The cracks in the road can be detected with the help of the road images. A supervised model is developed for the identification of the cracks in the road images with the help of extraction of the features from the images. The features were extracted and normalized and based on the resulting feature values were categorized into crack or non crack. Based on the extracted features the image is labelled as crack or non-crack. In the testing phase features were extracted from the images and cracks in the images were identified. The cracks were then further classified into different types by comparing the extracted feature values with the specific threshold proposed. The Performance of the process is finally measured. The cracks in the roads may lead to accidents and other damages. Inorder to identify the cracks in the roads, road images can be used inorder to identify and classify the crack. The cracks in the images were in different intensities than the other regions. Inorder to identify the different intensity in the images, segmentation methods can be employed. The segmentation process based on supervised learning is proposed in this process. Crack detection in pavements and objects has been a constant field of research in pavement management. Conventionally, humans were engaged to detect cracks in the pavements and they used to present report sheets based on their assessment. But, this process was a time consuming one and was costlier too. So, researchers were trying for some alternate method that would detect cracks, hence minimizing the human involvement and at the same time detecting the cracks precisely. This gave way to numerous automated techniques for the detection of cracks.