Every two months, the Taiwan Power Company will dispatch staffs to each household to read numbers in electricity meters to calculate and collect electricity bills. However, these electricity meter staff sometimes read the wrong meter numbers and so calculate the wrong electricity bill. A system that automatically detects the digital region in electricity meter, could reduce this misreading of numbers and calculate the electricity bill correctly, thereby increasing work efficiency. Herein, the deep learning model SSD (Single Shot MultiBox Detector) is applied and fine-turned to detect the digital region in electricity meter to help the Taiwan Power Company staff. From the experimental results, it is demonstrated that the presented deep learning methods detect the digital region better than the pre-trained SSD model. In the testing experiments, the accuracies of the digital region detection are 100% for both our collected data's and fine-tuned SSD, respectively.