Maize is a very important crop where its circulation in the market has to conform to thernrules of quality inspection. Currently, maize sample quality inspection is performedrnmanually by human experts through visual evaluation and the constituents will bernclassified into foreign matter, rotten and diseased, healthy, broken, discolored, shriveledrnand pest damaged kernels. However, visual evaluation requires significant amount ofrntime, trained and experienced people. Besides, it is affected by bias and inconsistenciesrnassociated with human nature. Such approach will not be satisfactory for large scalerninspection and grading unless fully automated.rnThe goal of this research work is to develop a system capable of assessing the quality ofrnmaize sample constituents using digital image processing techniques and artificialrnneural network classifier based on the standard for maize set by the EthiopianrnStandards Agency. A novel segmentation technique is proposed to segment and lay thernfoundation for feature extraction. A total of 24 features (14 color, 8 shape and 2 size)rnhave been identified to model maize sample constituents.rnFor classificat ion of maize samples, a feedforward artificial neural network classifierrnwith backpropagat ion learning algorithm, 24 input and 7 output nodes, correspondingrnto the number of features and classes respectively has been designed. The network isrntrained and its performance is compared against other classifiers both empirically andrnbased on supporting facts from the literature. For the purpose of training the classifier, arntotal of 534 kernels and foreign matters have been collected from Ethiopian Grain TradernEnterprise. The training data is randomly apportioned into training (70%) and testingrn(30%). The classifier achieved an overall classification accuracy of 97.8%. The successrnrates for detecting foreign, rotten and diseased, healthy, broken, discolored, shriveledrnand pest damaged kernels are 100%, 95.2%, 98.6%, 98.8%, 100%, 98.4%, and 94.8%,rnrespectively.rnKeywords: Artificial neural network, Maize quality assessment, Reconstructed image,rnMerged image, Color image segmentation, Digital image processing, Color structure tensor