China
Africa
Explore chapters and articles related to this topic
Recognition and categorization of plant from leaf image using visual traits
Published in Rajesh Singh, Anita Gehlot, Intelligent Circuits and Systems, 2021
The classification is done by classifiers. It classifies the input images in one of the leaf class by comparing the input image features with feature vectors dataset prepared as the output of the training. In this research paper, for the purpose of classification and identification probabilistic neural network (PNN) [5,18], support vector machine (SVM) [19–21], artificial neural network with training algorithm gradient descent (GD) and scalar conjugate gradient (SCG) have been implemented. Recognition is identification of the object in the input image. Recognition has been performed in this research work with the use of the SVM and PNN classifiers. The testing image is the input given to the trained classifier and the obtained output is the plant name.
Machine Learning
Published in Pedro Larrañaga, David Atienza, Javier Diaz-Rozo, Alberto Ogbechie, Carlos Puerto-Santana, Concha Bielza, Industrial Applications of Machine Learning, 2019
Pedro Larrañaga, David Atienza, Javier Diaz-Rozo, Alberto Ogbechie, Carlos Puerto-Santana, Concha Bielza
For classification, unseen instances are sorted down the tree from the root to one of the leaf nodes according to the outcome of the tests along the path. The predicted class is found at the leaf. Each path from the root of a classification tree to one of its leaves can be transformed into a rule (see Section 1.4.7) by simply conjoining the tests along the path to form the antecedent part of the rule and taking the leaf class prediction to form the consequent of the rule. Thus, the tree represents a disjunction of variable value conjunctions.
A total sales forecasting method for a new short life-cycle product in the pre-market period based on an improved evidence theory: application to the film industry
Published in International Journal of Production Research, 2021
Step 2. Construct the weak regression tree. The activities are as follows: Initialise a weak regression tree. A CART (Classification and Regression Tree) is selected as a basis function to generate a weak regression tree.Select a class node for each input value. The Gini index is used as the standard measure for non-leaf class node classifications.Class and form leaf nodes. Repeat the above two activities for all new input values to form leaf nodes until a termination condition is satisfied.Prune to get leaf nodes. A threshold value is set in advance. For two nodes with the same parent node, calculate the loss function of the current tree and of another tree that shrinks back to the parent node. If the loss function of the tree after retraction is small, then prune the tree, and replace the parent node by using the child node to establish a new leaf node.
Cognitive framework and learning paradigms of plant leaf classification using artificial neural network and support vector machine
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2022
Gajanand Sharma, Ashutosh Kumar, Nidhi Gour, Ashok Kumar Saini, Aditya Upadhyay, Ankit Kumar
X. Yang et al. present an ANN classification for identifying the precise leaf class by extracting shape, colour, and texture features from leaf images using the proposed method. The test results for six different classes are 63 leaf images (Yang et al., 2020).