No self-introduction
Loading
Profile
Follow
codes (3)
Beer Label Classification for Mobile Applications
no vote
this code present an image processing algorithm for the automated identification of beer types using SIFT-based image matching of bottle labels. With a database of 100 beer labels from various breweries, our algorithm correctly matched 100% of corresponding query photographs with an average search time
of 11 seconds. To test the sensitivity of our algorithm, this code also collected and tested a second database of 30 labels from the same brewery. Remarkably, the algorithm still correctly classified 97% of labels. In addition to these results, we show that the SIFT-based recognition system is highly robust against camera motion and
camera-to-bottle distance.
alireza795673 1 0
1
Preprocessing and Descriptor Features for Facial M
no vote
Facial micro-expressions contain signi cant information about how people feel, even when they are at-
tempting to conceal their emotions. Previously, very little research has been done to detect and recognize
micro-expressions using computer vision methods.
In this code, detection and classi cation of microexpressions from the Spontaneous Micro-Expression database were implemented, following preprocessing and cropping of raw images using Haar features, using local binary patterns on three orthogonal planes (LBP-TOP) and local gray code patterns on three orthogonal planes (LGCP-TOP) as descriptors and support vector machines (SVMs) as detection and recognition algorithms. Results show accuracy comparable to other work.
alireza795673 3 0
1
forward and backward and viterbi hmm matlab code
no vote
Four good and test matlab mfile for forward and backward and viterbi algorithm in Hidden markov model % VITERBI Find the most-probable (Viterbi) path through the HMM state trellis. % path = viterbi(prior, transmat, obslik) % % Inputs: % prior(i) = Pr(Q(1) = i) % transmat(i,j) = Pr(Q(t+1)=j | Q(t)=i) % obslik(i,t) = Pr(y(t) | Q(t)=i) % % Outputs: % path(t) = q(t), where q1 ... qT is the argmax of the above expression. % delta(j,t) = prob. of the best sequence of length t-1 and then going to state j, and O(1:t) % psi(j,t) = the best predecessor state, given that we ended up in state j at t
alireza795673 0 0
1
No more~
Follows0
Fans0