Identifying the writer of handwritten text poses a significant challenge due to the diversity and variability inherent in handwriting styles. This paper proposes a novel approach based on Siamese neural network (SNN)  for the task of writer identification in Khmer handwriting. The SNN architecture was leveraged for training and testing on a dataset specifically collected for this purpose. The dataset comprised 1400 samples collected from students, which were divided into training and testing sets containing 983 and 417 words, respectively. Promising results were achieved through extensive experimentation, with a training set accuracy of 96% and a testing set accuracy of 94%. The proposed SNN approach demonstrated effectiveness in handling the complexities of Khmer handwriting and accurately identifying the authorship of words. This research contributes to the advancement of writer identification techniques in the context of Khmer script, with potential applications in forensic analysis, document verification, and linguistic research. Future work may focus on enhancing the robustness and scalability of the model, as well as exploring additional features and optimization strategies to further improve performance