How automated image analysis techniques help scientists in species identification and classification?

Kalafi, Elham Yousef; Town, Christopher; Dhillon, Sarinder Kaur

doi:10.5603/fm.a2017.0079

Cited by 11 publications

(3 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In parallel, newly emerging supporting technologies are becoming increasingly affordable and accessible. These include various omics‐based applications, microbiomics, metabarcoding (Pawlowski et al ., 2018), automated species identification technologies (Gorsky et al ., 2010; Le Bourg et al ., 2015; Kalafi, Town & Dillon, 2018; Wäldchen & Mäder, 2018, First et al ., 2021), in vitro technology (Rosner et al ., 2021), bioinformatics, big data processing techniques and increased computing power. Omics technologies will facilitate studies on non‐model organisms; in vitro technology will enable the simultaneous analysis of samples from many species using a large number of tests; while technologies like DNA barcoding (Weigand et al ., 2019; Paz & Rinkevich, 2021) and automated species identification will reduce reliance on professional taxonomists, facilitating the processing of large amounts of data originating from (eco)toxicological tests performed on a variety of aquatic species.…”

Section: Discussionmentioning

confidence: 99%

A broad‐taxa approach as an important concept in ecotoxicological studies and pollution monitoring

Rosner,

Ballarin,

Barnay‐Verdier

et al. 2023

Biological Reviews

View full text Add to dashboard Cite

Aquatic invertebrates play a pivotal role in (eco)toxicological assessments because they offer ethical, cost‐effective and repeatable testing options. Additionally, their significance in the food chain and their ability to represent diverse aquatic ecosystems make them valuable subjects for (eco)toxicological studies. To ensure consistency and comparability across studies, international (eco)toxicology guidelines have been used to establish standardised methods and protocols for data collection, analysis and interpretation. However, the current standardised protocols primarily focus on a limited number of aquatic invertebrate species, mainly from Arthropoda, Mollusca and Annelida. These protocols are suitable for basic toxicity screening, effectively assessing the immediate and severe effects of toxic substances on organisms. For more comprehensive and ecologically relevant assessments, particularly those addressing long‐term effects and ecosystem‐wide impacts, we recommended the use of a broader diversity of species, since the present choice of taxa exacerbates the limited scope of basic ecotoxicological studies.This review provides a comprehensive overview of (eco)toxicological studies, focusing on major aquatic invertebrate taxa and how they are used to assess the impact of chemicals in diverse aquatic environments. The present work supports the use of a broad‐taxa approach in basic environmental assessments, as it better represents the natural populations inhabiting various ecosystems. Advances in omics and other biochemical and computational techniques make the broad‐taxa approach more feasible, enabling mechanistic studies on non‐model organisms. By combining these approaches with in vitro techniques together with the broad‐taxa approach, researchers can gain insights into less‐explored impacts of pollution, such as changes in population diversity, the development of tolerance and transgenerational inheritance of pollution responses, the impact on organism phenotypic plasticity, biological invasion outcomes, social behaviour changes, metabolome changes, regeneration phenomena, disease susceptibility and tissue pathologies. This review also emphasises the need for harmonised data‐reporting standards and minimum annotation checklists to ensure that research results are findable, accessible, interoperable and reusable (FAIR), maximising the use and reusability of data. The ultimate goal is to encourage integrated and holistic problem‐focused collaboration between diverse scientific disciplines, international standardisation organisations and decision‐making bodies, with a focus on transdisciplinary knowledge co‐production for the One‐Health approach.

show abstract

Section: Discussionmentioning

confidence: 99%

A broad‐taxa approach as an important concept in ecotoxicological studies and pollution monitoring

Rosner,

Ballarin,

Barnay‐Verdier

et al. 2023

Biological Reviews

View full text Add to dashboard Cite

show abstract

“…Taxonomists' eagerness to reduce the time consumed for analysing samples (Benfield et al, 2007) and to significantly cut down the costs (Kalafi et al, 2018) were the main reasons that influenced the development of image-based identification systems. Culverhouse et al (2003) have shown that categorizing specimens from species that have significant variations in their morphology is difficult.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Fully Automated and Semi-Automated Methods for Species Identification

Kalafi,

Anuar,

Sakharkar

et al. 2018

Fol. Biol.

View full text Add to dashboard Cite

The process of manual species identification is a daunting task, so much so that the number of taxonomists is seen to be declining. In order to assist taxonomists, many methods and algorithms have been proposed to develop semi-automated and fully automated systems for species identification. While semi-automated tools would require manual intervention by a domain expert, fully automated tools are assumed to be not as reliable as manual or semiautomated identification tools. Hence, in this study we investigate the accuracy of fully automated and semi-automated models for species identification. We have built fully automated and semi-automated species classification models using the monogenean species image dataset. With respect to monogeneans’ morphology, they are differentiated based on the morphological characteristics of haptoral bars, anchors, marginal hooks and reproductive organs (male and female copulatory organs). Landmarks (in the semi-automated model) and shape morphometric features (in the fully automated model) were extracted from four monogenean species images, which were then classified using k-nearest neighbour and artificial neural network. In semi-automated models, a classification accuracy of 96.67 % was obtained using the k-nearest neighbour and 97.5 % using the artificial neural network, whereas in fully automated models, a classification accuracy of 90 % was obtained using the k-nearest neighbour and 98.8 % using the artificial neural network. As for the crossvalidation, semi-automated models performed at 91.2 %, whereas fully automated models performed slightly higher at 93.75 %.

show abstract

“…With such obvious problems and various difficulties faced by researchers with manual identifications, automated identification systems seem to offer a possible solution. The idea of automated identification is not novel since it has been developed in various biological organisms previously (Abu et al 2013a(Abu et al , 2013bLeow et al 2015;Kalafi et al 2016;Morwenna et al 2016;Salimi et al 2016;Wong et al 2016;Kalafi et al 2017). Several classification methods such as neural network, structural, fuzzy and transform-based techniques have been used in biological image identification systems.…”

Section: Introductionmentioning

confidence: 99%

Automated plant identification using artificial neural network and support vector machine

Kho

Manickam

Malek

et al. 2017

Frontiers in Life Science

View full text Add to dashboard Cite

Ficus is one of the largest genera in plant kingdom reaching to about 1000 species worldwide. While taxonomic keys are available for identifying most species of Ficus, it is very difficult and time consuming for interpretation by a nonprofessional thus requires highly trained taxonomists. The purpose of the current study is to develop an efficient baseline automated system, using image processing with pattern recognition approach, to identify three species of Ficus, which have similar leaf morphology. Leaf images from three different Ficus species namely F. benjamina, F. pellucidopunctata and F. sumatrana were selected. A total of 54 leaf image samples were used in this study. Three main steps that are image pre-processing, feature extraction and recognition were carried out to develop the proposed system. Artificial neural network (ANN) and support vector machine (SVM) were the implemented recognition models. Evaluation results showed the ability of the proposed system to recognize leaf images with an accuracy of 83.3%. However, the ANN model performed slightly better using the AUC evaluation criteria. The system developed in the current study is able to classify the selected Ficus species with acceptable accuracy. ARTICLE HISTORY

show abstract

How automated image analysis techniques help scientists in species identification and classification?

Cited by 11 publications

References 80 publications

A broad‐taxa approach as an important concept in ecotoxicological studies and pollution monitoring

A broad‐taxa approach as an important concept in ecotoxicological studies and pollution monitoring

Comparison of Fully Automated and Semi-Automated Methods for Species Identification

Automated plant identification using artificial neural network and support vector machine

Contact Info

Product

Resources

About