I am designing a classifier that takes as input features matrices of different dimensions, for example (Nx5, Nx10, Nx100, Nx1000) using visual bags of words of distinct dictionary sizes and methods (SIFT, SURF, ORB). Right now I am training one classifier for each combination of dictionary size and method to extract particular feature descriptions, but the task of fine-tuning all these classifiers is a bit tedious. Is there any method or process to combine such feature matrices into a unique classifier?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.