Plant Identification

This article presents the participation of the ReVeS project to the ImageCLEF 2013 Plant Identification challenge. Our primary target being tree leaves, some extra effort had to be done this year to process images containing other plant organs. The proposed method tries to benefit from the presence of multiple sources of information for a same individual through the introduction of a late fusion system based on the decisions of classifiers for the different modalities. It also presents a way to incorporate the geographical information in the determination of the species by estimating their plausibility at the considered location. While maintaining its performance on leaf images (ranking 3rd on natural images and 4th on plain backgrounds) our team performed honorably on the brand new modalities with a 6th position.

This thesis identified and mapped the inhabiting grasses and vines found in Talim Island, Navotas, Cardona, Rizal. The research intended to provide basic information about the plants seen in the area of study. As an output of this study, a map which shows the distribution of the grasses and vines and a catalog which features the taxonomic classification, botanical descriptions, uses and geographic coordinates of identified plants in the locality were included.

The researchers conducted a botanical survey using the traditional method of identification of plant species; they utilized the global positioning system (GPS) to record the accurate geographic coordinates where the different species were found within trails. The gathered data were overlaid with digitalized map using the Auto Computer-Aided Design (AutoCAD) software application.

The research findings showed that there were 22 species identified found in barangay Navotas, Talim Island in the altitude range of 59 to 87 meters above sea level. 18 species of which were grasses and 4 were vines belonging to 6 families and 22 genera. The most commonly distributed grasses and vines were Bambusa spinosa Roxb (Kawayang-tinik), found in 14° 25' 12.5'' to 14° 24' 52.74" longitude and 121° 13' 26.9'' to 121° 13' 32" latitude, and Antigonon leptopus (Cadena de Amor), found in 14° 24' 40.82'' to 14° 24' 40.82'' longitude and 121° 13' 29.2" to 121° 13' 34.6" latitude, respectively.

Plant identification has been a challenging task for many researchers. Several researches proposed various techniques for plant identification based on leaves shape. However, image segmentation is an essential and critical part of analyzing the leaves images. This paper, proposed an efficient plant species identification model using the digital images of leaves. The proposed identification model adopts the particle swarm optimization for leaves images segmentation. Then, feature selection process using information gain and discritization process are applied to the segmented image's features. The proposed model was evaluated on the Flavia dataset. Experimental results on different kind of classifiers show an improvement in the identification accuracy up to 98.7%

Plants are the backbone of all life on Earth and an essential resource for human well-being. Plant recognition is very important in agriculture for the management of plant species whereas botanists can use this application for medicinal purposes. Leaf of different plants have different characteristics which can be used to classify them. This paper presents a simple and computationally efficient method for plant identification using digital image processing and machine vision technology. The proposed approach consists of three phases: pre-processing, feature extraction and classification. Pre-processing is the technique of enhancing data images prior to computational processing. The feature extraction phase derives features based on color and shape of the leaf image. These features are used as inputs to the classifier for efficient classification and the results were tested and compared using Artificial Neural Network (ANN) and Euclidean (KNN) classifier. The network was trained with 1907 sample leaves of 33 different plant species taken form Flavia dataset. The proposed approach is 93.3 percent accurate using ANN classifier and the comparison of classifiers shows that ANN takes less average time for execution than Euclidean distance method.

Identification of the correct medicinal plants that goes in to the preparation of a medicine is very important in ayurvedic, folk and herbal medicinal industry. The main features required to identify a medicinal plant is its leaf shape, color and texture. Color and texture from both sides of the leaf contain deterministic parameters to identify the species. In this project we explore feature vectors from both the front and back side of a green leaf along with morphological features to arrive at a unique optimum combination of features that maximizes the identification rate. A database of medicinal plant leaves is created from scanned images of front and back side of leaves of commonly used medicinal plants. The leaves are classified based on the shape and dimension combination. It is expected that for the automatic identification of medicinal plants this system will help the community people to develop their knowledge on medicinal plants, help taxonomists to develop more efficient species identification techniques and also participate significantly in the pharmaceutical drug manufacturing.

