8858 – Optimizing Bra Sizing According to the 3D Shape of Breasts

Cornell researchers have developed a 3D bra sizing method by evaluatingindividual breast shape. Specifically, this data system selects the mostappropriate human fit-models and offers customized recommendations based onconsumers’ body scans. This optimizedsizing system allows for constant updates and quick size recommendations byincorporating new data into the existing sizing system with the collection of3D body-scans for a target population. Our technique not only presents how tocreate a sizing system for bra, but also provides a solution on how to select themost representative fit-models or prototype shapes based on the 3D shape ofbreasts, rather than a combination of body measurements. A major change isunlike traditional breast measurements, this method describes the complex concavity,convexity and subtle fluctuations on the breast surface without involvement in placementof body landmarks. The key featureof this process is a series of evaluations based on a fit-loss function thatcalculates the dissimilarity between any two 3D body-scans via pointwise comparisionsof 9,000 location data sets on the layer-sliced breast scan surface. Shown inthe image above, A dissimilarity matrix constructed from filtered data of everybody-scan pair is used to estimate aggregate-fit-loss (AFL). Cluster analysis whichalso relys on the dissimilarity matrix is used for breast shape categorization(creating size groups). The within-group AFL is minimized by an algorithm thatreturns the optimal prototype for the assigned group while the overall AFL isreduced by optimal breast shape categorization. Our hydrid solution with theconstraint of band sizes allows a feasible integration to the current marketsizing system. This sizing method can be used for other types of apparelproducts as well, such as blouses, t-shirts and dresses. Aris Despo add74@cornell.edu 607-254-4698

Related Blog

Smart, interactive desk

Get ready to take your space management game to the next level with the University of Glasgow’s innovative project! By combining the

Mechanical Hamstring™

University of Delaware Technology Overview This device was created to allow athletes who suffer a hamstring strain to return to the field

Join Our Newsletter

                                                   Receive Innovation Updates, New Listing Highlights And More