Wheat is the most important food security crop at the global level including Ethiopia. The local production of wheat in Ethiopia did not satisfy the domestic demand. The government of Ethiopia has imported millions of tons of wheat and wheat products every year. Septoria, Powderly mildew and rusts are one of the major constraints to decline wheat production in Ethiopia. Image processing and Deep learning algorithms can be used to identify the disease of wheat to know whether the leaf is affected or not at an early stage. The proposed system is initially started on the collected wheat leaf image and then an image resized into 256 x 256 pixels to decrease the computational burden. The resized RGB images are processed using various Image enhancement techniques and then the processed wheat leaf image datasets are segmented using Threshold algorithm. Color, texture and morphological features like shape and size are extracted and calculate from wheat leaf image datasets. These three important features are combined together for building and implementing the disease detection model. The extracted wheat leaf images are used as a dataset into training and testing. We collect 1570 image datasets from research institutes and different internet sources (call and cagel),70 % of the dataset are used for training while the remaining 30 % of the datasets are used for testing purpose. Then, the wheat leaf Detection model is trained using convolutional Network algorithm. The Model training accuracy and the model loss is 99% and 0.3 respectively, The Model testing accuracy and the model loss is 87% and 0.5 respectively with 100 numbers of epochs, and finally the model takes the image as input and predicts the class of the image. For future in order to enhance the proposed model, there is a need to the high dimensional dataset for training and testing to increase the model accuracy further, in this research only a three disease for a single cereal crop was considered, but there exist too many disease types that can affect different type of cereal crops. Interested researcher can enlarge the scope this research to address additional diseases that are discussed in Chapter Two, in image acquisition steps, we couldn’t get a full information for each image in the agriculture center. To address this problem, the interested researcher will use drone technology and satellite imagery to collect an image with climate and land data of the image to make fully automated and improved solutions and the interesting researcher can develop the application using desktop or mobile web-based applications for delivering the solution to its primary beneficiaries.