Overcoming‘plant blindness’ is a critical goal for society and especially for education.In this article, we suggest variation theory can be a useful approach to plant identification training and evaluation in higher education contexts. We discuss an example from Swedish higher education in which we reflect on our teaching. We propose that the conscious use of variation theory may be useful in developing pedagogical tools and processes in the teaching of plant identification.

Ett viktigt mål för samhället, särskilt för utbildningssystemen, är att vi människor blirbättre på att få syn på växter och på deras betydelse i ekosystemen. Vi behöver över-vinna vad som benämns‘växtblindhet’. I denna artikel föreslår vi att variationsteori ären bra utgångspunkt i utbildning och utvärdering av växtidentifiering inom högreutbildning. Vi redovisar exempel från svensk universitetsutbildning där vi reflekteraröver vår egen undervisning på ett systematiskt sätt. Vi föreslår att en avsiktlig utgångspunkt i variationsteorin för lärande är användbar för att vidareutvecklapedagogiska verktyg och processer i undervisning om växtidentifiering.

Content based image retrieval is one of the most challenging field in which widespread research is been carried out. In this paper, a modified and effective shape based leaf image retrieval system is presented for leaf identification. The method proposed is an extension of centroid distance method. The major drawbacks of the centroid distance approach are identified and resolved in our proposed approach. This approach, called Quad Centroid Distance Variation (QCDV) uses the concept of shape based image retrieval approach. Four values are computed and used as the feature vectors. The proposed approach effectively manages the size of the feature vectors, is computationally simple and affine invariant. Experiments were conducted on Swedish Leaf Image Database (SLID). The results justify the superior performance of the method even though the feature vector representing the image is very small.

La presente Guía de especies de flora y Fauna de la Ciénaga de La Virgen así como la cartilla ¿Cómo propagar 12 especies nativas del bosque seco tropical y del manglar en la Ciénaga de La Virgen?, son publicadas por el Jardín Botánico de Cartagena “Guillermo Piñeres” (JBGP) y la Agencia de Cooperación Alemana para el Desarrollo (GIZ), en el marco del programa estrategias de Adaptación basada en Ecosistemas (EbA). El programa EbA presta asistencia técnica a los gobiernos de Colombia y Ecuador buscando el cumplimiento de 4 metas específicas: 1) Adaptación basada en ecosistemas en la práctica, 2) Desarrollo de capacidades, 3) Transversalización y aplicación en mayor escala de la adaptación basada en los ecosistemas y 4) Comunicación y gestión de conocimientos. Esta guía cuenta con un registro fotográfico y descripciones taxonómicas de las especies presentes en la Ciénaga de la Vírgen.

It is complicated to distinguish among thousands of plant species in the natural ecosystem, and many efforts have been investigated to address the issue. In Vietnam, the task of identifying one from 12,000 species requires specialized experts in flora management, with thorough training skills and in-depth knowledge. Therefore, with the advance of machine learning, automatic plant identification systems have been proposed to benefit various stakeholders, including botanists, pharmaceutical laboratories, taxonomists, forestry services, and organizations. The concept has fueled an interest in research and application from global researchers and engineers in both fields of machine learning and computer vision. In this paper, the Vietnamese plant image dataset was collected from an online encyclopedia of Vietnamese organisms, together with the Encyclopedia of Life, to generate a total of 28,046 environmental images of 109 plant species in Vietnam. A comparative evaluation of four deep convolutional feature extraction models, which are MobileNetV2, VGG16, ResnetV2, and Inception Resnet V2, is presented. Those models have been tested on the Support Vector Machine (SVM) classifier to experiment with the purpose of plant image identification. The proposed models achieve promising recognition rates, and MobilenetV2 attained the highest with 83.9%. This result demonstrates that machine learning models are potential for plant species identification in the natural environment, and future works need to examine proposing higher accuracy systems on a larger dataset to meet the current application demand.

