Cataract are the highest cause of blindness that there are 32.4 million peopleexperiencing blindness and as many as 191 million people experiencing visual disabilities in2010 in the world. On the other hand, the longer a patient suffers from cataracts or latetreatment. The development of cataract identification using a traditional algorithm based onfeature representation is highly dependent on the classification process carried out by an eyespecialist so that the method is prone to misclassification of a person detected or not. However,at this time there is a deep learning, convolutional neural network (CNN) which is used forpattern recognition which can help automate image classification. This research was conductedto increase the accuracy value and minimize data loss in the process of cataract identificationby performing an experience namely the manipulation process was carried out by changingepochs. The results of this study indicate that the addition of epochs affects accuracy and lossdata from CNN. By comparing variety of epoch values it can be ignored that the higher the agevalues used, the higher the value of the model. In this study, using the epoch 50 value reachedthe highest value with a value of 95%. Based on the model that has been made it has also beensuccessful to receive images according to the specified class. After testing accurately, 10 imagesachieved an average accuracy of 88%.
展开▼