Plant classification method based on sparse expression dictionary learning

Abstract

The invention relates to a plant classification method based on sparse expression dictionary learning. The method is technically characterized by comprising the following steps: performing parameter initialization, wherein the parameter initialization comprises arranging the size, a sparse limitation factor and an error tolerance parameter of each plant type dictionary; for a training sample of each type of plant blade images, obtaining an over-complete dictionary of each type of blade images by use of a K-SVD algorithm; splicing the over-complete dictionary of each type of blade images after training to form a redundancy dictionary, and performing normalization processing on each column of the redundancy dictionary; obtaining a sparse coefficient through solving a minimum norm; and calculating residual errors and selecting a corresponding sample type with a minimum difference as a final identification result of a sample to be identified. According to the invention, the over-complete dictionaries are solved by use of type-based dictionary learning and sparse representation of an image to be identified is calculated, such that the calculation time of an algorithm is reduced, the requirement for real-time performance is met, the obtained identification rate is quite high, and the average identification rate is as high as more than 95%.

Description

technical field

[0001] The invention relates to the technical field of computer image processing, in particular to a plant classification method based on sparse representation dictionary learning. Background technique

[0002] To protect the living environment of human beings, we must protect plants; to protect plants, we must first understand plants. For plant classification, plant leaves, flowers, fruits, stems, bark, and even tree roots are the basis for plant classification. Each of these features has its own classification value. Compared with other organs of plants, because the color, texture and shape of the leaves are relatively stable, and they are not very sensitive to changes in temperature and seasons, and more importantly, the survival time of plant leaves is longer, during most of the year It can be collected more conveniently, so it is often used as the identification feature of plants and the main reference organ for understanding plants. Therefore, classif...

Examples

Embodiment Construction

[0041] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0042] A plant classification method based on sparse representation dictionary learning, comprising the following steps:

[0043] Step 1. Initialize parameters: set the size K of each plant category dictionary, the sparse limit factor δ and the error tolerance parameter ε.

[0044]Taking the plant leaf image database including 20 different plant categories as an example, the dictionary learning is performed on the training set samples composed of each plant, and a super-complete dictionary D of each plant leaf image is constructed. 1 ,D 2 ,...,D 20 . According to the influence of parameter selection on the recognition algorithm during dictionary learning, over-complete dictionaries with different dictionary sizes K and sparse limiting factor δ were selected for plant classification experiments. In fact, when δ takes different values, there is l...

technical field

[0001] The invention relates to the technical field of computer image processing, in particular to a plant classification method based on sparse representation dictionary learning. Background technique

[0002] To protect the living environment of human beings, we must protect plants; to protect plants, we must first understand plants. For plant classification, plant leaves, flowers, fruits, stems, bark, and even tree roots are the basis for plant classification. Each of these features has its own classification value. Compared with other organs of plants, because the color, texture and shape of the leaves are relatively stable, and they are not very sensitive to changes in temperature and seasons, and more importantly, the survival time of plant leaves is longer, during most of the year It can be collected more conveniently, so it is often used as the identification feature of plants and the main reference organ for understanding plants. Therefore, classif...

Examples

Embodiment Construction

[0041] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0042] A plant classification method based on sparse representation dictionary learning, comprising the following steps:

[0043] Step 1. Initialize parameters: set the size K of each plant category dictionary, the sparse limit factor δ and the error tolerance parameter ε.

[0044]Taking the plant leaf image database including 20 different plant categories as an example, the dictionary learning is performed on the training set samples composed of each plant, and a super-complete dictionary D of each plant leaf image is constructed. 1 ,D 2 ,...,D 20 . According to the influence of parameter selection on the recognition algorithm during dictionary learning, over-complete dictionaries with different dictionary sizes K and sparse limiting factor δ were selected for plant classification experiments. In fact, when δ takes different values, there is l...

Images