?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.relation=http%3A%2F%2Fmiis.maths.ox.ac.uk%2Fmiis%2F670%2F&rft.title=Gabor+Filter+Selection+and+Computational+Processing+for+Emotion+Recognition&rft.creator=Coskun%2C+E.&rft.creator=Elson%2C+T.&rft.creator=Lim%2C+S.&rft.creator=Matthews%2C+J.&rft.creator=Morris%2C+G.&rft.creator=Nowaczyk%2C+N.&rft.creator=Raanes%2C+P.+N.&rft.creator=Wind%2C+D.+K.&rft.subject=Technology%2FDevices&rft.subject=Data+processing&rft.description=CrowdEmotion+produce+software+to+measure+a+person%E2%80%99s+emotions+based+on+analysis+of+microfacial+expressions+detected+using+a+webcam.+The+technology+relies+on+a+machine+learning+algorithm+to+recognize+which+features+correspond+with+which+emotions%3B+it+is+trained+on+a+labelled+dataset.+The+features+are+derived+by+applying+a+bank+of+Gabor+filters+to+a+set+of+frames%2C+determining+the+Local+Binary+Pattern+(LBP)+of+each+resulting+pixel%2C+and+then+averaging+the+results+over+three+orthogonal+planes+(TOP)%2C+as+outlined+in+%5B1%5D.+CrowdEmotion+challenged+the+study+group+to+improve+the+accuracy%2C+processing+speed+and+cost-efficiency+of+the+tool.+In+particular+they+wanted+to+know+if+a+subset+of+the+bank+of+Gabor+filters+was+sufficient%2C+and+whether+the+image+filtering+stage+could+be+implemented+on+a+GPU.+A+framework+for+choosing+the+optimum+set+of+Gabor+filters+was+established%2C+and+preliminary+testing+performed.+Different+ways+of+implementing+Gabor+filters+were+explored.+Some+ele-+ments+of+the+feature+set+give+little+information%2C+thus+ways+of+reducing+the+dimensionality+of+this+were+interrogated.+Some+steps+in+the+procedure+outlined+in+%5B1%5D+seemed+ad-hoc%2C+in+particular+when+taking+a+subset+of+LBPs+and+choosing+a+gridding+pattern+to+perform+the+TOP+step.+Taking+a+subset+of+LBPs+was+found+to+be+fully+justified.+Meanwhile+choosing+a+gridding+pattern+is+open+to+interpretation%3B+we+make+some+suggestions+on+how+this+choice+might+be+improved.+A+short+review+of+alternatives+to+using+a+SVM+as+a+classifier+is+presented.&rft.date=2014&rft.type=Study+Group+Report&rft.type=NonPeerReviewed&rft.format=application%2Fpdf&rft.language=en&rft.identifier=http%3A%2F%2Fmiis.maths.ox.ac.uk%2Fmiis%2F670%2F1%2Fesgi100-gabor-filter.pdf&rft.identifier=++Coskun%2C+E.+and+Elson%2C+T.+and+Lim%2C+S.+and+Matthews%2C+J.+and+Morris%2C+G.+and+Nowaczyk%2C+N.+and+Raanes%2C+P.+N.+and+Wind%2C+D.+K.++(2014)+Gabor+Filter+Selection+and+Computational+Processing+for+Emotion+Recognition.++%5BStudy+Group+Report%5D+++++