A Method for Automatic Colony Counting Based on Image Processing and Its Realization

A new automatic colony counting method based on image processing technique is introduced. According to the features of the colony image, binarization with between class variance (BCV) method, Hough transform to remove the edge image of Petri dish, distance transform and watershed algorithm to segment overlapping colonies are applied, and finally eight connected edge tracking algorithm and area filling algorithm are used to mark and count the colony. It has been proved that the method greatly improves the accuracy and efficiency of the colony counting and the counting result doesnot be affected by using inoculation, variety, shape and size of the colony. The method can well replace the traditional human counting and is worthy of popularizing and applying. Furthermore, the distance transform and the watershed algorithm are also applicable for segmentation of all kinds of overlapping granule images. It has a great utility value in granule image analysis, such as cell image processing and material image processing.