In recent times, digital image processing has witnessed the emergence of several novel image segmentation methods. Image segmentation is an important part of image processing which involves the critical task of partitioning a digital image into discrete segments. This process plays a fundamental role in image analysis, facilitating essential functions such as feature extraction and image interpretation. Furthermore, it is widely used in medical science, like tissue classification, tumor identification and sizing, surgical planning, and more. Numerous image segmentation methods are available, and the k-means clustering approach is a commonly employed technique for this purpose. This research paper extensively reviews a variety of existing image segmentation techniques based on k-means clustering. However, it is essential to acknowledge that the k-means clustering approach does come with inherent limitations due to its dependence on priori values. These constraints have spurred the development of several modified models to mitigate these drawbacks. In this survey paper, our focus is on highlighting specific k-means clustering-based image segmentation techniques that have garnered recognition in the field. The paper also compares the segmentation techniques by considering evaluation metrics like MSE, Jaccard index, PSNR, and Correlation index to provide a deeper understanding of their segmentation capability and accuracy.