Aim: Aim of this research work is to improve accuracy of blood smear image by applying novel k-means clustering algorithms and threshold segmentation technique. Materials and Methods: This investigation made use of a collection of data from Kaggle’s Website. Samples were considered as (N=30) for K-means clustering technique and (N=30) for threshold technique with total sample size calculated using clinical.com. As a result the total number of samples was calculated to be 60. Using IBM SPSS Software and a standard data set, the accuracy was obtained. Both segmentation techniques were implemented on blood smear images through Matlab coding and also extracting accuracy values of each image. Then through SPSS software comparison and analysis has been made. Results: The accuracy (%) value of both segmentation techniques are compared using SPSS software by independent sample t-tests. There is statistical insignificance with an accuracy of (99.8810%) and demonstrated a better outcome in comparison to threshold technique accuracy (58.6514%). Conclusion: Novel K-means clustering segmentation technique appears to give better accuracy than that of the threshold technique on blood smear images.