Ethiopia is one of the developing countries in the world, and its economy depends on both agriculture and industry. From agriculture products, maize crop is one of the most important for both human beings as well as for animals in Ethiopia. Even though, maize has a great share and nutritive value, it is very susceptible to different types of diseases. Currently, there are more than 72 maize diseases reported in Ethiopia caused by fungi, bacteria, nematode and viruses. Among this diseases maize leaf blight, maize common rust, and leaf spot are common diseases that attack maize leaf. There are different traditional mechanisms to recognize and classify maize leaf diseases by chemical analysis or visual observation. However, the traditional mechanisms to recognize maize leaf diseases have their own draw backs, such as expensiveness, inconsistent, prone to error, take more time, require professional staff, specialized instruments, inefficient etc. Therefore, we are motivated to develop maize leaf diseases recognition and classification model using imaging and machine learning techniques in order to support experts. In view of this, digital image analysis techniques based on texture, color and morphology features were developed to recognize and classify maize leaf diseases and healthy leaf. Sample of maize leaf disease images were taken from Amhara region maize farming area. Totally 800 images were acquired for training and testing, 200 images from each class. For the recognition and classification analysis, 7 textures, 6 colors and 9 morphological features, totally 22 features are extracted from each image. To build the recognition and classification model, K-nearest Neighbor (KNN), Artificial Neural Network (ANN) and Support Vector Machine (SVM) classification techniques were used. To evaluate the recognition and classification accuracy, form the total data set of 800 images, 80% were used for training and the remaining 20% was for testing the model. Based on the experimental results using combined texture, color and morphology features, the Support Vector machine (SVM) classifier was performing better than other classifier (KNN and ANN) algorithms. The SVM classifiers algorithm with combined features accuracy for each four classes (Common rust, leaf blight, healthy leaf and leaf spot) are 97.5%, 97.5%, 97.5% and 90.0% respectively, and the overall performance was 95.63%. As a conclusion, there was satisfactory result to recognize and classify maize leaf diseases.