Dataset Information

Identification of cichlid fishes from Lake Malawi using computer vision.

ABSTRACT:

Background

The explosively radiating evolution of cichlid fishes of Lake Malawi has yielded an amazing number of haplochromine species estimated as many as 500 to 800 with a surprising degree of diversity not only in color and stripe pattern but also in the shape of jaw and body among them. As these morphological diversities have been a central subject of adaptive speciation and taxonomic classification, such high diversity could serve as a foundation for automation of species identification of cichlids.

Methodology/principal finding

Here we demonstrate a method for automatic classification of the Lake Malawi cichlids based on computer vision and geometric morphometrics. For this end we developed a pipeline that integrates multiple image processing tools to automatically extract informative features of color and stripe patterns from a large set of photographic images of wild cichlids. The extracted information was evaluated by statistical classifiers Support Vector Machine and Random Forests. Both classifiers performed better when body shape information was added to the feature of color and stripe. Besides the coloration and stripe pattern, body shape variables boosted the accuracy of classification by about 10%. The programs were able to classify 594 live cichlid individuals belonging to 12 different classes (species and sexes) with an average accuracy of 78%, contrasting to a mere 42% success rate by human eyes. The variables that contributed most to the accuracy were body height and the hue of the most frequent color.

Conclusions

Computer vision showed a notable performance in extracting information from the color and stripe patterns of Lake Malawi cichlids although the information was not enough for errorless species identification. Our results indicate that there appears an unavoidable difficulty in automatic species identification of cichlid fishes, which may arise from short divergence times and gene flow between closely related species.

SUBMITTER: Joo D

PROVIDER: S-EPMC3808401 | biostudies-literature | 2013

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identification of cichlid fishes from Lake Malawi using computer vision.

Joo Deokjin D Kwan Ye-seul YS Song Jongwoo J Pinho Catarina C Hey Jody J Won Yong-Jin YJ

PloS one 20131025 10

<h4>Background</h4>The explosively radiating evolution of cichlid fishes of Lake Malawi has yielded an amazing number of haplochromine species estimated as many as 500 to 800 with a surprising degree of diversity not only in color and stripe pattern but also in the shape of jaw and body among them. As these morphological diversities have been a central subject of adaptive speciation and taxonomic classification, such high diversity could serve as a foundation for automation of species identifica ...[more]

PMID: 24204918

Similar Datasets

Project description:Morphological differentiation among closely related species provides opportunities to study mechanisms shaping natural phenotypic variation. Here, we address variation in the orientation of melanin-colored body stripes in three cichlid species of the tribe Haplochromini. Melanochromis auratus displays a common pattern of dark, straight horizontal body stripes, whereas in Aristochromis christyi and Buccochromis rhoadesii, oblique stripes extend from the anterior dorsal to the posterior mid-lateral trunk. We first validated a stably reference gene, and then, investigated the chromatophore distribution in the skin by assessing the expression levels of the iridophore and melanophore marker genes, ltk and slc24a5, respectively, as well as pmel, a melanophore pigmentation marker gene. We found anterior-posterior differences in the expression levels of the three genes in the oblique-striped species. The higher anterior expression of ltk, indicates increased iridophore density in the anterior region, i.e., uneven horizontal distribution of iridophores, which coincides with the anterior dorsalization of melanophore stripe in these species. The obliqueness of the horizontal body stripes might be a result of distinct migratory or patterning abilities of melanophores in anterior and posterior stripe regions which could be reflected by variation in the expression of genes involved in melanophore patterning. To address this, we investigated anterior-posterior expression levels of a primary set of candidate target genes with known functions in melanophore migration and stripe patterning in the adult zebrafish, and their related gene regulatory network. Among these genes, those with differences in anterior-posterior expression showed only species-specific differential expression, e.g., sdf1a, col14a1a, ifitm5, and agpat3, with the exception of fbxw4/hagoromo (differentially expressed in an oblique-and the straight-striped species). In summary, distinct anterior-posterior gradients in iridophore density found to be more similar characteristic between the two oblique-striped species. Furthermore, the species-specific differential expression of genes involved in stripe patterning might also implicate distinct molecular processes underlying the obliqueness of body stripe in two closely related cichlid species.

Dataset Information

Identification of cichlid fishes from Lake Malawi using computer vision.

Background

Methodology/principal finding

Conclusions

Publications

Identification of cichlid fishes from Lake Malawi using computer vision.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets