<p class="Abstract"><em>Abstract</em> – This study proposes a system for classification and counting the number of bacterial colonies using a photo image of bacteria. The system uses several image pretreatment process. Including Contrast Stretching, <em>Extended-Maxima Transform</em>, and <em>Regionprops</em>. The main purpose of this system is to determine the category of colonies of bacteria in large quantities can not be done manually. To build the algorithms necessary features must be determined such as <em>diameter, perimeter and roundness</em> method of determining the categories using KNN <em>(K-Nearest Neighbor)</em>. As a results of this research is classify three types of bacteria such as Lactobacillus Bulgaricus, Streptococcus thermophiles, and bifidobakterium Precision with a percentage of 97,97% and 87,09% F-Measure</p><p><strong>Keywords: Contrast Stretching, Lactobacillus, Regionprops, K-Nearest Neighbor</strong></p>