Plant identification system using its leaf features

Pradeep, N.; Madhumathi, V. J.

doi:10.1109/icatcct.2015.7456906

Cited by 12 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, we have witnessed ample research on artificial intelligent-based automatic plant identification from plant images [24,61]. The leaf is an appropriate organ for this identification system as it has several distinct features, such as shape, vein, and texture [61,62]. Thus, leaf identification is critical in plant classification [63,62].…”

Section: Expert or Community Not At Allmentioning

confidence: 99%

“…The leaf is an appropriate organ for this identification system as it has several distinct features, such as shape, vein, and texture [61,62]. Thus, leaf identification is critical in plant classification [63,62]. [61] provided a thorough overview of image processing techniques for this automatic plant identification from the leaf along with some frequently used machine learning algorithms such as SVM, KNN, RF, K-Means, and Hypersphere classifiers.…”

Section: Expert or Community Not At Allmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Plant Disease Detection Mobile Applications: Quality and Limitations

Siddiqua¹,

Kabir²,

Tanzina³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this technologically advanced era, with the proliferation of artificial intelligence, many mobile apps are available for plant disease detection, diagnosis and treatment, each with a variety of features. These apps need to be categorized and reviewed following a proper framework that ensures their quality. This study aims to present an approach to evaluating plant disease detection mobile apps, this includes providing ratings of distinct features of the apps and insights into the exploitation of artificial intelligence used in plant disease detection. The applicability of these apps for pathogen or disease detection, identification, and treatment will be assessed along with significant insights garnered. For this purpose, plant disease detection apps were searched in three prominent app stores (the Google Play store, Apple App store, and Microsoft store) using a set of keywords. A total of 606 apps were found and from them 17 relevant apps were identified based on inclusion and exclusion criteria. The selected apps were reviewed by three raters using our devised app rating scale. To validate the raters' agreement on the ratings, inter-rater reliability is computed alongside their intra-rater reliability, ensuring their rating consistency. Also, the internal consistency of our rating scale was evaluated against all selected apps. User comments from the app stores are collected and analyzed to understand their expectations and views. Following the rating procedure, most apps earned acceptable ratings in software quality characteristics such as aesthetics, usability and performance, but gained poor ratings in AI-based advanced functionality, which is the key aspect of this study. However, most of the apps cannot be used as a complete solution to plant disease detection, diagnosis and treatment. Only one app, Plantix -your crop doctor, could successfully identify plants from images, detect diseases, maintain a rich plant database, and suggest potential treatment for the disease presented. It also provides a community where plant lovers can communicate with each other to gain additional benefits. In general, all existing apps need to improve functionalities, user experience, and software quality. Therefore, a set of design considerations has been proposed for future app improvements.

show abstract

Section: Expert or Community Not At Allmentioning

confidence: 99%

Section: Expert or Community Not At Allmentioning

confidence: 99%

Evaluating Plant Disease Detection Mobile Applications: Quality and Limitations

Siddiqua¹,

Kabir²,

Tanzina³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Plants are vital to life in general both for the environment and for humankind, and the global ecology cannot exist without plant life. Humans extensively use plants in many fields, including energy, industry, food, and also in medicine ( Türkoğlu & Hanbay, 2015 ; Nijalingappa & Madhumathi, 2016 ; Bertrand et al., 2018 ). According to the literature, there are approximately 500,000 known plant species worldwide.…”

Section: Introductionmentioning

confidence: 99%

“…However, at the same time generations of certain plant species are at risk of extinction due to adverse seasonal conditions and from the detrimental effects of environmental pollution. Therefore, studies related to the protection of plants and for plant recognition are of significant importance for the determination of new plant species and the protection of existing plant life ( Türkoğlu & Hanbay, 2015 ; Nijalingappa & Madhumathi, 2016 ; Türkoğlu et al, 2016 , Bertrand et al., 2018 ) and ( López-Jiménez et al, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

“…In conjunction with advances in computer technology, many studies have been undertaken in the area of object recognition. In this context, data previously examined by individuals can now be made easier, error-free and automated without wasting time unnecessarily thanks to computer-based image processing techniques ( Türkoğlu & Hanbay, 2015 ; Nijalingappa & Madhumathi, 2016 ; Türkoğlu et al, 2016 ; Türkoğlu & Hanbay, 2019a ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A multi-division convolutional neural network-based plant identification system

Türkoğlu

Aslan

Arı

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Background Plants have an important place in the life of all living things. Today, there is a risk of extinction for many plant species due to climate change and its environmental impact. Therefore, researchers have conducted various studies with the aim of protecting the diversity of the planet’s plant life. Generally, research in this area is aimed at determining plant species and diseases, with works predominantly based on plant images. Advances in deep learning techniques have provided very successful results in this field, and have become widely used in research studies to identify plant species. Methods In this paper, a Multi-Division Convolutional Neural Network (MD-CNN)-based plant recognition system was developed in order to address an agricultural problem related to the classification of plant species. In the proposed system, we divide plant images into equal nxn-sized pieces, and then deep features are extracted for each piece using a Convolutional Neural Network (CNN). For each part of the obtained deep features, effective features are selected using the Principal Component Analysis (PCA) algorithm. Finally, the obtained effective features are combined and classification conducted using the Support Vector Machine (SVM) method. Results In order to test the performance of the proposed deep-based system, eight different plant datasets were used: Flavia, Swedish, ICL, Foliage, Folio, Flower17, Flower102, and LeafSnap. According to the results of these experimental studies, 100% accuracy scores were achieved for the Flavia, Swedish, and Folio datasets, whilst the ICL, Foliage, Flower17, Flower102, and LeafSnap datasets achieved results of 99.77%, 99.93%, 97.87%, 98.03%, and 94.38%, respectively.

show abstract