The first step toward Seed Certification, a mechanism to ensure high quality of the seed and propagate materials of superior adapted crop varieties is the identification of seed type. A plant researcher inspects the visual attributes and morphology of a seed to identify the seed type, a process that is tedious. Advances in deep learning have led to the development of convolutional neural networks (CNN) that aid in classification using images. While they classify efficiently, a key bottleneck is the need for an extensive amount of labelled data to train the CNN before it can be put to the task of classification. The work strives to address the aforementioned challenges and leverages the concepts of Contrastive Learning and Domain Randomization in order to achieve the same. Synthetic image datasets of five different types of seed images namely, canola, rough rice, sorghum, soy and wheat are applied to three different self-supervised learning frameworks namely, SimCLR, Momentum Contrast (MoCo) and Build Your Own Latent (BYOL) where ResNet-50 is used as the backbone in each of the networks. The performance of the self-supervised learning frameworks is compared against the performance of a supervised learning model built on ResNet-50. When the self-supervised models are fine-tuned with only 5% of the labels from the synthetic dataset, results show that MoCo, the model that yields the best performance of the self-supervised learning frameworks in question, achieves an accuracy of 77% on the test dataset which is only 13% less than the accuracy of 90% achieved by ResNet-50 trained on 100% of the labels demonstrating the feasibility of domain randomization for classification of seeds using self-supervised learning frameworks.