From species to cultivar: Soybean cultivar recognition using joint leaf image patterns by multiscale sliding chord matching

Wang, Bin; Gao, Yongsheng; Yuan, Xiaohui; Xiong, Shengwu; Feng, Xianzhong

doi:10.1016/j.biosystemseng.2020.03.019

Cited by 32 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is mainly due to score-level fusion, which provides moderately rich information 48 while avoiding dimension explosion and complicated dimension reduction 49 , which are difficult challenges encountered when using small datasets. The high accuracy of the multigrowth-period score fusion method proved that leaves from different growth periods of the same cultivar render complementary information for cultivar classification 38 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

et al. 2021

Self Cite

View full text Add to dashboard Cite

Recognizing plant cultivars reliably and efficiently can benefit plant breeders in terms of property rights protection and innovation of germplasm resources. Although leaf image-based methods have been widely adopted in plant species identification, they seldom have been applied in cultivar identification due to the high similarity of leaves among cultivars. Here, we propose an automatic leaf image-based cultivar identification pipeline called MFCIS (Multi-feature Combined Cultivar Identification System), which combines multiple leaf morphological features collected by persistent homology and a convolutional neural network (CNN). Persistent homology, a multiscale and robust method, was employed to extract the topological signatures of leaf shape, texture, and venation details. A CNN-based algorithm, the Xception network, was fine-tuned for extracting high-level leaf image features. For fruit species, we benchmarked the MFCIS pipeline on a sweet cherry (Prunus avium L.) leaf dataset with >5000 leaf images from 88 varieties or unreleased selections and achieved a mean accuracy of 83.52%. For annual crop species, we applied the MFCIS pipeline to a soybean (Glycine max L. Merr.) leaf dataset with 5000 leaf images of 100 cultivars or elite breeding lines collected at five growth periods. The identification models for each growth period were trained independently, and their results were combined using a score-level fusion strategy. The classification accuracy after score-level fusion was 91.4%, which is much higher than the accuracy when utilizing each growth period independently or mixing all growth periods. To facilitate the adoption of the proposed pipelines, we constructed a user-friendly web service, which is freely available at http://www.mfcis.online.

show abstract

Section: Discussionmentioning

confidence: 99%

“…1a . Leaves from different growth periods of the same cultivar may provide different but complementary clues for cultivar classification 38 . Therefore, we adopted a score-level fusion method to combine the prediction results of each growth period.…”

Section: Methodsmentioning

confidence: 99%

MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…A recognition method based on Multiscale Sliding Chord Matching (MSCM) is presented in [34]. The method aims to recognize soybean cultivar by joint leaf patterns.…”

Section: Leaf Recognition and Classification Methodsmentioning

confidence: 99%

A Review on Classification Methods for Plants Leaves Recognition

Suwais¹,

Alheeti²,

Al_Dosary³

2022

IJACSA

View full text Add to dashboard Cite

Plants leaves recognition is an important scientific field that is concerned of recognizing leaves using image processing techniques. Several methods are presented using different algorithms to achieve the highest possible accuracy. This paper provides an analytical survey of various methods used in image processing for the recognition of plants through their leaves. These methods help in extracting useful information for botanists to utilize the medicinal properties of these leaves, or for any other agricultural and environmental purposes. We also provide insights and a complete review of different techniques used by researchers that consider different features and classifiers. These features and classifiers are studied in term of their capabilities in enhancing the accuracy ratios of the classification methods. Our analysis shows that both of the Support Victor Machines (SVM) and the Convolutional Neural Network (CNN) are positively dominant among other methods in term of accuracy.

show abstract

“…Hasil uji BNJ taraf 1% menunjukkan bahwa kultivar wangga menghasilkan nilai rata-rata produksi yang lebih rendah dibanding kultivar yang lain, sedangkan kultivar jahara menghasilkan nilai rata-rata produksi yang lebih tinggi namun tidak berbeda nyata dengan kultivar kalendeng dan dongan (Cui et al, 2020;Oculi et al, 2020;Wang et al, 2020).…”

Section: Hasil Dan Pembahasanunclassified

Daya Hasil Beberapa Kultivar Padi Gogo Lokal Asal Kabupaten Tojo Una-Una dan Sigi

et al. 2020

View full text Add to dashboard Cite

Pengembangan padi gogo merupakan salah satu alternatif untuk meningkatkan produksi padi nasional. Evaluasi daya hasil padi gogo lokal sangat penting untuk dilakukan mengingat padi gogo memiliki daya adaptasi yang berbeda-beda. Tujuan dari penelitian ini ialah untuk mengkaji dan mengetahui daya hasil padi gogo lokal asal Pipikoro dan Ampana yang ditanam di Tamarenja (Lembah Kalama) pada tahun pertama. Penelitiaan ini dilaksanakan di Desa Tamarenja (Lembah Kalama), dengan ketinggian tempat 180-250 Mdpl denganletaklintang LS 00o26’51.5” serta BT 119o49’50.6” Kecamatan Sindue, Kabupaten Donggala. Waktu penelitian dimulai dari bulan April sampai Oktober 2017. Penelitian ini disusun menggunakan Rancangan Acak Kelompok dengan 10 kultivar sebagai perlakuan genotip yaitu: kultivar jahara, kalendeng, pulu tau leru, uva buya, dongan, wangga, tako, delima, buncaili dan uva yang diulang sebanyak empat kali sehingga terdapat 40 unit percobaan. Peubah yang diamati meliputi: tinggi tanaman, panjang daun, jumlah anakan, jumlah akan produktif, panjang malai, umur panen, jumlah biji per malai, bobot 1000 biji dan produksi. Hasil penelitian menunjukkan bahwa kultivar Jahara dan Dongan menghasilkan daya hasil yang tinggi.

show abstract

From species to cultivar: Soybean cultivar recognition using joint leaf image patterns by multiscale sliding chord matching

Cited by 32 publications

References 44 publications

MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

MFCIS: an automatic leaf-based identification pipeline for plant cultivars using deep learning and persistent homology

A Review on Classification Methods for Plants Leaves Recognition

Daya Hasil Beberapa Kultivar Padi Gogo Lokal Asal Kabupaten Tojo Una-Una dan Sigi

Contact Info

Product

Resources

About