There are more than 391,000 plant species currently known to global science, and it is challenging to distinguish among them. The identification of plant species requires in-depth surveyors and botanists who possess a tremendous amount of knowledge on native plant species. Therefore, plant recognition has become an interdisciplinary concentration in both botanical taxonomy and machine learning for a faster identification process. In this paper, a convolutional neural network system has been proposed to perform feature extraction using different deep learning models in large-scale plant classification methods. The plant image dataset was collected from the PlantCLEF2003 dataset, which consists of 51,273 images from 609 plant species. Four deep convolutional feature extraction methods, including Resnet50V2, Inception Resnet V2, MobilenetV2, and VGG16, are used to extract features from the images. A comparative evaluation of four deep learning models using two classification methods, Support Vector Machine (SVN) and k-nearest neighbor (KNN), is presented. With the highest accuracy of 95.6%, MobilenetV2 performed better than the other deep learning models for plant recognition in both SVM and KNN classification methods. Moreover, the SVM classifier has outperformed the KNN in terms of accuracy in the plant image recognition system. The outcomes are promising for further applications and future work gears towards experiments on a larger dataset with high-performance computing facilities to propose a higher accuracy system of plant image identification in natural environments.

We propose an equation to evaluate the efficiency of a classification as a function of the effort required and the population size of data collectors. The formula postulates a "classification efficiency coefficient", which relates not only to the complexity of the object to be classified, but also to the data availability and representativeness. When applied to the classification of phytocoenoses, the equation suggests that a classification system based on vascular plants offers the best compromise between sampling effort, resolution power and data availability. We discuss the possibility of basing a vegetation classification on plot records for all macroscopic photoautotrophic organisms co-occurring in the vertical projection of a given ground area, as recently suggested by some authors. We argue that the inclusion of cryptogams in the description of phytocoenoses dominated by vascular plants should rely on a synusial approach, conceived as complementary to the traditional Braun-Blanquet approach.

This paper discusses the variety of recent digital media available for the identification and mapping of plants in cities in relation to the history of plant guides and maps. It raises the question: how has our focus on plants-especially their identification and mapping-evolved over the centuries and how might new digital media extend and/or limit our relationships with plants? The paper begins with an historical perspective on the processes of identifying and mapping plants and describes the development of plant books and their changing purposes within the general development of Western culture through a scientific lens. It touches on Theophrastus' Enquiry into Plants, Dioscorides' De Materia Medica, Linneaus' Systema Naturae, and Tansley's work in ecology. Next, the paper discusses the recent proliferation of locative media for identifying and mapping plants, which use face recognition software, crowd-sourcing, and location-based-services through GIS. These include Leafsnap for plant identification and i-Tree for ecological investigations of vegetation in cities. The paper concludes that in every era, human interests in plants and the media we've devised to investigate plants have been knit together. The 21 st century is no different and the new digital media will be of great use in addressing issues as complex as climate change and as basic as identifying fresh fruit in cities. Overall, the new media have the potential to deliver knowledge to people about plants that was formerly hard to get, which may lead to an increase in plant literacy, especially in cities.

In this paper, a plant identification approach using 2D digital leaves images is proposed. The approach made use of two methods of features extraction (one-dimensional (1D) and two-dimensional (2D) techniques) and the Bagging classifier. For the 1D-based method, PCA and LDA techniques were applied, while
2D-PCA and 2D-LDA algorithms were used for the 2D-based method. To classify the extracted features in both methods, the Bagging classifier, with the decision tree as a weak learner, was used. The proposed approach, with its four feature extraction techniques, was tested using Flavia dataset which consists of 1907 colored leaves images. The experimental results showed that the accuracy and the performance of our approach, with the 2D-PCA and 2D-LDA, was much better than using the PCA and LDA. Furthermore, it was proven that the 2D-LDA-based method gave the best plant identification accuracy and increasing the weak learners of the Bagging classifier leaded to a better accuracy. Also, a comparison with the most related work showed that our approach achieved better accuracy under the same dataset and same experimental setup.

