The issue of aging is a complex social challenge. When elderly people suffer from diseases such as hemiplegia, their quality of life is greatly affected. The only way to reduce the impact of such diseases is to perform long-term rehabilitation, which is extremely time-consuming. Thus, gait information for clinical practice can effectively help subjects with stroke and their occupational therapists. In this study, a pressure-sensor-based gait analysis system is proposed to help occupational therapists evaluate the gait of disabled people. To effectively acquire gait information without affecting the user’s activities, the insole of the foot is selected as the pressure-sensing interface. To accurately acquire information of the plantar pressure, force-sensing resistor (FSR) film pressure sensors (FPSs) are used. To greatly reduce the differences between the outputs of FSR FPSs, linear regression is used to normalize the outputs. To correctly detect the steps in the gait cycle, an endpoint detection algorithm is applied. The experimental results showed that the proposed normalization process can greatly reduce the differences between the outputs of FSR FPSs. Moreover, occupational therapists agreed that the proposed system can help them evaluate the gait of users.