This study proposes an automatic labeling method for liver regions in Computed Tomography (CT) images, addressing the time-consuming nature of manual medical image labeling. The approach utilizes edge detection to identify overall edge distributions in CT images, constrains the region of interest to locate characteristic liver areas, and performs object segmentation to generate liver masks for labeling. The method tackles key challenges in liver CT image analysis, including image noise, blurred edge features, and minimal pixel differences in suspected tumor areas. It employs Gaussian blur for noise reduction, followed by brightness and contrast adjustments to enhance edge characteristics. The watershed algorithm is then applied to segment the complete liver contour. Performance evaluation using approximately 17,000 images from the LiTS datasets demonstrated an average accuracy of 75% for liver labeling, with a maximum of 80% and a minimum of 62%. The process achieves a labeling speed of about 1 s per 100 images, highlighting its efficiency. The proposed method shows promise in automating liver labeling in CT images, potentially streamlining the image analysis process in medical research and diagnosis.