Species differentiation of slipper orchids using color image analysis

Sanz, Ernesto; Taubadel, Noreen von Cramon; Roberts, David L.

doi:10.15517/lank.v0i0.11743

Cited by 4 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the case of slipper orchids (Cypripedioideae), a popular horticultural group of orchids of which many species are highly endangered in the wild and in which illegal trade is soaring [5,12], more tools are needed to increase taxonomic identification to prevent species from going extinct. On-going advances in computer vision and machine learning have led to the development of numerous semi-and fully automated species identification systems.…”

Section: Introductionmentioning

confidence: 99%

“…On-going advances in computer vision and machine learning have led to the development of numerous semi-and fully automated species identification systems. Such systems have been successful in the identification of plant species [4][5][6], phytoplankton [7], diatom frustules [8], and insects [9,10], among others. However, these systems frequently rely on costly scientific imaging and analysis (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

OrchID: a Generalized Framework for Taxonomic Classification of Images Using Evolved Artificial Neural Networks

Pereira

Gravendeel

Wijntjes

et al. 2016

Preprint

View full text Add to dashboard Cite

Taxonomic expertise for the identification of species is rare and costly. On-going advances in computer vision and machine learning have led to the development of numerous semi-and fully automated species identification systems. However, these systems are rarely agnostic to specific morphology, rarely can perform taxonomic "approximation" (by which we mean partial identification at least to higher taxonomic level if not to species), and frequently rely on costly scientific imaging technologies. We present a generic, hierarchical identification system for automated taxonomic approximation of organisms from images. We assessed the effectiveness of this system using photographs of slipper orchids (Cypripedioideae), for which we implemented image pre-processing, segmentation, and colour and shape feature extraction algorithms to obtain digital phenotypes for 116 species. The identification system trained on these digital phenotypes uses a nested hierarchy of artificial neural networks for pattern recognition and automated classification that mirrors the Linnean taxonomy, such that user-submitted photos can be assigned a genus, section, and species classification by traversing this hierarchy. Performance of the identification system varied depending on photo quality, number of species included for training, and desired taxonomic level for identification. High quality photos were scarce for some taxa and were under-represented in the training set, resulting in imbalanced network training. The image features used for training were sufficient to reliably identify photos to the correct genus but less so to the correct section and species. The outcomes of this project include a library of feature extraction algorithms called ImgPheno, a collection of scripts for neural network training called

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

OrchID: a Generalized Framework for Taxonomic Classification of Images Using Evolved Artificial Neural Networks

Pereira

Gravendeel

Wijntjes

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

“…The system aims to be a tool in the quick identification of species especially taxa that form part of routine investigations [5]. A number of automated species recognition systems have been developed and many of these systems used geometric morphometric-based techniques [6,7,8,9,10]. Geometric morphometrics can either be a landmark-based analysis (using a set of landmarks to describe the object or specimen), or an outline-based analysis (using the margin of the specimen) [11].…”

mentioning

confidence: 99%

Outline Based Geometric Morphometric Analysis in Describing Shape Variation in Suckermouth Armoured Catfishes (Pterygoplichthys spp.): Basis for the Development of Automated Species Identification System

2014

International Conference on Agricultural, Ecological and Medical Sciences (AEMS-2014) Feb. 6-7, 2014 Bali (Indonesia)

View full text Add to dashboard Cite

The scientific community is facing taxonomic crisis. With still a huge number of species yet to be discovered, there is a great challenge to classify Earth's biodiversity. Computer-based automated species recognition has been suggested as a prospective technology to aid in the quick identification of species, especially taxa that form part of routine investigation. Most automated species recognition systems mainly used geometric morphometric-based techniques. The present study investigates whether suckermouth armoured catfishes (Pterygoplichthys spp.), locally known as janitor fish, can be differentiated based on the shape of its head, using outline based geometric morphometric analysis.The variation in shapes is further determined and described. Specifically, we look at Pterygoplichthys spp., being an invasive species in the Philippines, which may establish negative effects in the freshwater environments. A total of 150 closely connected points were made along the outline of the head using tpsDig 2. Relative warp scores generated were used for the analysis of shape variations. Relative warp analysis demonstrated variation in the outline of the head. The four significant relative warps jointly accounted for 87.34% and 80.51% of the variation in the dorsal view and lateral view, respectively. This suggests that shape could be a potential character for the differentiation of Pterygoplichthys species, which would serve as the basis for the development of an automated species identification system.

show abstract

Web image search revealed large‐scale variations in breeding season and nuptial coloration in a mutually ornamented fish, Tribolodon hakonensis

Atsumi

Koizumi

2017

Ecological Research

View full text Add to dashboard Cite

Geographic variations in reproductive traits are important for evolutionary biology, but often difficult to investigate because of the need for a large‐scale survey and the ephemeral nature of secondary sexual characteristics. Here, using web image searches (Google Images and Twitter), we revealed large‐scale geographic variations (>1500 km) in breeding timing and nuptial coloration in the mutually ornamented fish, Japanese dace (Tribolodon hakonensis). As this fish is easily caught and many anglers upload their photographs on the web, we were able to find a total of 401 high‐resolution photographs from all over Japan. Breeding periods were determined from dates of photographs with/without nuptial coloration, which matched with previous studies. We also found that breeding periods might have advanced three weeks over the last 80 years in the Chitose River, potentially because of climate change. Additionally, the pattern of latitudinal cline for breeding timing revealed delayed timing in higher latitudes, although regional variations were also high. Finally, we quantified the patterns of nuptial coloration for this mutually ornamented fish, and confirmed that over 80% of individuals showed typical colorations, but others showed rare phenotypes that were never previously described, including an intermediate coloration between T. hakonensis and a potentially hybridizing species, T. brandtii. Our web‐based method for estimating breeding phenology could be adopted for organisms with temporal sexual characteristics, such as plants (e.g., flowering time) and some fishes. Web image analyses are still preliminarily with many limitations, but could be promising for investigating variations in visible traits.

show abstract

Species differentiation of slipper orchids using color image analysis

Cited by 4 publications

References 5 publications

OrchID: a Generalized Framework for Taxonomic Classification of Images Using Evolved Artificial Neural Networks

OrchID: a Generalized Framework for Taxonomic Classification of Images Using Evolved Artificial Neural Networks

Outline Based Geometric Morphometric Analysis in Describing Shape Variation in Suckermouth Armoured Catfishes (Pterygoplichthys spp.): Basis for the Development of Automated Species Identification System

Web image search revealed large‐scale variations in breeding season and nuptial coloration in a mutually ornamented fish, Tribolodon hakonensis

Contact Info

Product

Resources

About