Inflammation of the conjunctiva and pain and discomfort in the inner surface of the eyelids is referred to as Conjunctivitis. It causes severe pain, burning sensation or in extreme cases blindness of the eye. Normally conjunctivitis is detected by eye specialist doctors and their limited number makes it difficult for everyone to reach them and get themselves diagnosed. This paper describes an automatic efficient image processing based method to identify conjunctivitis infected eye from a normal eye and classify it according to its types. Some statistical and texture features were used and then followed by PCA for extraction of discriminatory features and then classified using supervised learning method such as multi-class SVM and KNN. The intensity of the infected eyes were also calculated using the significant red plane. Plotconfusion was used to calculate the accuracy and a high accuracy was achieved using this method. Also in addition this proposed method is efficient, computationally fast and costs very low.