Recognition procedure for identifying multiple items in images

作者: Sri Kaushik Pavani , Jorge Moraleda , Anshul Garg

DOI:

关键词: Artificial intelligenceFeature detection (computer vision)Automatic image annotationFeature (computer vision)Image (mathematics)Region of interestImage matchingPattern recognitionMathematicsImage textureSet (abstract data type)

摘要: The disclosure includes a system and method for identifying multiple items in an image. A image recognition application receives (602) query of items, computes (604) features the image, each feature finds indexed with closest matched database, determines (608) that shape is geometrically consistent, (610) whether matches responsive to matching returns inliers, region interest where match was found removes inliers from set reduce (616) all when fails

参考文章(10)
Laura Pennino, Gianguido Rizzotto, Federico Travaglia, Rinaldo Poluzzi, Massimo Mancuso, Fuzzy logic device for image noise reduction ,(1995)
Agata Opalach, Fredrik Linaker, Andrew Fano, Robert Bernard Robin Groenevelt, Planogram extraction based on image processing ,(2008)
Agata Opalach, Fredrik Linaker, Andrew Fano, Robert Bernard Robin Groenevelt, Detection of stock out conditions based on image processing ,(2007)
Alexander Ring, Craig Hamilton, Wayne Spencer, Method and system for automatically measuring retail store display compliance ,(2006)
Deepak Khosla, David J. Huber, Method for recognition and pose estimation of multiple occurrences of multiple objects in visual images Proceedings of SPIE. ,vol. 8049, pp. 804903- ,(2010) , 10.1117/12.883584
Michele Sassano, Pier Paolo Campari, Marco Dini, Andrew E. Fano, Simone Morandi, Digital point-of-sale analyzer ,(2010)
Keshav Menon, Gurumurthy D. Ramkumar, Sunil Ramesh, Max Delgadillo, Method and system for image matching ,(2010)