Data released on May 22, 2015
Extracting important biological descriptors and features from images of biological specimens remains an important and open problem. In many biological disciplines, landmark and semi-landmark based approaches are used to define features. These features are determined a priori based on numerous
criteria such as homology, or some measure of biological significance. An alternative, widely used strategy uses computational pattern-recognition, in which features are acquired from the image denovo. Sub-sets of these features are then selected based on some objective criteria. Computational pattern-recognition has been extensively developed primarily for classification of samples into groups, while landmark methods have been broadly applied to biological inference.
To address how these approaches compare, and to provide a general community resource, we have constructed an image database of Drosophila melanogaster wings, individually identifiable and organized by sex, genotype, and replicate imaging system, for the development and testing of measurement and classification tools for biological images.