP reported outstanding classification accuracy (98.93%) on ROIs size (150 × 150) [11].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…The classification models used in their study included random forest (RF), BayesNet (BN), LogitBoost (LB) and multilayer perceptron (MLP), along with optimised multi-feature using the (10-fold) cross-validation approach. Among these classifiers, MLP reported outstanding classification accuracy (98.93%) on ROIs size (150 × 150) [11].…”
Section: Related Workmentioning
confidence: 99%
“…In recent studies, machine learning techniques have been observed more frequently to perform seed classification of various crops, fruits and vegetables. Most of these studies have been conducted on a single genre of seed (e.g., weed seeds [3], cottonseeds [4], rice seeds [5,6], oat seeds [7], sunflower seeds [8], tomato seeds [9] and corn [10,11]) with varying purposes. These included observing germination and vigour detection, purification and growth stages.…”
Section: Introductionmentioning
confidence: 99%
“…There many ML based features selection approaches such as PCA technique provided excellent results on linearly separated dataset, also used in the selection of features [31]. The PCA method is an unsupervised approach [32], but the medicinal plant leaves varieties dataset is labeled, and the PCA results were not as promising on the labeled data. To solve this problem, ML based supervised feature selection techniques, namely, chi-square attribute evaluator with ranker search method [33] were used to select optimize features from the large FVS.…”
Section: Feature Selectionmentioning
confidence: 99%
“…During the last few decades, machine vision systems have inspired researchers to overcome these issues associated with human visual perception. [8] According to a literature survey, such methods have already been employed for crop classification, [8][9][10][11][12][13] land cover classification, and medical image analysis, [14][15][16] etc., successfully. Many researchers used machine vision approaches to classify different seed varieties, such as corn seeds are sorted out as damaged, healthy and defective kernels by Valiente-Gonzalez et al, with an accuracy of 90%.…”
Section: Literature Reviewmentioning
confidence: 99%
“…[26] Corn six varieties were correctly identified using the machine vision approaches and achieved 98.93% overall accuracy. [13] As reflected from the cited literature, most of the published research work mainly focuses on the classification of kernels, such as barley, oats, corn, maize, wheat, and similar using a large number of textures, morphological, and color features. As discussed above literature, a little work on the recognition and identification of canola varieties is cited in the literature.…”
Section: Literature Reviewmentioning
confidence: 99%