Plants are natural resources that are abundant and all around us. As a conservation action, its use is needed, one of which is as medicine. Since long time ago, Indonesian people have used plants as a source of disease treatment or health care. Today, people still have various species of medicinal plants, including in urban housing. Plant species from various families, habitus, cultivation, and wild can be found. The existence of medicinal plants can be used by the community as an alternative to health. In the observation in the housing complex, various families of medicinal plants have been found that have various health benefits.

This research proposes MedLeaf as a new mobile application for medicinal plants identification based on leaf image. The application runs on the Android operating system. MedLeaf has two main functionalities, i.e. medicinal plants identification and document searching of medicinal plant. We used Local Binary Pattern to extract leaf texture and Probabilistic Neural Network to classify the image. In this research, we used 30 species of Indonesian medicinal plants and each species consists of 48 digital leaf images. To evaluate user satisfaction of the application we used questionnaire based on heuristic evaluation. The evaluation result shows that MedLeaf is promising for medicinal plants identification. MedLeaf will help botanical garden or natural reserve park management to identify medicinal plant, discover new plant species, plant taxonomy and so on. Also, it will help individual, groups and communities to find unused and undeveloped their skill to optimize the potential of medicinal plants. As the results, MedLeaf will increase of their resources, capitals, and economic wealth.

Background: Hundreds of herbarium collections have accumulated a valuable heritage and knowledge of plants over several centuries. Recent initiatives started ambitious preservation plans to digitize this information and make it available to botanists and the general public through web portals. However, thousands of sheets are still unidentified at the species level while numerous sheets should be reviewed and updated following more recent taxonomic knowledge. These annotations and revisions require an unrealistic amount of work for botanists to carry out in a reasonable time. Computer vision and machine learning approaches applied to herbarium sheets are promising but are still not well studied compared to automated species identification from leaf scans or pictures of plants in the field. Results: In this work, we propose to study and evaluate the accuracy with which herbarium images can be potentially exploited for species identification with deep learning technology. In addition, we propose to study if the combination of herbarium sheets with photos of plants in the field is relevant in terms of accuracy, and finally, we explore if herbarium images from one region that has one specific flora can be used to do transfer learning to another region with other species; for example, on a region under-represented in terms of collected data. Conclusions: This is, to our knowledge, the first study that uses deep learning to analyze a big dataset with thousands of species from herbaria. Results show the potential of Deep Learning on herbarium species identification, particularly by training and testing across different datasets from different herbaria. This could potentially lead to the creation of a semi, or even fully automated system to help taxonomists and experts with their annotation, classification, and revision works.

Content based image retrieval is one of the most challenging field in which widespread research is been carried out. In this paper, a modified and effective shape based leaf image retrieval system is presented for leaf identification. The method proposed is an extension of centroid distance method. The major drawbacks of the centroid distance approach are identified and resolved in our proposed approach. This approach, called Quad Centroid Distance Variation (QCDV) uses the concept of shape based image retrieval approach. Four values are computed and used as the feature vectors. The proposed approach effectively manages the size of the feature vectors, is computationally simple and affine invariant. Experiments were conducted on Swedish Leaf Image Database (SLID). The results justify the superior performance of the method even though the feature vector representing the image is very small.

Identification of plants is a very important field in the earth’s ecology to maintain a healthy atmosphere. Certain of these plants have significant medicinal properties. Nowadays of finding a plant is not easy by looking at its physical properties. This paper provides an academic database of literature between the duration of 2015–2020. It has been observed that the new generation of convolutionary neural networks (CNNs) in the space area of image recognition has produced remarkable performance. In this paper, techniques are discussed the concepts of Deep learning and different leaf recognition methods.

This research proposes MedLeaf as a new mobile application for medicinal plants identification based on leaf image. The application runs on the Android operating system. MedLeaf has two main functionalities, i.e. medicinal plants identification and document searching of medicinal plant. We used Local Binary Pattern to extract leaf texture and Probabilistic Neural Network to classify the image. In this research, we used 30 species of Indonesian medicinal plants and each species consists of 48 digital leaf images. To evaluate user satisfaction of the application we used questionnaire based on heuristic evaluation. The evaluation result shows that MedLeaf is promising for medicinal plants identification. MedLeaf will help botanical garden or natural reserve park management to identify medicinal plant, discover new plant species, plant taxonomy and so on. Also, it will help individual, groups and communities to find unused and undeveloped their skill to optimize the potential of medicinal plants. As the results, MedLeaf will increase of their resources, capitals, and economic wealth.

