Automatic counting the number of Collembola in digital images

Counting the number of Collembola in digital images is a routine task in laboratories of soil ecotoxicology. This process is based on a direct visual identification of Collembola, and is consequently a time consuming task. This paper present a fully automatic system for counting the number of Collembola in digital images. The system selects the interest area of the image, detects and removes the specular reflection of the incident light, as well as the foam developed during laboratory experiment and finally identifies and counts the number of Collembola. The system performance was tested using 5 treatments with 9 or 10 replicates and 13 treatments with 4 or 5 replicates. A total of 111 images were tested and the results were compared with those obtained by manual identification. The average relative error between automatic and manual counts from multiple observations of the same treatment was 2:1%, which can be considered a good result, given that this value is below the standard deviation between multiple replicate counts.