Copepods are the largest and most diversified group of crustaceans and their habitat can be anywhere with water at any condition. Copepods act as the important link in the marine food chain and studying the community structure and abundance of copepods in relation to the environment is essential to evaluate their contribution to mangrove trophodynamics and coastal fisheries. The routine identification of copepods of the previously described species can be very technical, requiring taxonomic expertise and great amount of knowledge in biodiversity studies. It is also a burdening and time consuming process. Hence, there is a need to develop a computer system to automate identification and classification of copepod specimens. This study aims to develop a prototype of the system using digital image processing techniques for image pre-processing, image segmentation and to discover and extract significant and suitable features of copepod specimens for classification. We plan to use neural network to classify the copepod specimens based on their morphological features. In this study, we aim to automate classification of copepod specimens up to the genus level. The copepod specimens used in this work were collected from Matang Mangrove Forest Reserve (MMFR) on the west coast of Peninsular Malaysia.