13 Questions 13 Answers 0 Followers
Questions related from Farhad Bulbul
Hi All, I wanna convert an image its binary coded form which is typically done by LBP operator. But I need to use algorithms different than LBP. Could anyone kindly can suggest algorithms to...
05 February 2020 9,976 3 View
Hi All, How to improve the action recognition accuracy using the vgg16 features? Is there any way to improve the features?
27 December 2019 2,868 3 View
Hi, I need to know the computational complexities to extract the texture feature from an image using the Wavelet Transform . Also, I should know the limitations of Wavelet while it captures...
30 November 2018 3,409 1 View
Hi All, I've herein attached a configuration of a PC for deep learning. Please see this one and ask me whether this configuration is perfect or not regarding the deep learning phenomena.
18 March 2018 7,113 7 View
Hi All, I've developed an action recognition algorithm using depth action sequences. I wanna implement the algorithm in a surveillance camera which captures rgb videos. Would the algorithm be...
18 February 2018 1,903 3 View
I'm facing a problem to building the exe file using MATLAB compiler. Please see the attached stuff and help me to fix the bug!
24 September 2017 3,975 1 View
Hi, Just after one level wavelet decomposition I can get edge information, which can be used as a feature. So why do I need to make two, three... more level wavelet decompositions? Moreover, due...
06 December 2014 2,087 8 View
Hi, I have a 16 by 16 image. Can I take 9 cells to compute HOG? How would the cell size be here? Is every cell different in size? Please clarify.
02 December 2014 3,912 1 View
Hi, What is the difference between depth and RGB-depth images? What is meaning of depth information in depth images? How to get depth and RGB depth image using camera? Please give some materials...
27 November 2014 6,820 5 View
Hi, Could someone inform me about the weight vector in SVM?
23 November 2014 2,591 6 View
Hi, I am doing human activity recognition. In my task, feature scaling gives low accuracy, rather than keeping original feature values. But my feature values are not in either [-1 1] or [0 1]. So,...
19 November 2014 8,764 5 View
Hi, I have training samples 4611x4096. Where number of samples = 4611 and number of features = 4096. Now, I want to apply Block circulant decomposition methods to improve my detection results. But...
13 November 2014 10,064 1 View
Hi, I want to use feature selection and feature extraction method both before classification. Do I apply feature selection first and then feature extraction or reverse? Please let me help.
11 November 2014 8,527 12 View