Running convolutional neural network (CNN) algorithm using dedicated integrated circuits (ICs) on real-time portable applications is mainly restricted by slow performance and large power consumption. The power and delay are mainly due to external memory access, which incurs considerable energy consumption and bandwidth issues. In this paper, we propose an efficient convolution layer design using domain wall memory (DWM) for eliminating external memory access in image sensor embedded application. A low energy access scheme using tag is employed to further reduce power consumption. The experimental results show that the proposed CNN architecture achieve 11.2% memory energy savings and 21.8% of MAC operation reduction in compared to conventional architecture.