Category: Discrimination between weed and crop via image analysis using machine learning algorithm
-
Conclusion
Agriculture plays a significant role in improving the economic condition of any country. The crop growth is reduced due to weeds. Earlier the weeds were detected manually, however it is a very expensive and time consuming process. Currently, weed detection is done by robotics, automatic sprayer and weed cutting are thus used. This kind of robotics…
-
Neural network classifier
The image data are trained through the convolution neural network. The input is given as the feature-based image which separates the weed and plants in the segmented image. The convolution operation is performed on the matrix of pixels and trained through extracted features. The two layers involved are fully connected and pooling layers. The pooling layer…
-
Support vector machine classifier
The machine learning algorithm of SVM is supervised method and used for both regression and classification problems. In SVM algorithm, given plot of image data with n number of features each feature belongs to a particular dimension. Here the two classes are distinguished as weed and as plant. The SVM is a linear hyper plane…
-
Feature extraction
The structure represents texture-based local properties of micro-texture and macro textures represent the spatial texture of narrow properties. These properties are not similar between the image pixels. The statistical features based method builds relationship among the gray levels. One-pixel based classifiers known as first order derivative and more than two pixels based classifier is known…
-
Proposed interval type II intuitionistic fuzzy c means with spatial triangular fuzzy number
This algorithm decreases various uncertainties in histopathology images. It comprises the following steps: This proposed algorithm detects the weed from various crop images by selecting GLCM features from segmented image. Segmentation of the weed from crops and soil in the input image properly. These results are shown in Figure 3.3. The weed and crops in same…
-
Image segmentation
Advanced fuzzy set theory is mostly used in real-time applications such as medical, satellite and agricultural field (Rani and Amsini 2019). In 1975, Zadeh pioneered another advanced fuzzy set called type II fuzzy set. Obviously, membership functions were defined by an expert based on his or her knowledge. These fuzzy set theories were applied to…
-
Image preprocessing
An image Z with M rows and N columns and its intensity level range is measured as a collection of fuzzy singletons. The intensity range is in between L, 0 to 1. The membership value μik with color intensity xn xm is considered. The contrast intensification operator was introduced by Zadeh in 1973. This operator is fully dependent…
-
Image acquisition
The dataset comprises 60 images and it is accessible online. These pictures are taken from real-time robot bonirob. The images are of carrot plants for detecting inter- and intra-weeds (Haug and Ostermann, 2014). All these images are taken for the processing and provide better results for detection of the areas of weeds and plants.
-
Literature survey
An exhaustive research was done on several papers describing various methods adopted for weed detection. These papers were summarized as follows. Image processing techniques and machine vision are broadly used in various fields such as agriculture industry or for detection of an object. The images are mathematically represented as rows and columns with red. So,…
-
Objectives of proposed work
Machine learning algorithms are used for plant differentiation and weed detection with accuracy. These algorithms are used in real-time applications of nondestructive analysis of image objects.