In order to adapt to strict requirements of the pharmaceutical industry for quality of medicinal aluminum foil when printed, a print quality detection system for medicinal aluminum foil based on machine vision was developed after analyzing the detection requirements for tiny pinhole defects, words defects on the front side and small foreign body on the back side. A high real-time, high-definition image acquisition environment is built by the linear array CCD camera, bar-shaped LED light source and other necessary hardware. The architecture of the detection system is based on WinSock network communication; the processing results of the multiple industrial computers are transmitted to the central control system through the network communication. The test shows that the detection system can run stably and efficiently in the field and it can improve the automation degree of the print quality detection of medical aluminum foil.