Malt-barley selection is the main procedure in beer production. The varieties of grain have to be inspected upon purchase in every malt house. Varietal uniformity is crucial for the production of high quality malt. Discrimination between malt-barley varieties is a difficult task during inspection, since it requires training and experience. In order to tackle varietal selection difficulties Malt industries have been employed and trained experts; even though, those experts do not work effectively due to tiredness, bias and other factors. Therefore, many researchers are motivated for the development of automatic prediction model based on image processing in order to support experts across the world. However, as far as the researcher‟s knowledge no attempts has been done for Ethiopian emerged malt-barley varieties, and hence, in this study an attempt has been made to develop malt-barley variety identification model. In view of this, a digital image processing technique based on combined morphological, texture and color features have been explored to identify different varieties of Ethiopian malt-barley. Sample malt-barleys were taken from Gondar Malt Factory which is the only nearby area for taking the varieties. On the average 52 images were taken from each of the four varieties (Holker, Propino, Sabini and Misikal). The total number of images taken was 208 containing 5408 malt-barley seeds. For the identification, nine morphological, five textures and six color features were extracted from each scanned barley seed images. To build the identification models for prediction of maltbarley varieties, K-Nearest Neighbors (KNN), Artificial Neural Network (ANN) and the ensemble of the two techniques are investigated. Based on experimental results, ensemble model of ANN and KNN outperforms a single model constructed using either ANN or KNN, on combined features of morphology, texture and color employing Sequential Forward Feature Selection (SFFS) technique. Quantitatively, an average accuracy of 95.1% is achieved for Holker, Propino, Sabini and Misikal varieties with the combined feature sets of morphology, color and texture using the ensemble of ANN and KNN. This shows a promising result to design an applicable malt-barley identification model. Non-uniform size and overlap malt-barley images affect greatly the performance of the identifier and hence they are the future research direction that needs an investigation of generic segmentation and noise removal techniques.