Plant Classification in Images of Natural Scenes Using Segmentations Fusion

Authors

  • H. Agahi Department of Mathematics, Faculty of Basic Science, Babol Noshirvani University of Technology, Babol, Iran
  • N. Nikbakhsh Department of Electrical & Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
  • Y. Baleghi Damavandi Department of Electrical & Computer Engineering, Babol Noshirvani University of Technology, Babol, Iran
Abstract:

This paper presents a novel approach to automatic classifying and identifying of tree leaves using image segmentation fusion. With the development of mobile devices and remote access, automatic plant identification in images taken in natural scenes has received much attention. Image segmentation plays a key role in most plant identification methods, especially in complex background images. Where there are no presumptions about leaf and background, segmentation of leaves in images with complex background is very difficult. In addition, each image has special conditions, so parameters of the algorithm must be set for each image. In this paper, image segmentation fusion is used to overcome this problem. A fast method based on maximum mutual information is used to fuse the results of leaf segmentation algorithms with different parameters. Applying Tsallis entropy and g-calculus, generalized mutual information equations are derived and used to obtain the best consensus segmentation. To evaluate the proposed methods, a dataset with tree leaf images in natural scenes and complex backgrounds is used. These images were taken from Pl@ntLeaves dataset and modified so that they do not have a presumption. The experimental results show the use of Tsallis entropy and g-calculus in image segmentation fusion, improves plant species identification.

Upgrade to premium to download articles

Sign up to access the full text

Already have an account?login

similar resources

Nonhomogeneous resolution of images of natural scenes.

The aim of this research is to model and simulate the loss of visual resolution as a function of retinal eccentricity in the perception of natural scenes. The model of visual resolution is based on a space-variant low-pass filter, having a variable convolution kernel according to retinal eccentricity. The parameters of the model are computed from psychophysical measures of visual acuity as a fu...

full text

Visual sensitivity to color errors in images of natural scenes.

Simple color-difference formulae and pictorial images have traditionally been used to estimate the visual impact of color errors introduced by image-reproduction processes. But the limited gamut of RGB cameras constrains such analyses, particularly of natural scenes. The purpose of this work was to estimate visual sensitivity to color errors introduced deliberately into pictures synthesized fro...

full text

Improving Text Recognition in Images of Natural Scenes

IMPROVING TEXT RECOGNITION IN IMAGES OF NATURAL SCENES

full text

Classification of Ultra-high Resolution Images using Soft Computing

The main objective of this paper is to use a computational intelligence algorithm for preparing a mapping map that categorizes different patterns of identification of infected areas and changes in radiation pollution. In this paper, the use of the fuzzy inference system has been proposed to determine the degree of radiation contamination in the regions. The study uses ultra-high resolution spec...

full text

Inferring Depth from Single Images in Natural Scenes

The inverse optics problem is one of the oldest and most well known problems in visual perception. Inferring the underlying sources of visual images has no analytic solution. Recent work on brightness, color, and form has suggested that visual percepts represent the probable sources of visual stimuli and not the stimuli as such, suggesting an empirical theory of visual perception. Here I explor...

full text

My Resources

Save resource for easier access later

Save to my library Already added to my library

{@ msg_add @}


Journal title

volume 33  issue 9

pages  1743- 1750

publication date 2020-09-01

By following a journal you will be notified via email when a new issue of this journal is published.

Hosted on Doprax cloud platform doprax.com

copyright © 2015-2023