What are training Images?

How to train images using classifiers?

Answer 1

[Walter Roberson]

Training images are a bunch of images for which the required outcome is known. You input them to a program that analyzers their features and passes the features through a classification routine that determines the appropriate weights to use on the features in order to best achieve the required result.

Once you have used the training images to determine the best weights and procedures to follow, you then pass through a set of "test" images, for which you also know the outcome. The images are extracted and the procedures and weights determined above are applied to make a prediction of how the image should classify. Then the predicted classification is compared to the actual known classification to determine how well the procedures and weights do on analyzing data that was not originally used to determine the weights. If you got a high score on the training images but a low score on the test images then the implication is that the routine "overtrained" and has become too specific to the training images and not able to predict for images whose results are not known.

Once you are getting good scores on the training images and good scores on the test images as well, you can start using the procedures and weights to analyze data for which the outcome is not known.

[sheeza rafaqat]

Is there any code available which can help me in understanding training and testing images??

[Walter Roberson]

Could you expand on what you hope to learn?

[sheeza rafaqat]

i have my final year project on object detection and identification for which i have to create a database of some images and do training and testing for those images..kindly help me in this regard.. thanks in advance

[Walter Roberson]

If you use a CNN then all you need to input are the training images and the class labels (but CNN are not as fast as if you extract features based upon something that you know to be true about the kinds of objects you are looking for.)

[Mansa Murthy]

hii .. my project is detection of diabetic retinopathy. i have completed uptill feature extraction. Now i dnt know how to train datasets using svm. Can you pleas help?

which values are to be fed into classifiers and how they are generated?

[Walter Roberson]

Well, that's the catch: no-one knows what features are the best ones to extract for classification. What some people have done is tried a whole bunch of different features, and done feature selection to figure out which of the features is most important (one the images they trained on) and used those features. But there might be a different set of features that would be even better.