Вопрос

I have calculated texture, color and shape features on an image.But those just add up to 12 features. I read that people extract 1000 features and such. Could someone please explain to me how do i increase the number of features? And then how do i save them to form a feature vector?

Это было полезно?

Решение

Features are the most significant or interest points of an image.In general lets say I am interested in the edges information of an image.As we know edges are found by laplacian filter in spatial domain so the only points that will remain in the image will be edges point.Each edge point will have its x,y co-ordinate followed by intensity value.These three information of all the interest points would probably lead to multi-dimension feature vector in this case which would be depend on the type of image you are taking.These three multidimensional information will be called my feature vector.

Similarly histogram of an image can also be your feature which will range from 0 to 255 value for an gray scale image.So in that case you can store for every image this 255 values as features.

Hope you got the idea.Image is an subjective thing so depending on any application and given data set we will extract features and form feature vectors.

Apart from color,texture and shape you can even work on the signatures,edges,histogram and so on properties of an image.

Лицензировано под: CC-BY-SA с атрибуция
Не связан с StackOverflow
scroll top