Evaluating classification and feature selection techniques for honeybee subspecies identification using wing images

Silva, Felipe Leno da; Sella, Marina Lopes Grassi; Francoy, Tiago Maurício; Costa, Anna Helena Reali

doi:10.1016/j.compag.2015.03.012

Cited by 45 publications

(44 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Globally, many A. mellifera L. sub-species (up to 30) have been described in the literature (Ruttner 1988(Ruttner , 1992Hepburn and Radloff 1998;Bouga et al 2011;da Silva et al 2015). Sub-species are mainly classified based on various morphological characteristics, and more recently, molecular techniques have also been applied (Ruttner 1988;Meixner et al 2013).…”

Section: Honeybees Of Africamentioning

confidence: 99%

Honeybee health in Africa—a review

Pirk¹,

Strauss²,

Yusuf³

et al. 2015

Apidologie

View full text Add to dashboard Cite

-Honeybee (Apis mellifera L.) pathogens and parasites and the negative effects thereof on honeybee populations remain an issue of public concern and the subject of active research. Africa with its high genetic diversity of honeybee sub-species and large wild population is also exposed to various factors responsible for colony losses in other parts of the world. Apart from the current American foulbrood epidemic in the Western Cape of South Africa, no large-scale colony losses have been reported elsewhere on the continent. We discuss the presence of pathogens, parasites, pests and predators of African honeybees as well as the threats they face in relation to habitat changes arising from the impact of increased human populations. In addition, we discuss current efforts aimed at protecting and promoting the health of African honeybees.honeybees / Africa / honeybee health / pathogens / parasites / pests / predators / habitat loss

show abstract

Section: Honeybees Of Africamentioning

confidence: 99%

Honeybee health in Africa—a review

Pirk¹,

Strauss²,

Yusuf³

et al. 2015

Apidologie

View full text Add to dashboard Cite

show abstract

“…Honeybees live in different environments, such as mountainous, hilly areas, plains, dessert or wetlands and they are usually classified into about 30 subspecies (Leno da Silva, et al, 2015;Rinderer, 2008). Honeybees are grouped into four phylogenetic lines: A, C, M and O, each associated to a particular geographical area.…”

Section: Introductionmentioning

confidence: 99%

“…Wings are considered the most reliable morphological structure for insect identification; the evaluation of wing morphology being also recommended for the identification of honey bees. In the last years, the measurements of the fore wings have proven to be reliable for the c 1 lassification of honeybees (Leno da Silva et al, 2015). Even though differences between species are much more important than the intra-species ones, the intra-species variation is large enough to discriminate the bee subspecies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of the Honeybee Subspecies From Some Romanian Counties Using a Semiautomatic System for Analyzing Wings

Buescu

Gurău

Daneş

2018

CBUP

View full text Add to dashboard Cite

Morphometric analysis of honeybee wings can be used to discriminate between honeybee subspecies. The classic morphometric methods used to identify honeybee subspecies are time consuming while geometric morphometric analysis are proven to be more efficient and rapid for the identification of honeybee subspecies. Even if the geometric morphometric analysis involves several steps such as: obtaining the image of the honeybee wing, processing the wings image (settlement of the 19 points), classification and validation, in terms of consumed time,it takes less than classic morphometric methodes and it is easier to apply. The aim of this study was to identify honeybee subspecies from the Romanian South-Eastern area, using the geometric morphometric method. To accomplish this, the semiautomated French system ApiClass was used. This system allows us to identify the honeybee subspecies based on the wing's image of the Apis mellifera honeybee worker. The program is using the recent approaches of geometric morphometry and is analyzing the wing considering 19 points corresponding to the intersections of the main veins of the bee forewings. These coordinates are processed by the system before being analyzed after which the system returns the probability of the analyzed honeybee belonging to one of the honeybee subspecies from its reference system. The system has more than 5000 honeybee wing references off the main lines and honeybee subspecies. Using this system we analyzed samples from the counties of Braila, Buzau, Galati and Ilfov. Each sample was composed from wings of 20 honeybees. Most of the analyzed samples were identified as hybrids without being possible to specify the type or the level of the hybridization: only three samples were identified as being Apis mellifera carnica presenting a homology degree over 90%.

show abstract

“…The analysis of known research related to the measurement of morphological characteristics of bees shows that appropriate methods for this purpose are the following (El-Aw et al, 2012;Silvaa et al, 2015):…”

Section: Introductionmentioning

confidence: 99%

An algorithm for determination of the morphological characteristics of honey bees

Zlatev

Nedeva

2017

JCEA

View full text Add to dashboard Cite

At the current level of science and technology is used semi-automatic measurement of body parts of the bees, yielding images taken with a reference object via a camera or a scanner and then perform measurement by software using a pointing device. There are attempts to fully automated process of measuring the morphological characteristics of bees, at this stage there are conversions for Measuring wings, but this process for other parts are still made by manual way. The informative colour features for the separation of tergite and probotics from background in the image are selected by distance functions and correspondence analysis. Distances are determined between the values of the colour components of the object and background. From statistical analysis is found that appropriate for the separation of an object from background are S and V colour components of the HSV colour model. Algorithms and program in Matlab environment for separating tergite and proboscis from the background of the image and definition of their main sizes are developed. From the analysis of the results is found that the major influence on the accuracy of the measurement is the angle at the disposal of the bee body part in the image.

show abstract

Evaluating classification and feature selection techniques for honeybee subspecies identification using wing images

Cited by 45 publications

References 35 publications

Honeybee health in Africa—a review

Honeybee health in Africa—a review

Identification of the Honeybee Subspecies From Some Romanian Counties Using a Semiautomatic System for Analyzing Wings

An algorithm for determination of the morphological characteristics of honey bees

Contact Info

Product

Resources

About