Automated species identification is a method of making the expertise of taxonomists available to ecologists, parataxonomists and others via digital technology and artificial intelligence. Today, most automated identification systems rely on images depicting the species for the identification.[1] Based on precisely identified images of a species, a classifier is trained. Once exposed to a sufficient amount of training data, this classifier can then identify the trained species on previously unseen images.
The automated identification of biological objects such as insects (individuals) and/or groups (e.g., species, guilds, characters) has been a dream among systematists for centuries. The goal of some of the first multivariatebiometric methods was to address the perennial problem of group discrimination and inter-group characterization. Despite much preliminary work in the 1950s and '60s, progress in designing and implementing practical systems for fully automated object biological identification has proven frustratingly slow. As recently as 2004 Dan Janzen[2] updated the dream for a new audience:
The spaceship lands. He steps out. He points it around. It says 'friendly–unfriendly—edible–poisonous—safe– dangerous—living–inanimate'. On the next sweep it says 'Quercus oleoides—Homo sapiens—Spondias mombin—Solanum nigrum—Crotalus durissus—Morpho peleides—serpentine'. This has been in my head since reading science fiction in ninth grade half a century ago.[clarification needed]
The species identification problem
DFE - the graphical interface of the Daisy system. The image is the wing of a biting midge Culicoides sp., some species of which are vectors of Bluetongue. Others may also be vectors of Schmallenberg virus an emerging disease of livestock, especially sheep. (Credit: Mark A. O'Neill)
Janzen's preferred solution to this classic problem involved building machines to identify species from their DNA. However, recent developments in computer architectures, as well as innovations in software design, have placed the tools needed to realize Janzen's vision in the hands of the systematics and computer science community not in several years hence, but now; and not just for creating DNA barcodes, but also for identification based on digital images.
A survey published in 2004,[3] studies why automated species identification had not become widely employed at this time and whether it would be a realistic option for the future. The authors found that "a small but growing number of studies sought to develop automated species identification systems based on morphological characters". An overview of 20 studies analyzing species' structures, such as cells, pollen, wings, and genitalia, shows identification success rates between 40% and 100% on training sets with 1 to 72 species. However, they also identified four fundamental problems with these systems: (1) training sets—were too small (5-10 specimens per species) and their extension especially for rare species may be difficult, (2) errors in identification—are not sufficiently studied to handle them and to find systematics, (3) scaling—studies consider only small numbers of species (<200 species), and (4) novel species — systems are restricted to the species they have been trained for and will classify any novel observation as one of the known species.
A survey published in 2017[4] systematically compares and discusses progress and findings towards automated plant species identification within the last decade (2005–2015). 120 primary studies have been published in high-quality venues within this time, mainly by authors with computer science background. These studies propose a wealth of computer vision approaches, i.e., features reducing the high-dimensionality of the pixel-based image data while preserving the characteristic information as well as classification methods. The vast majority of these studies analyzes leaves for identification, while only 13 studies propose methods for flower-based identification. The reasons being that leaves can easier be collected and imaged and are available for most of the year. Proposed features capture generic object characteristic, i.e., shape, texture, and color as well as leaf-specific characteristics, i.e., venation and margin. The majority of studies still used datasets for evaluation that contained no more than 250 species. However, there is progress in this regard, one study uses a dataset with >2k[5] and another with >20k[6]species.
A system developed in 2022[7] showed that automated identification achieves accuracy that is sufficiently high for being used in an automated insect surveillance system using electronic traps. By training classifiers on a few hundred images it correctly identified fruit-flies, and can be used for continuous monitoring aimed at detecting species invasion or pest outbreak. Several aspects contribute to the success of this system. Primarily, using e-traps provide a standardized setting, which means that even though they are deployed in different countries and regions, the visual variability, in terms of size view angle and illumination are controlled. This suggests that trap-based systems may be easier to develop than free-view systems for automatic pest identification.
