TY - JOUR T1 - Automatic classification of diatoms of Merja fouarate JF - bioRxiv DO - 10.1101/099135 SP - 099135 AU - Nouzha Chahboune AU - Mohamed Mehdi AU - Allal Douira Y1 - 2017/01/01 UR - http://biorxiv.org/content/early/2017/01/09/099135.abstract N2 - Objective: This work consists of developing an automatic method of form analysis and classification of diatoms through processing of scanned images. The fundamental objective is to determine to what extent two diatoms are similar from the images stored in a database, and to conclude to what classes they belong. To do so, a comparison is made between a manual identification and an automatic identification, based on the ultimate points and the Freeman Chain Code. ER -