Face verification using alexnet in Matlab

$10-30 USD

Anulowano

Opublikowano

około 6 lat temu

$10-30 USD

Płatne przy odbiorze

my solution is One thing we can do is to put two images side by side . and train the network as matched Vs unmatched. hope can get more 90% accuracy in test . The image database is already has . it contain image that is match and unmatch . Anyone can help me . Or any neural network method that can get 90% accuracy .

C Programming

Computer Science

Electrical Engineering

Electronics

Matlab and Mathematica

Identyfikator projektu: 16832557

Informację o projekcie

1 oferta

Zdalny projekt

Aktywny 6 lat temu

Szukasz sposobu na zarobienie pieniędzy?

Adres e-mail

Korzyści ze składania ofert na Freelancer.com

Ustal budżet i ramy czasowe

Otrzymuj wynagrodzenie za swoją pracę

Przedstaw swoją propozycję

Rejestracja i składanie ofert jest bezpłatne

1 freelancer składa ofertę o średniej wysokości $555 USD dla tej pracy

@camelserg

Hi, I have done some work in face recognition in the past, with neural networks. There are a couple of very promising new papers that may give the accuracy that you require but no implementation so far. The best one is by facebook research and it will take some time to implement it, but it basically is what powers (or used to power some iterations ago) facebooks face recognition. You mentioned that you have a database of images which consist of faces side by side, how large is it? Also you say that you need at least 90% accuracy on the test set, which in my experience is a very bad estimate of how a model performs. (it is very easy to overfit something to get 90% on test :) ) Another kind of big question I have is where is this going to be used. You need a matlab implementation which is okay, but I would not recommend using any matlab in production, so maybe we should think about some alternatives? (tensorflow, pytorch?) Hope we will work together!

$555 USD w 30 dni