Abstract Image segmentation is the critical step in the process of object recognition in digital image

processing. It segments the overall image into different regions so that their description can be used to
identify different objects in an image. The quality of object recognition depends upon the quality of
segmentation. This paper proposes a novel approach to segment an image. Unlike traditional approaches
which does classification after segmentation, our method repeatedly takes output of classification as the
basis for image segmentation.

Lime library: https://eli5.readthedocs.io/en/latest/blackbox/lime.html

Pre processing:
Using keras preprocessing

https://keras.io/preprocessing/image/

Segmentation
skimage.segmentation import mark_boundaries

Classification
neural networks model
#inet_model = inc_net.InceptionV3()
inet_model = inc_net.InceptionV3(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None, pooling=None, classe
s=1000)

InceptionV3
https://medium.com/@sh.tsang/review-inception-v3-1st-runner-up-image-classification-in-ilsvrc-2015-
17915421f77c

flowchart