Human motion recognition using flexible/stretchable wearable sensors holds great promise for human-machine interaction and biomedical engineering. However, to measure the individual joint motion with multiple degrees of freedom, many sensor networks are normally required and pinpointed onto the targeted area, restricting body movement. This is due to the limitation of current wearable sensors; inferring a sensor deformation based on the sensor's electrical signal is challenging. A new concept of wearable sensor that can recognize how the sensor deforms could radically solve this issue. Here, we report a wearable integrated piezoelectric film sensor (i-PFS) capable of detecting basic deformations. To achieve this, for the first time, we propose a novel design concept of using uniaxially drawn piezoelectric poly L-lactic acid (PLLA) films to engineer unimodal tension, bend, shear, and twist sensors that only respond to their corresponding deformations with the enhanced piezoelectric response and self-shielding function. Based on this, we construct the i-PFS by combining the four unimodal sensors and demonstrate that the i-PFS can detect and differentiate individual deformation modes, such as tensioning, bending, shearing, and twisting. To our best knowledge, the i-PFS is the world's first film-based sensor that identifies the abovementioned deformations. To prove the potential impact of the i-PFS, we design a sleeve and a glove with the i-PFS that can capture various wrist motions and subtle finger movements, respectively. We also develop a virtual text-entry interface system using the glove and a deep neural network algorithm with a character classification accuracy of about 90 %. The i-PFS technology is expected to provide a turning point in developing motion capture systems.