Image-Segmentation-using-SVM

Dataset:-

Dataset consists of images of cats and dogs with their respective semantic segmented images

Support Vector Machines

Support Vector Machine” (SVM) is a supervised machine learning algorithm that can be used for both classification or regression challenges. However, it is mostly used in classification problems. In the SVM algorithm, we plot each data item as a point in n-dimensional space (where n is a number of features you have) with the value of each feature being the value of a particular coordinate. Then, we perform classification by finding the hyper-plane that differentiates the two classes very well.

How i used SVM for this data?

In simple words I treated the pixels of the semantic segmented representing the dogs or cats as one class and the background as another class and used SVM to classify those classes for us

Training Support Vector Machine model on the Oxford iiit pets dataset

Train and Test predictions using cat_image_segmentation_model(1).sav and dog_image_segmentation_model(1).sav