In recent years, even though the average using a navigation system for destination user has gradually increased, we continue to witness on news a slight increase in getting lost with a GPS. Most of the getting lost events occur due to the navigation system usually using the shortest paths as their recommended route.Supposedly, we use the shortest path may encounter the following situation:(1)GPS device might lead you down the narrow alley or down a closed road. If we are driving down a narrow alley, we have to pay more attention to our surrounding environment, as well as the inconvenience caused by the vehicle passing cross form the opposite lane. (2)If we are driving down a brick road or driving into some areas of damaged roads, we must lower the speed. The traffic is often dense and crowds because most of brick road area is laid near to the tourist attractions. In addition, the vehicle driving on the brick road areas might more easily skid than driving on the asphalt road areas when it is raining. Furthermore, the driver may feel bumpy when driving pass through some areas of damaged roads or driving on a brick road.To address the above problems, in this thesis, we present a framework of system for vision-based path recommend from street view images.The entire system is a combination of the following three steps:(1)Data collection, the path is selected by graphical user interface. Also, we download the street view images of the whole path.(2)Surface extraction, the vanishing point is calculated from the collection images. The area of the pavement is extracted by the Grow-Cut in super-pixel level, and the road width of the area is calculated finally.(3)Surface classification, training step is carried out on the types of brick pavement and asphalt pavement collected in advance. Finally, the pavement categories for each image were predicted by using our previously trained modules.In the experimental results, in this thesis, we use the surface extraction and classification method, the results of the extraction and classification are displayed, then we explain the rules of its distribution. After that, we will discuss the accuracy of surface classification. Since we calculate the recommend scores for each path through our own scoring rules, we will examine whether the results of the path proposed by our system can effectively solve the above problems.