Aimed at the image of the simple grapevine taken in the pergola trellis, a grape recognition algorithm combined with color and texture feature of color image was suggested in order to get the center line and the length of the grape. Firstly, Sobel operation was used to get the edge of the |G-R|+|G-B| chromatic aberration image. Then, berries of the grape were detected by Hough transform according to the mathematical model of the outline of the grape berries. The circles detected by the Hough transform were judged by the feature of the color and texture of grape berries and the concentrated berries. At last, the shape parameters of the grape bunch were determined by the information of the berries after judged, which was needed by bagging automation of grape. The experimental results showed that the method of grape recognition was effective in segmenting the comparison of grapes. There were totally 78 images used in test, and 70 of them were correctly recognized. The correct recognition of grapes reached to 90%.