The segmentation of a brain tumor is an exciting and exigent research task in the field of medical image analysis. An early finding of a brain tumor aids to obtain effective treatment and boosting the survival time of the patients. The brain tumor segmentation segregates the abnormal tissues region from the normal tissues region. The major challenges are the complex structure, size, and location of the tumor region. In this proposed methodology, quantile transformation, Gabor filter, and various edge techniques are implemented to segment the tumor tissues in the MRI brain images. The quantile transformation computes the Gaussian probability distribution values to increase the semantic gap between tumor region and the non-tumor region. Gabor technique analyses the texture information for identifying specific frequency contents in the brain image. Various edge techniques such as Canny, Robert, Scharr, Prewitt, and Sobel edges are applied to extract the actual location and effective boundary regions. Gaussian low pass filter and median filter concept is applied to eliminate the external factors like unwanted noise. At last, the collected properties are then fed into the Random Forest classifier to isolate tumor tissue regions from the brain MRI images. Accuracy, precision, recall, and f-measures are used to estimate the performance of the proposed methodology. The results of the experiments reveal that our proposed strategy produced better outcomes.