# CEDAR Document Recognition **Entity class:** Research center / postal document analysis ## Definition and history CEDAR, the Center of Excellence for Document Analysis and Recognition at the University at Buffalo, developed handwritten-address interpretation for the U.S. Postal Service. [[articles/Intelligence Inside|Intelligence Inside]] separates its HWAI work from SRI's address-recognition deployment rather than merging both under an undifferentiated postal AI story. Sargur Srihari was principal investigator in the CEDAR work described by the university. The postal problem joined image recognition to address interpretation and routing in a national operational system. ## Mechanism and limits A handwritten address contains visual variation that ordinary printed-character recognition struggles to normalize. Interpretation must extract candidate words and reconcile them with plausible destination information before a sorting decision follows. Deployment inside the Remote Computer Reader gave the research a specific processing place rather than a merely laboratory demonstration. ## Relationships **Institution:** [[wiki/University at Buffalo|University at Buffalo]]. **Principal investigator:** [[wiki/Sargur Srihari|Sargur Srihari]]. **Built:** [[wiki/Handwritten Address Interpretation|Handwritten Address Interpretation]]. **Different program:** [[wiki/SRI Postal Address Recognition|SRI Postal Address Recognition]]. **Article route:** [[articles/Intelligence Inside|Intelligence Inside]]. ## Sources [University at Buffalo, Pioneers in AI Systems](https://www.buffalo.edu/cubs/research/pioneers-in-ai-systems.html); [[articles/Intelligence Inside|Intelligence Inside]].