Age Detection by NN trained LBP features

(57 customer reviews)

$0.00

Total downloads: 283

This Repository is designed to detect the age from an image using LBP features. The Neural network is used as a classifier for it.  FGNET database is used which has 1002 sample images of different objects at different ages. The number of samples in each class is highly non -uniform. So the data is oversampled first and then trained.

This Repository contains the MATLAB code:

  • age detection using neural network
Download Test
 Discuss Code

Description

The neural network in machine learning facilitates automation in image processing facilities which is either number plate recognition, face detection, expression recognition, joining images at different exposures etc. It also eases the task to recognize and verify the ages from the images which help in passports and other related applications. This MATLAB code for age detection from images contributes towards that fact. We developed this code at free-thesis. We used FGNET aging dataset for the features generation and testing. Though testing also worked on other images that don’t have covered faces by sunglasses or by any other means. The complete pipeline is like this:

Age detection by Neural Network
Age detection by Neural Network [free-thesis]
The features are extracted by Local binary feature extraction. MATLAB has a toolbox for that.

files=dir('./FGNET/images');
for ii=3:size(files,1)
    imgname=files(ii).name;
    img=imread(['./FGNET/images/',imgname]);
    if size(img,3)==3
        img=rgb2gray(img);
    end
    features(ii,:) = extractLBPFeatures(img);
end

After extracting features we had a matrix of dimension 1002*20 where each row represents every image in the database. The interesting step in the whole pipeline is the features pre-processing. The whole database is divided into eight different age groups, which makes this data highly imbalanced as shown in figure 2.

Dataset distribution in each age group class
Dataset distribution in each age group class[free-thesis]
We had the highest number of samples in class 1 and non-competitive very few numbers of samples in other classes. Training the neural network using this dataset would be highly biased and the same class would be predicted with every different test image. To avoid this, this data is made balanced with the help of SMOTE algorithm. This was developed for binary classes. In it, the classes with less number of samples are oversampled to balance the distribution and we tweaked this algorithm to make it suitable for multiclass data.

The difference in the number of samples from the major class is used to balance for every class. The code snippet for this is as

%add on samples will be calculated by taking the difference of each
%classSamples with highest number of class samples

[maximumSamples,sampleClass]=max(classNo); % number of maximum samples
for ii=1:numel(class)
    samplediff(ii)=maximumSamples-classNo(ii);
    N (ii) = ceil(samplediff(ii)/ 100);
    
end

The samples distribution in each class after the SMOTE algorithm is shown in the figure.

Balanced data distribution after SMOTE
Balanced data distribution after SMOTE [free-thesis]
We recommend users to read the SMOTE in detail here.

 

57 reviews for Age Detection by NN trained LBP features

  1. admin (verified owner)

    Thanks

  2. Anonymous

    it helped me to kickstart

  3. Anonymous

    LETS CHECK THE SERVICES PROVIDED BY YOU

  4. chandra.jonala (verified owner)

    Thank you

  5. chandra.jonala (verified owner)

    Thank you

  6. aaaaa.aaaaaa (verified owner)

    nice

  7. john.doe (verified owner)

    Easy

  8. morteza (verified owner)

    good

  9. neha.baruah (verified owner)

    good

  10. garba.abdulrauf (verified owner)

    Thank you

  11. enireddy.vamsidhar (verified owner)

    good site for researchers

  12. akarsh.simha (verified owner)

    Good projects

  13. venkat.reddy (verified owner)

    great

  14. venkat.reddy (verified owner)

    great

  15. waseem.sajjad (verified owner)

    Good for thesis

  16. abhishek.mishra (verified owner)

    nice site for reference

  17. abhishek.mishra (verified owner)

    nice site for reference

  18. abhishek.mishra (verified owner)

    nice site for learning

  19. ankush.chaudhary (verified owner)

    Good

  20. divya.punia (verified owner)

    great

  21. garba.abdulrauf (verified owner)

    Thank you this code is very useful.

  22. kaif.lodi (verified owner)

    good

  23. vankani.arjun (verified owner)

    Nice project !!

  24. ernesto.garcia amaro (verified owner)

    .

  25. sameer.kumthekar (verified owner)

    best one

  26. samarpit.sahoo (verified owner)

    thanks

  27. satrughan.kumar (verified owner)

    well suported content

  28. ratheesh.p m (verified owner)

    Very Helpful

  29. ratheesh.p m (verified owner)

    Very Useful

  30. heriansyah.najemi (verified owner)

    verygood

  31. rupali.jumbadkar (verified owner)

    i am doing research in age detection so I need this code….thankyou

  32. rupali.jumbadkar (verified owner)

    thanks

  33. arun.s (verified owner)

  34. yousef.qudeisat (verified owner)

    thank you

  35. yousef.qudeisat (verified owner)

    thanks alot

  36. thiyagarajan.n (verified owner)

    good

  37. thiyagarajan.n (verified owner)

    good

  38. thiyagarajan.n (verified owner)

    good

  39. thiyagarajan.n (verified owner)

    good

  40. chou_aib (verified owner)

    Great

  41. alaoui.alaoui (verified owner)

    goog

  42. krisma.ziliwu (verified owner)

    how

  43. satrughan.kumar (verified owner)

    thanks

  44. mokhtar.besseghier (verified owner)

    nice

  45. bijoy.harun (verified owner)

    Good process system. It is helpful.

  46. bijoy.harun (verified owner)

    It is helpful.

  47. sujin.kumar (verified owner)

    nice

  48. sujin.kumar (verified owner)

    hfg

  49. sujin.kumar (verified owner)

    hfg

  50. sujin.kumar (verified owner)

    hfg

  51. sujin.kumar (verified owner)

    jklj

  52. panduranga.terlapu (verified owner)

    GOOD

  53. panduranga.terlapu (verified owner)

    GOOD

  54. sagar.verma (verified owner)

    good

  55. e1w.w (verified owner)

    33

  56. razmig.avedis (verified owner)

    Thank You

  57. sm.rs (verified owner)

    very good

  58. aditi (verified owner)

    thankyou for the help

  59. ftafta

    thank you so much

Only logged in customers who have purchased this product may leave a review.

No more offers for this product!