Assessment of ZooImage as a tool for the classification of zooplankton

Bell, Jenefer L.; Hopcroft, Russell R.

doi:10.1093/plankt/fbn092

Cited by 59 publications

(63 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In training sets with higher error, more images may be necessary to increase accuracy. In other plankton image analysis, a visually sorted training set with 200-300 images per category was recommended with 60% accuracy (Gorsky et al 2010), but in other analyses acceptable training sets have contained 100 images or less (Bell and Hopcroft 2008;Gislason and Silva 2009;Fernandes et al 2009). …”

Section: Thompson Et Almentioning

confidence: 99%

“…With all age classes included in a training set, CV accuracies were slightly lower at 92% to 96% of all species because images within each class are less homogenous (Thompson 2011). In other plankton imaging methods, copepods had different error rates between size classes and were found to be better classified if separated by size (Bell and Hopcroft 2008). Measuring error rates for genetic identification, visual sorting, and computer classification using hatchery-reared larvae…”

Section: Thompson Et Almentioning

confidence: 99%

“…About half of the field PCR samples only amplified at the 18S locus, and those reactions were re-amplified with only the 18S primers. Sequencing this 430 base-pair band provided an alternative means of identifying field larvae that were not targeted by multiplex CO1 primers, as 18S can be diagnostic for some bivalve families and genera (Bell and Grassle 1998). This step was not performed in the above test with the hatchery species but may have led to increased accuracy for that method by eliminating the false negatives resulting from no CO1 amplification (Table 2).…”

Section: Genetic Identification Of Field Larvaementioning

confidence: 99%

“…Studies have demonstrated the use of these methods for observations of real-time zooplankton distribution through quantitative high-resolution maps (Gallager et al 1996, Davis et al 2004, seasonal zooplankton abundance and biomass estimates from preserved net samples (Bell and Hopcroft 2008;Gorsky et al 2010), phytoplankton size and biomass (Sieracki et al 1998), and taxa-specific phytoplankton distributions (Sosik and Olson 2007). More recent studies have employed these techniques to address large-scale biological questions, such as zooplankton biomass and spatial distribution in the Bay of Biscay over an eight-year period ), spatial structure of zooplankton distribution in relation to oceanographic variables in an upwelling region in Chile (Manriquez et al 2009;Manriquez et al 2012), and association of zooplankton taxa with water mass types on the Western Antarctic Peninsula (Ashjian et al 2008).…”

mentioning

confidence: 99%

See 3 more Smart Citations

Semi‐automated image analysis for the identification of bivalve larvae from a Cape Cod estuary

Thompson

Hare

Gallager

2012

Limnology & Ocean Methods

View full text Add to dashboard Cite

Machine-learning methods for identifying planktonic organisms are becoming well-established. Although similar morphologies among species make traditional image identification methods difficult for larval bivalves, species-specific shell birefringence patterns under polarized light permit identification by color and texturebased features. This approach uses cross-polarized images of bivalve larvae, extracts Gabor and color angle features from each image, and classifies images using a Support Vector Machine. We adapted this method, which was established on hatchery-reared larvae, to identify bivalve larvae from a series of field samples from a Cape Cod estuary in 2009. This method had 98% identification accuracy for four hatchery-reared species. We used a multiplex polymerase chain reaction (PCR) method to confirm field identifications and to compare accuracies to the software classifications. Image classification of larvae collected in the field had lower accuracies than both the classification of hatchery species and PCR-based identification due to error in visually classifying unknown larvae and variability in larval images from the field. A six-species field training set had the best correspondence to our visual classifications with 75% overall agreement and individual species agreements from 63% to 88%. Larval abundance estimates for a time-series of field samples showed good correspondence with visual methods after correction. Overall, this approach represents a cost-and time-saving alternative to molecular-based identifications and can produce sufficient results to address long-term abundance and transport-based questions on a species-specific level, a rarity in studies of bivalve larvae.

show abstract

Section: Thompson Et Almentioning

confidence: 99%

Section: Thompson Et Almentioning

confidence: 99%

Section: Genetic Identification Of Field Larvaementioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Semi‐automated image analysis for the identification of bivalve larvae from a Cape Cod estuary

Thompson

Hare

Gallager

2012

Limnology & Ocean Methods

View full text Add to dashboard Cite

show abstract

“…In this work, 1000 WM examples are firstly divided into eight (simplified) and 29 (detailed) classes, then a discriminant vector forest algorithm and a supplementary algorithm are used to classify the WMs based on the insert functions of ZOOSCAN, finally an overall accuracy between 80 and 85% is obtained. In Bell and Hopgroft (2008), an assessment of ZooImage system (a tool for zooplankton classification) is given. In this work, 53 categories of WMs are classified using the RF method, and an overall classification error lower than 13% is obtained.…”

Section: Third Party Toolsmentioning

confidence: 99%

A survey for the applications of content-based microscopic image analysis in microorganism classification domains

Wang

2017

Artif Intell Rev

View full text Add to dashboard Cite

Microorganisms such as protozoa and bacteria play very important roles in many practical domains, like agriculture, industry and medicine. To explore functions of different categories of microorganisms is a fundamental work in biological studies, which can assist biologists and related scientists to get to know more properties, habits and characteristics of these tiny but obbligato living beings. However, taxonomy of microorganisms (microorganism classification) is traditionally investigated through morphological, chemical or physical analysis, which is time and money consuming. In order to overcome this, since the 1970s innovative content-based microscopic image analysis (CBMIA) approaches are introduced to microbiological fields. CBMIA methods classify microorganisms into different categories using multiple artificial intelligence approaches, such as machine vision, pattern recognition and machine learning algorithms. Furthermore, because CBMIA approaches are semior full-automatic computer-based methods, they are very efficient and labour cost saving, supporting a technical feasibility for microorganism classification in our current big data age. In this article, we review the development history of microorganism classification using CBMIA approaches with two crossed pipelines. In the first pipeline, all related works are grouped by their corresponding microorganism application domains. By this pipeline, it is easy for microbiologists to have an insight into each special application domain and find their interested applied CBMIA techniques. In the second pipeline, the related works in each application domain are reviewed by time periods. Using this pipeline, computer scientists can see the dynamic of technological development clearly and keep up with the future devel-

show abstract