There is a shortage of specialists who can identify the very biodiversity whose preservation has become a global concern. In commenting on this problem in palaeontology in 1993, Roger Kaesler[8] recognized:
"... we are running out of systematic palaeontologists who have anything approaching synoptic knowledge of a major group of organisms ... Palaeontologists of the next century are unlikely to have the luxury of dealing at length with taxonomic problems ... Palaeontology will have to sustain its level of excitement without the aid of systematists, who have contributed so much to its success."
This expertise deficiency cuts as deeply into those commercial industries that rely on accurate identifications (e.g., agriculture, biostratigraphy) as it does into a wide range of pure and applied research programmes (e.g., conservation, biological oceanography, climatology, ecology). It is also commonly, though informally, acknowledged that the technical, taxonomic literature of all organismal groups is littered with examples of inconsistent and incorrect identifications. This is due to a variety of factors, including taxonomists being insufficiently trained and skilled in making identifications (e.g., using different rules-of-thumb in recognizing the boundaries between similar groups), insufficiently detailed original group descriptions and/or illustrations, inadequate access to current monographs and well-curated collections and, of course, taxonomists having different opinions regarding group concepts. Peer review only weeds out the most obvious errors of commission or omission in this area, and then only when an author provides adequate representations (e.g., illustrations, recordings, and gene sequences) of the specimens in question.
Systematics too has much to gain from the further development and use of automated identification systems. In order to attract both personnel and resources, systematics must transform itself into a "large, coordinated, international scientific enterprise".[9] Many have identified use of the Internet— especially via the World Wide Web — as the medium through which this transformation can be made. While establishment of a virtual, GenBank-like system for accessing morphological data, audio clips, video files and so forth would be a significant step in the right direction, improved access to observational information and/or text-based descriptions alone will not address either the taxonomic impediment or low identification reproducibility issues successfully. Instead, the inevitable subjectivity associated with making critical decisions on the basis of qualitative criteria must be reduced or, at the very least, embedded within a more formally analytic context.
SDS protein gel images of sphinx moth caterpillars. It can be used in a similar way to DNA fingerprinting
Properly designed, flexible, and robust, automated identification systems, organized around distributed computing architectures and referenced to authoritatively identified collections of training set data (e.g., images, and gene sequences) can, in principle, provide all systematists with access to the electronic data archives and the necessary analytic tools to handle routine identifications of common taxa. Properly designed systems can also recognize when their algorithms cannot make a reliable identification and refer that image to a specialist (whose address can be accessed from another database). Such systems can also include elements of artificial intelligence and so improve their performance the more they are used. Once morphological (or molecular) models of a species have been developed and demonstrated to be accurate, these models can be queried to determine which aspects of the observed patterns of variation and variation limits are being used to achieve the identification, thus opening the way for the discovery of new and (potentially) more reliable taxonomic characters.
iNaturalist is a global citizen science project and social network of naturalists that incorporates both human and automatic identification of plants, animals, and other living creatures via browser or mobile apps.[10]
A multi-source model trained with expert-validated data and used by several European biodiversity portals for citizen scientist projects in different countries across Europe;
A model for analyzing images from insect camera DIOPSIS;
8 AI models for butterflies, cone snails, bird eggs, rays and sharks egg capsules, as well as masks from different cultures that are in the collections of 5 Dutch museums;
Sound recognition models.
Pl@ntNet is a global citizen science project which provides an app and a website for plant identification through photographs, based on machine-learning
Google Photos can automatically identify various species in photographs.[13]
Plant.id is a web application and API made by FlowerChecker company which uses a neural network trained on photos from FlowerChecker mobile app.[14][15]
See also
Multi-access key– type of identification key that lets users evaluate characteristics in a non-set orderPages displaying wikidata descriptions as a fallback
Here are some links to the home pages of species identification systems. The SPIDA and DAISY system are essentially generic and capable of classifying any image material presented. The ABIS and DrawWing system are restricted to insects with membranous wings as they operate by matching a specific set of characters based on wing venation.
Insect.id by Kindwise recognizes over 6,000 species including beetles, spiders, centipedes, butterflies, ants, bees and other insect-like animals
Mushroom id by Kindwise recognizes over 3,200 species including mushrooms, lichens and slime molds
Plant.id by Kindwise recognizes more than 33,000 taxa, including houseplants, garden plants, trees, weeds, fungi, and lichens; it also recognizes common plant diseases
Computer vision tasks include methods for acquiring, processing, analyzing and understanding digital images, and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context means the transformation of visual images into descriptions of the world that make sense to thought processes and can elicit appropriate action. This image understanding can be seen as the disentangling of symbolic information from image data using models constructed with the aid of geometry, physics, statistics, and learning theory.
Linnaean taxonomy can mean either of two related concepts:
The particular form of biological classification (taxonomy) set up by Carl Linnaeus, as set forth in his Systema Naturae (1735) and subsequent works. In the taxonomy of Linnaeus there are three kingdoms, divided into classes, and the classes divided into lower ranks in a hierarchical order.
A term for rank-based classification of organisms, in general. That is, taxonomy in the traditional sense of the word: rank-based scientific classification. This term is especially used as opposed to cladistic systematics, which groups organisms into clades. It is attributed to Linnaeus, although he neither invented the concept of ranked classification nor gave it its present form. In fact, it does not have an exact present form, as "Linnaean taxonomy" as such does not really exist: it is a collective (abstracting) term for what actually are several separate fields, which use similar approaches.
Natural language processing (NLP) is an interdisciplinary subfield of computer science and artificial intelligence. It is primarily concerned with providing computers with the ability to process data encoded in natural language and is thus closely related to information retrieval, knowledge representation and computational linguistics, a subfield of linguistics. Typically data is collected in text corpora, using either rule-based, statistical or neural-based approaches in machine learning and deep learning.
In biology, phenetics, also known as taximetrics, is an attempt to classify organisms based on overall similarity, usually with respect to morphology or other observable traits, regardless of their phylogeny or evolutionary relation. It is related closely to numerical taxonomy which is concerned with the use of numerical methods for taxonomic classification. Many people contributed to the development of phenetics, but the most influential were Peter Sneath and Robert R. Sokal. Their books are still primary references for this sub-discipline, although now out of print.
Systematics is the study of the diversification of living forms, both past and present, and the relationships among living things through time. Relationships are visualized as evolutionary trees. Phylogenies have two components: branching order and branch length. Phylogenetic trees of species and higher taxa are used to study the evolution of traits and the distribution of organisms (biogeography). Systematics, in other words, is used to understand the evolutionary history of life on Earth.
In biology, taxonomy is the scientific study of naming, defining (circumscribing) and classifying groups of biological organisms based on shared characteristics. Organisms are grouped into taxa and these groups are given a taxonomic rank; groups of a given rank can be aggregated to form a more inclusive group of higher rank, thus creating a taxonomic hierarchy. The principal ranks in modern use are domain, kingdom, phylum, class, order, family, genus, and species. The Swedish botanist Carl Linnaeus is regarded as the founder of the current system of taxonomy, as he developed a ranked system known as Linnaean taxonomy for categorizing organisms and binomial nomenclature for naming organisms.
Order is one of the eight major hierarchical taxonomic ranks in Linnaean taxonomy. It is classified between family and class. In biological classification, the order is a taxonomic rank used in the classification of organisms and recognized by the nomenclature codes. An immediately higher rank, superorder, is sometimes added directly above order, with suborder directly beneath order. An order can also be defined as a group of related families.
