Neovascularization is a new vessel in the retina beside the artery-venous. Neovascularization can appear on the optic disk and the entire surface of the retina. The retina categorized in Proliferative Diabetic Retinopathy (PDR) if it has neovascularization. PDR is a severe Diabetic Retinopathy (DR). An image classification system between normal and neovascularization is here presented. The classification using Convolutional Neural Network (CNN) model and classification method such as Support Vector Machine, k-Nearest Neighbor, Naïve Bayes classifier, Discriminant Analysis, and Decision Tree. By far, there are no data patches of neovascularization for the process of classification. Data consist of normal, New Vessel on the Disc (NVD) and New Vessel Elsewhere (NVE). Images are taken from 2 databases, MESSIDOR and Retina Image Bank. The patches are made from a manual crop on the image that has been marked by experts as neovascularization. The dataset consists of 100 data patches. The test results using three scenarios obtained a classification accuracy of 90%-100% with linear loss cross validation 0%-26.67%. The test performs using a single Graphical Processing Unit (GPU).

This article discusses the maize leaf disease image classification. The experimental images consist of 200 images with 4 classes: healthy, cercospora, common rust and northern leaf blight. There are 2 steps: feature extraction and classification. Feature extraction obtains features automatically using convolutional neural network (CNN). Seven CNN models were tested i.e AlexNet, virtual geometry group (VGG) 16, VGG19, GoogleNet, Inception-V3, residual network 50 (ResNet50) and ResNet101. While the classification using machine learning methods include k-Nearest neighbor, decision tree and support vector machine. Based on the testing results, the best classification was AlexNet and support vector machine with accuracy, sensitivity, specificity of 93.5%, 95.08%, and 93%, respectively.

Transfer learning (TL) is a technique of reuse and modify a pre-trained network. It reuses feature extraction layer at a pre-trained network. A target domain in TL obtains the features knowledge from the source domain. TL modified classification layer at a pre-trained network. The target domain can do new tasks according to a purpose. In this article, the target domain is fundus image classification includes normal and neovascularization. Data consist of 100 patches. The comparison of training and validation data was 70:30. The selection of training and validation data is done randomly. Steps of TL i.e load pre-trained networks, replace final layers, train the network, and assess network accuracy. First, the pre-trained network is a layer configuration of the convolutional neural network architecture. Pre-trained network used are AlexNet, VGG16, VGG19, ResNet50, ResNet101, GoogLeNet, Inception-V3, InceptionResNetV2, and squeezenet. Second, replace the final layer is to replace the last three layers. They are fully connected layer, softmax, and output layer. The layer is replaced with a fully connected layer that classifies according to number of classes. Furthermore, it's followed by a softmax and output layer that matches with the target domain. Third, we trained the network. Networks were trained to produce optimal accuracy. In this section, we use gradient descent algorithm optimization. Fourth, assess network accuracy. The experiment results show a testing accuracy between 80% and 100%.

Convolutional neural network (CNN) is a method of supervised deep learning. The architectures including AlexNet, VGG16, VGG19, ResNet 50, ResNet101, GoogleNet, Inception-V3, Inception ResNet-V2, and Squeezenet that have 25 to 825 layers. This study aims to simplify layers of CNN architectures and increased accuracy for fundus patches classification. Fundus patches classify two categories: normal and neovascularization. Data used for classification is MESSIDOR and Retina Image Bank that have 2,080 patches. Results show the best accuracy of 93.17% for original data and 99,33% for augmentation data using CNN 31 layers. It consists input layer, 7 convolutional layers, 7 batch normalization, 7 rectified linear unit, 6 max-pooling, fully connected layer, softmax, and output layer.

No abstract