Brain tumor segmentation is an important process for early tumor analysis and the treatment of disease. Although many brain tumor segmentation methods have been presented, enhancing tumor segmentation methods is still challenging because brain tumor CT images exhibit intricate characteristics like high diversity in tumor appearance and arguable tumor boundaries. To address this problem, we propose a novel automatic tumor segmentation method for CT images. This method treats tumor segmentation as a classification problem. Additionally, the Local Independent Projection-based Classification (LIPC) method is used to classify each pixel into different classes. Locality is crucial in the calculation of local independent projections for LIPC. The segmentation results of LIPC Method are compared with the radiologist ground truth images. Quantitative analysis between ground truth images and segmented tumor images is presented in terms of different performance measures. © Research India Publications.