The number of species of macro organisms on the planet is estimated at about 10 million. This staggering diversity and the need to better understand it led inevitably to the development of classification schemes called biological taxonomies. Unfortunately, in addition to this enormous diversity, the traditional identification and classification workflows are both slow and error-prone; classification expertise is in the hands of a small number of expert taxonomists; and to make things worse, the number of taxonomists has steadily declined in recent years. Automated identification of organisms has therefore become not just a long time desire but a need to better understand, use, and save biodiversity. This paper presents a survey of recent efforts to use computer vision and machine learning techniques to identify organisms. It focuses on the use of leaf images to identify plant species. In addition, it presents the main technical and scientific challenges as well as the opportunities for herbaria and cybertaxonomists to take a quantum leap towards identifying biodiversity efficiently and empowering the general public by putting in their hands automated identification tools.

Frequently, the vineyards in the Douro Region present multiple grape varieties per parcel and even per row. An automatic algorithm for grape variety identification as an integrated software component was proposed that can be applied, for example, to a robotic harvesting system. However, some issues and constraints in its development were highlighted, namely, the images captured in natural environment, low volume of images, high similarity of the images among different grape varieties, leaf senescence, and significant changes on the grapevine leaf and bunch images in the harvest seasons, mainly due to adverse climatic conditions, diseases, and the presence of pesticides. In this paper, the performance of the transfer learning and fine-tuning techniques based on AlexNet architecture were evaluated when applied to the identification of grape varieties. Two natural vineyard image datasets were captured in different geographical locations and harvest seasons. To generate different datase...

Automatic plant identification tasks have witnessed increased interest from the machine learning community in recent years. This paper describes our (team IITK’s) participation in the Plant Identification Task, CLEF 2012, organized by the Combined Lab Evaluation Forum (CLEF) where the challenge was to identify plant species based on leaf images. We first categorize the different types of images and then use a variety of novel preprocessing methods such as shadow and background correction, petiole removal and automatic leaflet segmentation for identifying the leaf blobs. We next use complex network framework along with novel tooth detection method and morphological operations to compute several useful features. Finally, we use a random forest for classification. Based on the proposed approach, we achieved 2 rank on the overall score in the competition.

In this paper, a plant identification approach using 2D digital leaves images is proposed. The approach made use of two methods of features extraction (one-dimensional (1D) and two-dimensional (2D) techniques) and the Bagging classifier. For the 1D-based method, PCA and LDA techniques were applied, while 2D-PCA and 2D-LDA algorithms were used for the 2D-based method. To classify the extracted features in both methods, the Bagging classifier, with the decision tree as a weak learner, was used. The proposed approach, with its four feature extraction techniques, was tested using Flavia dataset which consists of 1907 colored leaves images. The experimental results showed that the accuracy and the performance of our approach, with the 2D-PCA and 2D-LDA, was much better than using the PCA and LDA. Furthermore, it was proven that the 2D-LDA-based method gave the best plant identification accuracy and increasing the weak learners of the Bagging classifier leaded to a better accuracy. Also, a comparison with the most related work showed that our approach achieved better accuracy under the same dataset and same experimental setup. Keywords Plant identification ⋅ Principal component analysis ⋅ Linear discriminant analysis ⋅ Bagging classifier ⋅ Decision tree ⋅ Weak learners ⋅ 2D-LDA ⋅ 2D-PCA ⋅ Leaf image ⋅ Leaves images Scientific Research Group in Egypt (SRGE) http://www.egyptscience.net.

