Inspired by hypotheses of how the brain processes images, researchers developed an automated framework for visual discovery and recognition of object categories, according to a study. Most existing object recognition programs rely on supervised training of algorithms using bounding boxes or object labeling of hundreds of images. However, the human brain learns to recognize objects in varied contexts without repeated training. Inspired by the brain's unsupervised learning ability, Thomas Kailath, Vwani Roychowdhury, and colleagues incorporated basic computational principles that the brain likely uses to perform visual recognition and developed Structural Unsupervised Viewlets Models (SUVMs) of various objects. The authors developed a series of viewlets, which are images depicting pieces of objects in different poses or orientations, together with a spatial map of how the pieces mesh together to create an entire object. The authors tested the SUVMs on two existing visual datasets. The face and human SUVMs recognized human faces correctly without false positives. The airplane SUVM performed less well, a result that the authors attribute to the relatively small number of training images presented. Adding relative probability to viewlets could increase the sensitivity of the models, which could be potentially applied to videos, according to the authors.
###
Article #18-02103: "Brain-inspired automated visual object discovery and detection," by Lichao Chen, Sudhir Singh, Thomas Kailath, and Vwani Roychowdhury.
MEDIA CONTACT: Thomas Kailath, Stanford University, Stanford, CA; tel: 650-494-9401; e-mail: profkailath@yahoo.com; Vwani Roychowdhury, University of California, Los Angeles, CA; tel: 310-206-4975; email: vwani@ee.ucla.edu
Journal
Proceedings of the National Academy of Sciences