Dataset Information

Plant species classification using flower images-A comparative study of local feature representations.

ABSTRACT: Steady improvements of image description methods induced a growing interest in image-based plant species classification, a task vital to the study of biodiversity and ecological sensitivity. Various techniques have been proposed for general object classification over the past years and several of them have already been studied for plant species classification. However, results of these studies are selective in the evaluated steps of a classification pipeline, in the utilized datasets for evaluation, and in the compared baseline methods. No study is available that evaluates the main competing methods for building an image representation on the same datasets allowing for generalized findings regarding flower-based plant species classification. The aim of this paper is to comparatively evaluate methods, method combinations, and their parameters towards classification accuracy. The investigated methods span from detection, extraction, fusion, pooling, to encoding of local features for quantifying shape and color information of flower images. We selected the flower image datasets Oxford Flower 17 and Oxford Flower 102 as well as our own Jena Flower 30 dataset for our experiments. Findings show large differences among the various studied techniques and that their wisely chosen orchestration allows for high accuracies in species classification. We further found that true local feature detectors in combination with advanced encoding methods yield higher classification results at lower computational costs compared to commonly used dense sampling and spatial pooling methods. Color was found to be an indispensable feature for high classification results, especially while preserving spatial correspondence to gray-level features. In result, our study provides a comprehensive overview of competing techniques and the implications of their main parameters for flower-based plant species classification.

SUBMITTER: Seeland M

PROVIDER: S-EPMC5325198 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Plant species classification using flower images-A comparative study of local feature representations.

Seeland Marco M Rzanny Michael M Alaqraa Nedal N Wäldchen Jana J Mäder Patrick P

PloS one 20170224 2

Steady improvements of image description methods induced a growing interest in image-based plant species classification, a task vital to the study of biodiversity and ecological sensitivity. Various techniques have been proposed for general object classification over the past years and several of them have already been studied for plant species classification. However, results of these studies are selective in the evaluated steps of a classification pipeline, in the utilized datasets for evaluat ...[more]

PMID: 28234999

Similar Datasets

Project description:Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Project description:BackgroundPlant growth, reproduction and yields are severely damaged under adverse environmental stresses. These stresses can be either biotic or abiotic, and many stress related proteins are expressed in response to these stresses. Among these proteins dehydrins are reported to have a role primarily in the abiotic stresses. Dehydrins are very diverse proteins and a uniform annotation system is needed for their functional characterization in the future research.ObjectivesThe aim of the present work is to identify, classify and analyze the expression of dehydrin proteins under different biotic and abiotic stresses in the selected plant species by using different computational tools.Materials and methodsProsite database is used for dehydrin proteins identification, and to conform the location of conserved motifs in selected plant species. The dehydrins extracted from uniprot database were annotated, based on the ensemble plant gene id. Subcellular localization was predicted using PSI predictor tool. Dehydrin expression analyses were retrieved form the genevestigator tool.ResultsDehydrins were annotated on the basis of dehydrin gene locus and conserved motifs available in different domain databases. Dehydrins were identified and annotated in Arabidopsis thaliana (13), Glycine max (12), Zea mays (05), Oryza sativa (11), Solanum tuberosum (05), Solanum lycopersicum (06), Triticum aestivum (32) and Vitis vinifera (06). It has been proposed that dehydrins are located primarily in cytosol and nucleus. Based on genevestigater expression analyses the plant species selected for this study contain all the classes of dehydrins, namely YnSKn, Kn, SKn, and YnKn; except class KnS.ConclusionsDehydrins are diverse proteins and a uniform classification is introduced for their better characterization. The distribution of dehydrins in different tissues and developmental stages suggest an important function throughout plant growth cycle. It has also been concluded that dehydrins expressed particularly in drought, cold and salt stresses, and may have limited role in heat, anoxia, heavy-metal and biotic stresses as well.

Dataset Information

Plant species classification using flower images-A comparative study of local feature representations.

Publications

Plant species classification using flower images-A comparative study of local feature representations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets