Low-light image enhancement is generally regarded as a challenging task in image processing, especially for the images captured at nighttime or images taken in low-light conditions. It is because various factors of the image such as contrast, sharpness and color coordination should be handled simultaneously and effectively. To reduce the blurs or noises on the low-light images, many papers have contributed by proposing different techniques. One such technique addresses this problem using a pipeline neural network and a convolutional neural network. Due to the irregularity of intensity calculation in the working of the pipeline neural networks model, a hidden layer is added to the model which results in a decrease in irregularity. The CNN algorithm uses more number of hidden layers in identifying features of the image in the pixel level, and the process of repairing in the pixel level will increase the intensity of the image and thus increases the clarity of the image. The proposed model using DCNN increases the intensity accuracy percentage by 10–15%.