Automated Classification and Identification System for Freshwater Algae Using Convolutional Neural Networks

Taxonomy and classification of freshwater algae is highly dependent on morpho-taxonomic characterization molecular genetic techniques. However, these methods are considered time- consuming tedious. This study was conducted to integrate the latest technological innovations digital image processing machine learning in developing an automated detection, recognition, identification selected algal species from divisions Chlorophyta Cyanobacteria. OpenCV Tensorflow (convolutional neural networks or CNN) were used development a system common (Chlorococcum infusionum, Chlorella vulgaris, Nostoc commune, Leptolyngbya lagerheimii, Desmodesmus abundans, Acutodesmus dimorphus, Oscillatoria proboscidea, limosa). Using OpenCV, microalgae images subjected enhancement techniques for removal noise other unwanted objects that minimizes errors. TensorFlow classified pre-processed using CNN gives percentage results which it identifies each image. The developed correctly identified 75 total 80 yielding final test accuracy 93.75%. exhibited first time Philippines use CNN-based recognition algae. applicable culture collections taxonomists fast easy taxa improved storage database.