Research Labs
Voice Signal Processing Laboratory


       This laboratory was established in 2005. Its main research directions are: signal enhancement, image recognition, fingerprint recognition, speech emotion recognition, voiceprint recognition, face recognition, flower recognition, FPGA-based H.264 CODEC (coder and decoder), and DSP-based parallel processing algorithm, etc. The research results have been successfully applied to the fields such as risk assessment of acute kidney injury, bladder cancer prognosis model, printing materials' quality inspection based on image processing, and machine vision-based three-dimensional object localization and control. By June 2018, a total of 36 graduate students have been cultivated, 4 programs of Natural Science Foundation of China, 1 program of Beijing Municipal Commission of Education Plan and 10 horizontal programs have been completed.


Computer School, Beijing Information Science and Technology University ©2013-2018