amit shah's profile - activity

I did not understand what you meant by normalize. What I did was simply use the landmark points obtained and used them to train SVM. How do you normalize them ? Tried using Linear and RBF kernel without noticing much improvement in the classification process. Also, is the landmark feature best way to recognize facial expression?

When I say not efficient, I meant it give false classification. Eg: Sad image was classified as being happy and so on. I used only the relevant landmark points for SVM training. I feel training it with something other than landmark points may prove better. Which alternative method should I follow ? Also, how do I use HOG or LBP features to train the model !

I am trying to extract all the skin pixels in the image. Images are not pre-known. They could be captured in various lighting conditions. The method that I currently use involves converting the image from RGB color space to YCbCr color space and classifying pixels as skin pixels if they happen to fall within certain range of Y, Cb and Cr.

Could someone suggest a better method ? Could converting image to HSV model prove useful ? If YCbCr is best color space to work in then what should the ranges for all the factors.

So basically in 5 one-against all, I will have 5 different SVM classifiers. The first classifier will check if the test-class belongs to class A. If it belongs to it, I will predict '1' else '0'. Same will happen for other SVM classifiers and at the end, the classifier having predicted value '1' will be selected. Am I correct ?

5 one-against all SVM? I dint quite get you!

Is it possible to have a single SVM classifier perform multi-class classification? Eg: If I have 5 classes say A,B,C,D,E with label 0,1,2,3,4 and if a single SVM classifier is trained for this data, then it will correctly label class B element with label 2. From what I read, it said that I will have to train multiple SVM binary classifiers and then predict label using One-to-All or One-to-One comparision. Could some one clear things for me?

Is there a way other than using FisherFace Algorithm to achieve it ? Can SVM be trained to achieve appropriate result ?

Is there some reference document to understand how does Deep Learning Technique work?

@berak: Tried using landmarks detected using dlib. These landmark locations along with the label coressponding to each image was fed to SVM and trained. It does not allow a very efficient model. Is there any other method which can be used ? How can LBP or HOG features be extracted for training model ?

@berak: thnak you so much! If feed wid side facing images, will it be capable of automatically landmarking the image ?

@berak: "you'd rather train an automatic landmark detector on images". How can that be achieved?

Does SVM training for facial landmark detection involve annotating the images(marking the images with landmark points) and feeding this data to SVM ? How many images ideally are enough for robust facial landmarking? How would the SVm behave if the images I used to train SVM where exactky half side faced and the testing image is more covered than the images used for training?

I am currently workin on profile faces. I want to be able to detect faces with side views. Is there a way other than having to use haarcascade_profileface.xml ? This cascade tends to have large false alarm rate. Besides, I want to learn some other technique to deal with it. The Facebook-tag people seems to be very much robust while detecting people with side views. Any algorithm which can achieve such robustness? My ultimate goal is to be able to determine emotions from side viewing faces if at all thats possible.

In any case do you know, how do I go about it ? Not enough information is available for it.

I am working on locatimg more landmark points. Will have a look at dlib. After I have detected the points, what do I need to train my SVM model with ? Is it that these points would prove better or should I feed in images directly ? Is there some tutorial to assist me with it.

I am using flandmark detector library to locate landmark points. Is there another way to locate them? Labelling is not an issue, bt how do I train the network? Is it using the location of these landmark points or entire images or with some other method. I saw suggestion that features extracted using HOG, LBP should be fed to SVM model. Could you suggest.

I am working on emotion detection with landmark points detected. I now want to train SVM for emotion classification(happy, angry, fear, ) with these landmark points and then make SVM capable of detecting emotion in images. Being a novice to SVM, I tried using a simple SVM example already available for OpenCV C++. It works for classification into either of two regions depending on the point location. Also, I expected a .xml file of trained model (eg: lbpcascade_frontalface.xml which is trained on LBP features is already available in opencv) to be generated for future use. But no such file was generated.

How do we generate such a file for future use ? And is it possible to classify images into various classes depending using SVM.