Rank: 63 based on 882 downloads (last 30 days) and 10 files submitted
photo

Masayuki Tanaka

E-mail

Personal Profile:

http://like.silk.to/matlab/


 

Watch this Author's files

 

Files Posted by Masayuki Tanaka View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
10 Sep 2014 Screenshot Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka machine learning 387 57
  • 4.78947
4.8 | 23 ratings
06 Aug 2014 Screenshot Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka image processing, face, computer vision 252 78
  • 4.51852
4.5 | 30 ratings
18 Jul 2014 Screenshot Guided Upsampling and Residual Interpolation This tool upsamples the data with the high-resolution guidance image. Author: Masayuki Tanaka upsampling, image processing, filter 21 0
07 May 2014 Screenshot Noise Level Estimation from a Single Image It can precisely estimate noise level from a single image. Author: Masayuki Tanaka image processing, pick of the week, potw 96 12
  • 5.0
5.0 | 3 ratings
25 Nov 2013 Screenshot GUI Image Mask Sample It is a sample code to draw and erase mask on an image by GUI. It gives you hints to develop the GUI Author: Masayuki Tanaka gui, image processing, image 7 0
  • 2.0
2.0 | 1 rating
Comments and Ratings by Masayuki Tanaka View all
Updated File Comments Rating
07 Dec 2014 Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka

Hi rizwan,

You can get the eye's region by my code. Please try to find the eye corner with that region.

Thanks.

26 Nov 2014 Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka

Hi Salem,

For the object detection, I think that the convolution network is better. But, I hope this code also works for the object detection.

Thanks.

17 Nov 2014 Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka

Hi Meenakshi,

My code does not provide the region of the forehead. But, you may be able to estimate rough the region of the forehead with eyes and face regions’ information.

Thanks.

17 Nov 2014 Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka

Hi Nirmal,

I won’t consult on each specific problem.
If you have any bug, please report that. I will fix it if I have time…

Thank you!

14 Nov 2014 Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka

Hi Meenakshi,

I didn’t publish any technical paper. If you want to cite this work, please cite by the following url:
http://like.silk.to/matlab/detectFaceParts.html

I also share the slide on slide share.
http://www.slideshare.net/masayukitanaka1975/face-partsdetection

Thanks!

Comments and Ratings on Masayuki Tanaka's Files View all
Updated File Comment by Comments Rating
09 Dec 2014 Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka Marco

Hi Masayuki,
I find your toolbox very interesting but I have two separate issues.

First: if I run testDNN I get:
??? Error using ==> randperm
Too many input arguments.

Error in ==> pretrainRBM at 172
p = randperm(dimV, DropOutNum);

Error in ==> pretrainDBN at 88
dbn.rbm{i} = pretrainRBM(dbn.rbm{i}, X, opts);

Error in ==> testDNN at 21
dnn = pretrainDBN(dnn, IN, opts);

Secondly, I've tried to write a script of mine following your nice helps but it seem not to be working correctly. It always chose class one no matter what. Actually

pretrainDBN(dbn, train_data, opts);

returns a first layer that does not learn anything. I mean no matter the size the answer always look like this (now 3 iterations just for sake of space)

1 : 57.8774 0.7509
2 : 57.8774 0.7656
3 : 57.8774 0.7656
1 : 0.4938 0.4939
2 : 0.4846 0.5583
3 : 0.4719 0.6207

Which seem strange when the N of neurons of the autoencoder is set equal to the N_ of inputs.

Could you please help me with this?

p.s. here is the script except for the data loading part

% Sets variables
datanum = size(train_data,1);
outputnum = size(train_target,2);
inputnum = size(train_data,2);
hiddennum = 32;

opts.Verbose = true;
opts.MaxIter = 10;

dbn = randDBN([192 192 11], type);
dbn2 = pretrainDBN(dbn, train_data, opts);
dbn3 = SetLinearMapping(dbn2, train_data, train_target);
dbn4 = trainDBN(dbn3, train_data, train_target);

train_estimate = v2h(dbn4, train_data);
[~,CM,~,~] = confusion(train_target', train_estimate')
test_estimate = v2h(dbn4, test_data);
[~,CM,~,~] = confusion(test_target', test_estimate')

07 Dec 2014 Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka Masayuki Tanaka

Hi rizwan,

You can get the eye's region by my code. Please try to find the eye corner with that region.

Thanks.

06 Dec 2014 Face Parts Detection It detects faces with left eye, right eye, mouth, and norse. Author: Masayuki Tanaka rizwan ali naqvi

Hello Massayuki Tanaka,

I am interested in extracting bounding boxs of left and right eyes. how I can extract it actually I am interested in eye corner detections by using standard detection techniques but I am facing difficulty in accessing eyes bounding box except nose and mouth. I have seen your reply that you have given on 24 july 2013 but it is not working in my case. I want to apply harris corner detection only on eyes. Please reply me on my email id: naqvirizwan@yahoo.com

Waiting for your kind reply.

Thanks in advance.

26 Nov 2014 Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka Salem

Hi Masayuki,
Thanks for replying, I have my own data set. Therefore, I applied this code to it and the result was an excellent, much better than Conv. Neural Networks. I want to go through the implementation again because the result is something incredible and I want to make sure I have implemented in the correct way. Thanks again for sharing the code.

26 Nov 2014 Deep Neural Network It provides deep learning tools of deep belief networks (DBNs). Author: Masayuki Tanaka Masayuki Tanaka

Hi Salem,

For the object detection, I think that the convolution network is better. But, I hope this code also works for the object detection.

Thanks.

Contact us