Deep Learning based Corn Kernel Classification

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

doi:10.1109/cvprw50498.2020.00041

Cited by 25 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As deep learning approaches have shown superior performance across numerous machine vision tasks in multiple domains, they have been increasingly adopted for kernel counting tasks as well. Velesaca et al ( 2020 ) used Mask R-CNN to segment individual corn kernels as well as to classify them as good, impure, or defective. This analysis was done on loose, not on-ear, kernels with a highly uniform background.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels

Hobbs

Khachatryan²,

Anandan

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

Crop monitoring and yield prediction are central to management decisions for farmers. One key task is counting the number of kernels on an ear of corn to estimate yield in a field. As ears of corn can easily have 400–900 kernels, manual counting is unrealistic; traditionally, growers have approximated the number of kernels on an ear of corn through a mixture of counting and estimation. With the success of deep learning, these human estimates can now be replaced with more accurate machine learning models, many of which are efficient enough to run on a mobile device. Although a conceptually simple task, the counting and localization of hundreds of instances in an image is challenging for many image detection algorithms which struggle when objects are small in size and large in number. We compare different detection-based frameworks, Faster R-CNN, YOLO, and density-estimation approaches for on-ear corn kernel counting and localization. In addition to the YOLOv5 model which is accurate and edge-deployable, our density-estimation approach produces high-quality results, is lightweight enough for edge deployment, and maintains its computational efficiency independent of the number of kernels in the image. Additionally, we seek to standardize and broaden this line of work through the release of a challenging dataset with high-quality, multi-class segmentation masks. This dataset firstly enables quantitative comparison of approaches within the kernel counting application space and secondly promotes further research in transfer learning and domain adaptation, large count segmentation methods, and edge deployment methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Corn kernel counting is not a new task for computational agriculture (Velesaca et al, 2020 ; Wu et al, 2020 ). However, past analyses have been done on proprietary datasets which prevents comparison across approaches.…”

Section: Introductionmentioning

confidence: 99%

Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels

Hobbs

Khachatryan²,

Anandan

et al. 2021

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…Plant health monitoring approaches are addressed, including weed, insect, and disease detection [3]. With the success of DNNs, different approaches have been proposed to tackle problems of corn seed classification [12,10,11]. Fine-grained objects (seeds) are visually similar by a rough glimpse, and details can correctly recognize them in discriminative local regions.…”

Section: Related Workmentioning

confidence: 99%

“…With the advent of Deep Neural Networks (DNNs), data-driven models have become increasingly adept at image classification/detection tasks. DNN models have been used in literature for seed quality testing problems [10,11,12]. However, there are some significant impediments to their widespread adoption.…”

Section: Introductionmentioning

confidence: 99%

Automated Seed Quality Testing System using GAN & Active Learning

Nagar¹,

Pani²,

Nair³

et al. 2021

Preprint

View full text Add to dashboard Cite

Quality assessment of agricultural produce is a crucial step in minimizing food stock wastage. However, this is currently done manually and often requires expert supervision, especially in smaller seeds like corn. We propose a novel computer vision-based system for automating this process. We build a novel seed image acquisition setup, which captures both the top and bottom views. Dataset collection for this problem has challenges of data annotation costs/time and class imbalance. We address these challenges by i.) using a Conditional Generative Adversarial Network (CGAN) to generate real-looking images for the classes with lesser images and ii.) annotate a large dataset with minimal expert human intervention by using a Batch Active Learning (BAL) based annotation tool. We benchmark different image classification models on the dataset obtained. We are able to get accuracies of up to 91.6% for testing the physical purity of seed samples.

show abstract

“…Berdasarkan hasil pengujian, metode ini mampu memberikan jumlah dari biji jagung dalam berbagai arah. Pengklasifikasian biji jagung dengan menggunakan deep learning dilakukan oleh [10] dengan menggunakan arsitektur Mask R-CNN untuk mendeteksi jagung bagus, rusak dan tidak murni. Data set yang digunakan merupakan data dari jagung yang tidak terkena sentuhan dan digunakan sebagai segmentasi training dan klasifikasi.…”

unclassified

Penerapan Convolutional Neural Network Deep Learning dalam Pendeteksian Citra Biji Jagung Kering

TiaraSari

Haryatmi

2021

RESTI

View full text Add to dashboard Cite

Corn kernels detection can be implemented in industry area. This can be implemented in the selection and packaging the corn kernels before it is distributed. This technique can be implemented in the selection and packaging machine to detect corn kernels accurately. Corn kernel images was used before it is implemented in real-time. The objective of this research was corn kernel detection using Convolutional Neural Network (CNN) deep learning. This technique consists of 3 main stages, the first preprocessing or normalizing the input of corn kernels image data by wrapping and cropping, both modeling and training the system, and testing. The experiment used CNN method to classify images of dry corn kernels and to determine the accuracy value. This research used 20 dry corn kernels images as testing from 80 dry corn kernels images which used in training dataset. The accuracy of detection was dependent from the size of image and position when the image was taken. The accuracy is around 80% - 100% by using 7 convolutional layers and the average of accuracy for testing data was 0,90296. The convolutional layer which implemented in CNN has the strength to detect features in the input image.

show abstract

Deep Learning based Corn Kernel Classification

Cited by 25 publications

References 17 publications

Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels

Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels

Automated Seed Quality Testing System using GAN & Active Learning

Penerapan Convolutional Neural Network Deep Learning dalam Pendeteksian Citra Biji Jagung Kering

Contact Info

Product

Resources

About