Taxonomists frequently identify specimen from various populations based on the morphological characteristics and molecular data.
This study looks into another invasive process in identification of house shrew () using image analysis and machine learning approaches.
the images for both training and testing data sets, features to represent the image, the classifier, query specification and the expected output of the identification process.
The prototype was first developed and tested to discriminate five species of parasitic wasp, based on differences in their wing structure using principle component analysis and linear discriminant analysis .
The present study has the objectives of (1) extracting shape characteristics (morphological information) from the dorsal, lateral and jaw views of skull by using image processing techniques in order to perform an automatic species identification based on different populations of Peninsular Malaysia, and (2) to examine the variations in the combination of shape of the dorsal, lateral and jaw views and sexes of male and female among the different regions of its distribution. The views can be made in four different angles; i.e.
dorsal, ventral, jaw, and lateral, depending on the shape of the specimen.
The findings contribute to scientific research as well as teaching and educational purposes.
With the advancement in computer vision  and machine vision studies which involve studies such as artificial intelligence, imaging and pattern recognition, digital images in biology can be applied for species identification which is needed to assist and support biologists in doing their research.
An Artificial Neural Network (ANN) is used as classifier to classify the skulls of based on region (northern and southern populations of Peninsular Malaysia) and sex (adult male and female).