AbstractStudents studying either animal or veterinary science at Charles Sturt University are required to be competent in recognising a range of plants that are potentially poisonous to domestic grazing animals. In 2013 these students used a newly developed application ‘Visual Learning – Agricultural Plants of the Riverina’ (VL-APR) for their poisonous plant recognition training. VL-APR has two main advantages over poisonous plant books or other computer-based applications. Firstly, an average of nine images per species is available, so a range of growth stages and variation in structure is shown. Secondly, multiple interactive quizzes and tests are available so students are actively engaged in the learning process. At the start of session the animal and veterinary science students obtained an average class mark (for recognition of 40 species) of 11.9%, with a wide range of individual student marks (0.0 to 40.0%). A class of first year agricultural science students was also tested and scored a similar ave...

Plant identification is vital for the management of plant species. An automated plant identification system is required for the characterization of plant species without requiring the expertise of botanists. This paper presents an efficient and computational model for plant species identification using digital images of leaves. The proposed identification system combines the leaf biometric features, where shape and venation features are used for leaf image classification. 10 combined biometric leaf features are extracted and passed to Hidden naaive bays classifiers to be categorized. Several experiments are conducted and demonstrated on 1907 sample leaves of 32 different plant species taken form Flavia dataset. Where, the proposed plant identification model shows consistently performances of 97% average identification accuracy.

Motivation students by providing personalized researches and using IT during classes is relevant in the frame of STEM approach of education. However, there is a lack of researches devoted to the justification of these approaches. The aim of the research is justifying of the choosing of AR-plant recognition application choosing to provide personalized during both, educational process at school and extracurricular activities. All apps were analyzed and characterized by all processes of interaction of the app with the user. In addition, social environments of the apps and their usage during extracurricular activities described. The didactics of usage of AR-recognition apps on biology classes have been described. To provide usability analysis, a survey of experts on digital education on installation simplicity, level of friendliness of the interface, and correctness of picture processing was conducted. To evaluate the rationality of usage, apps were analyzed on the accuracy of plants recognition of the "Dneprovskiy district of Kiev" list. It is proven that Google Lens is most recommended to use. Taking to account results of the analysis, as alternative Seek or Flora Incognita; however, these apps were characterized by lower accuracy.

The objective of this paper is to develop a computer aided system for leaf medicinal plant identification using Probabilistic Neural Network. In Indonesia only 20-22% of medicinal plants have been cultivated. Generally, identification process of medicinal plants has been done manually by a herbarium taxonomist using guidebook of taxonomy/dendrology. This system is designed to help taxonomist to identify leaf medicinal plant automatically using a computer-aided system. This system uses three features of leaf to identify the medicinal plant, i.e., morphology, shape, and texture. Leaf is used in this system for identification because easily to find. To classify medicinal plant we used Probabilistic Neural Network. The features will be combined using Product Decision Rule (PDR). The system was tested on 30 species medicinal plant from Garden of

The objective of this paper is to develop a computer aided system for leaf medicinal plant identification using Probabilistic Neural Network. In Indonesia only 20-22% of medicinal plants have been cultivated. Generally, identification process of medicinal plants has been done manually by a herbarium taxonomist using guidebook of taxonomy/dendrology. This system is designed to help taxonomist to identify leaf medicinal plant automatically using a computer-aided system. This system uses three features of leaf to identify the medicinal plant, i.e., morphology, shape, and texture. Leaf is used in this system for identification because easily to find. To classify medicinal plant we used Probabilistic Neural Network. The features will be combined using Product Decision Rule (PDR). The system was tested on 30 species medicinal plant from Garden Experiment results showed that the accuracy of medicinal plant identification using combination of leaf features increase until 74,67%. The comparative analysis of leaf features has been performed statistically. It showed that shape is a dominant features for plant identification. This system is very promising to help people identify medicinal plant automatically and for conservation and utilization of medicinal plants.

The Mesoamerican Ethnobotanical Database is a collaborative project between The Searle Herbarium of the Field Museum of Natural History and the Department of Anthropology at Northeastern Illinois University, with support from the National Science Foundation (Grant No. BCS-1321469).  Over 4000 images from 2522 vouchers represent 140 plant families in this database.  Searchable fields include scientific name, family, country, collector, collector number, common name, and use.  Additional images and data will be uploaded in by the end of 2015.