Nowadays, the most demanding and time consuming task in medical image processing is Brain tumor segmentation and detection. Magnetic Resonance Imaging (MRI) is employed for creating a picture of any part in a body. MRI provides a competent quick manner for analyzing tumor in the brain. This proposed framework contains different stages for classifying tumor like Preprocessing, Feature extraction, Classification, and Segmentation. Initially, T1-weighted magnetic resonance brain images are considered as an input for computational purpose. Median filter is proposed to optimize the skull stripping in MRI images. Abnormal brain tissues are extracted in low contrast, in addition to meticulous location of edges of affected tissue can be detected. Then, Discrete Wavelet Transform (DWT) and Histogram of Oriented Gradients (HOG) are performing feature extraction process. HOG is used for extracting the features like texture and shape. Then, Classification is performed through Machine learning categorization techniques via Random Forest Classifier (RFC), Support Vector Machine (SVM), and Decision Tree (DT). These classifiers classify the brain image as either normal or abnormal and the performance is analyzed by various parameters such as sensitivity, specificity and accuracy.

如今，医学图像处理中最苛刻且最耗时的任务是脑肿瘤分割和检测。磁共振成像（MRI）用于创建人体任何部位的图像。MRI为分析脑部肿瘤提供了一种有效的快速方法。该提议的框架包含用于对肿瘤进行分类的不同阶段，例如预处理，特征提取，分类和分割。最初，T1加权磁共振脑图像被视为用于计算目的的输入。提出了中值滤波器来优化MRI图像中的颅骨剥离。以低对比度提取异常的脑组织，此外还可以检测到受影响的组织边缘的细微位置。然后，离散小波变换（DWT）和定向梯度直方图（HOG）正在执行特征提取过程。HOG用于提取纹理和形状等特征。然后，通过随机森林分类器（RFC），支持向量机（SVM）和决策树（DT）通过机器学习分类技术执行分类。这些分类器将大脑图像分类为正常图像或异常图像，并通过各种参数（例如灵敏度，特异性和准确性）对性能进行分析。