In biology, a taxon is a group of one or more populations of an organism or organisms seen by taxonomists to form a unit. Although neither is required, a taxon is usually known by a particular name and given a particular ranking, especially if and when it is accepted or becomes established. It is very common, however, for taxonomists to remain at odds over what belongs to a taxon and the criteria used for inclusion, especially in the context of rank-based ("Linnaean") nomenclature. If a taxon is given a formal scientific name, its use is then governed by one of the nomenclature codes specifying which scientific name is correct for a particular grouping.
When classification is performed by a computer, statistical methods are normally used to develop the algorithm.
The history of plant systematics—the biological classification of plants—stretches from the work of ancient Greek to modern evolutionary biologists. As a field of science, plant systematics came into being only slowly, early plant lore usually being treated as part of the study of medicine. Later, classification and description was driven by natural history and natural theology. Until the advent of the theory of evolution, nearly all classification was based on the scala naturae. The professionalization of botany in the 18th and 19th century marked a shift toward more holistic classification methods, eventually based on evolutionary relationships.
Sentiment analysis is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly.
Computer-aided detection (CADe), also called computer-aided diagnosis (CADx), are systems that assist doctors in the interpretation of medical images. Imaging techniques in X-ray, MRI, endoscopy, and ultrasound diagnostics yield a great deal of information that the radiologist or other medical professional has to analyze and evaluate comprehensively in a short time. CAD systems process digital images or videos for typical appearances and to highlight conspicuous sections, such as possible diseases, in order to offer input to support a decision taken by the professional.
In biology, determination is the process of matching a specimen of an organism to a known taxon, for example identifying a plant. The term is also used in cellular biology, where it means the act of the differentiation of stem cells becoming fixed. Various methods are used, for example single or multi-access identification keys.
Parataxonomy is a system of labor division for use in biodiversity research, in which the rough sorting tasks of specimen collection, field identification, documentation and preservation are conducted by primarily local, less specialized individuals, thereby alleviating the workload for the "alpha" or "master" taxonomist. Parataxonomy may be used to improve taxonomic efficiency by enabling more expert taxonomists to restrict their activity to the tasks that require their specialist knowledge and skills, which has the potential to expedite the rate at which new taxa may be described and existing taxa may be sorted and discussed. Parataxonomists generally work in the field, sorting collected samples into recognizable taxonomic units (RTUs) based on easily recognized features. The process can be used alone for rapid assessment of biodiversity.
Digital automated identification system (DAISY) is an automated species identification system optimised for the rapid screening of invertebrates by non-experts.
DNA barcoding is a method of species identification using a short section of DNA from a specific gene or genes. The premise of DNA barcoding is that by comparison with a reference library of such DNA sections, an individual sequence can be used to uniquely identify an organism to species, just as a supermarket scanner uses the familiar black stripes of the UPC barcode to identify an item in its stock against its reference database. These "barcodes" are sometimes used in an effort to identify unknown species or parts of an organism, simply to catalog as many taxa as possible, or to compare with traditional taxonomy in an effort to determine species boundaries.
An all-taxa biodiversity inventory, or ATBI, is an attempt to document and identify all biological species living in some defined area, usually a park, reserve, or research area. The term was coined in 1993, in connection with an effort initiated by ecologist Daniel Janzen to document the diversity of the Guanacaste National Park in Costa Rica.
Taxonomy is a practice and science concerned with classification or categorization. Typically, there are two parts to it: the development of an underlying scheme of classes and the allocation of things to the classes (classification).
The following outline is provided as an overview of and topical guide to natural-language processing:
FlowerChecker, also known as Kindwise, is a company that uses machine learning to identify natural objects from images. This includes plants and their diseases, but also insects and mushrooms. It is based in Brno, Czech Republic. It was founded in 2014 by Ondřej Veselý, Jiří Řihák, and Ondřej Vild, at the time Ph.D. students.
This page is based on this Wikipedia article Text is available under the CC BY-SA 4.0 license; additional terms may apply. Images, videos and audio are available under their respective licenses.
