A CNN Based Hybrid Model Method for Image Segmentation in Similar Fusion Background Image

Abstract

In this study we propose a convolutional neural network (CNN) based hybrid model method to improve the image segmentation of similar fusion background images which means the features such as the color and texture of objects in the image are similar to the background This leads to errors in image segmentation using convolutional layers as feature extraction In order to address this problem we use the PyNET model to enhance the features of the objects and the background in the image and overlay this enhanced image with the original image according to a certain overlap weight By overlapping the image while retaining the features of the original image and the enhanced image the convolution layer can easily extract different features from the object and the background so that the object will not be ignored in the background In the experimental results this study will use the Intersection over Union (IoU) score as an criteria to evaluate the performance of the image segmentation models Our result shows that U-Net model got 20 % more than DeepLab got in the average score criterion

Date of Award	2020
Original language	English
Supervisor	Chin-Feng Lai (Supervisor)