Digital image analysis (DIA) algorithms were developed to facilitate classification of bulk samples of Canada Western Red Spring (CWRS) wheat, Canada Westem Amber Durum (CWAD) wheat, barley, oats, and rye using textural and color features of the grains. To classify individual kernels of CWRS wheat, CWAD wheat, barley, oats, and rye, DIA algorithms were developed based on morphological, textural, and color features of the grains. The textural features of bulk samples and individual kemels were extracted from different colors (e.g., red, green, or blue) and color band combinations (e.g., black & white ${$(R+G+B)/3)$}$, (3R+2G+1B)/6, (2R+1G+3B)/6, or (1R+3G+2B)/6) of images to determine the color or color band combination that gave the highest classification accuracies in cereal grains. For bulk samples, the textural features extracted from the red color band at maximum gray level value 32 gave the highest classification accuracies in cereal grains. The mean accuracy which was the average of the classification accuracies of the cereal grains at a maximum gray level value, was 100.0% when tested on an independent data set. For individual kernels, the textural features extracted from the green color band at maximum gray level value 8 gave the highest classification accuracies in cereal grains. The mean accuracies were 92.0 and 92.9% when the texture model with the first 15 most significant features was tested on an independent data set and on the training data set, respectively. When the original bulk images were partitioned into sub-images and textural or color features extracted from the sub-images were used, the classification accuracies of cereal grains decreased compared to those based on the original images. The mean accuracy was 100.0% when color features of bulk samples were used for classification of cereal grains in an independent data set. For classification of individual kemels of cereal grains, the color model with the first 10 most significant color features gave mean accuracies of 93.4 and 94.9% when tested on an independent data set and on the training data set, respectively. The morphological model with the first 10 most significant morphological features gave mean accuracies of 94.2 and 96.0% when tested on an independent data set and on the training data set, respectively. The mean accuracies of 98.6 and 99.3% were achieved when the morphology-texture model with the first 15 most significant features was used to test on an independent data set and on the training data set, respectively. When the morphology-color model (with the first 15 most significant features) was tested on an independent data set and on the training data set, the mean accuracies were 99.4 and 99.6%, respectively. Similarly, using the texture-color model (wi h the first 15 most significant features) the mean accuracies were 98.4 and 98.0%, respectively for an independent data set and the training data set. The highest classification accuracies were achieved when the morphology-texture-color model was used. The mean accuracies using the first 20 most significant features in the morphology-texture-color model were 99.7 and 99.8% when tested on an independent data set and on the training data set, respectively.