A New Shape Feature Extraction Method for Leaf Image Retrieval

Vijayalakshmi, B.

doi:10.1007/978-81-322-0997-3_22

Cited by 6 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the first phases in automatic plant identification is to extract a set of features from leaves (after some pre-processing on images). In spite of many descriptors based on the shape, color, texture and veins of leaves [18,3,4,5,11,12,16] have been proposed in last decade, little attention has been paid to develop new methods to make an automatic distinction between the different types of leaves, such as unlobed, lobed, simple and compound. This categorization of leaves is important, and it is usually used in dichotomous keys for classic plant identification, see for example [14,2,9,17,15].…”

Section: Introductionmentioning

confidence: 99%

Automatic Classification of Lobed Simple and Unlobed Simple Leaves for Plant Identification

Flores-Bastida¹,

López-Chau²,

Rojas-Hernández³

et al. 2017

RCS

View full text Add to dashboard Cite

Commonly, classic plant identification methods use dichotomous or multi-access keys that compare characteristics of the leaves, asking if they are lobed, unlobed, simple or compound, among others leaf features. However, in the literature very little attention has been paid to make an automatic distinction of leaves using such features. In this paper, we contribute to fill this gap. We propose a novel method to differentiate between types of leaves. The proposal is invariant to rotation and also to scaling. In order to show the effectiveness of the proposal, we tested it with more than 1,900 images of leaves which are publicly available on the Internet, achieving correct identification rates greater than 86%.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Classification of Lobed Simple and Unlobed Simple Leaves for Plant Identification

Flores-Bastida¹,

López-Chau²,

Rojas-Hernández³

et al. 2017

RCS

View full text Add to dashboard Cite

show abstract

Feature Extraction and Recognition Based on Machine Vision Application in Lotus Picking Robot

Tang

Zhao

Jia

et al. 2016

Computer and Computing Technologies in Agriculture IX

View full text Add to dashboard Cite

Recently the picking technology of high value crops has become a new research hot spot, and the image segmentation and recognition are still the key link of fruit picking robot. In order to realize the lotus image recognition, this paper proposes a new feature extraction method combined with shape and color, and uses the K-Means clustering algorithm to get lotus recognition model. Before the feature extraction, the existing pulse coupled neural network segmentation algorithm, combined with morphological operation, is used to achieve nice segmentation image, including lotus, lotus flower, lotus leaf and stems. Then in the feature extraction processing, the chromatic aberration method and the moment invariant algorithm are selected to extract the color and shape features of the segmented images, in which principal component analysis algorithm is selected to reduce the dimension of the color and shape features to achieve principal components of lotus, lotus flower, lotus leaf and stems. In the experiment, K-Means clustering algorithm is used to get lotus recognition model and four clustering centers according to above principal components of training samples about lotus, lotus flower, lotus leaf and stems; then the testing experiment is applied to validate the recognition model. Experimental results shows that the correct recognition rate is 90.57% about 53 testing samples of lotus, and the average recognition time is 0.0473s, which further indicates that the feature extraction algorithm is applicable to lotus feature extraction, and K-Means algorithm is simple, reliable and feasible, providing a theoretical basis for positioning and picking of lotus harvest robot.

show abstract