Research on weed recognition method based on invariant moments

Zhao, Bo; Hua, Wu; Jun, Li Shu; Hua, Mao Wen; Chao, Zhang Xiao

doi:10.1109/wcica.2014.7053057

Cited by 5 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed technique has also reached maximum classification accuracy rates that outperformed most of the methods included in the comparison table. It can also be seen that the classification accuracy has outperformed DMF and ZMI approaches in [12] and CCD method in [14] including the minimum accuracy rates recorded over 100 runs for the equivalent fold numbers.…”

Section: Performance Comparisonmentioning

confidence: 82%

See 1 more Smart Citation

Automated Leaf Alignment and Partial Shape Feature Extraction for Plant Leaf Classification

Hamid

Al-Haddad

2019

ELCVIA

View full text Add to dashboard Cite

The last few decades have witnessed various approaches to automate the process of plant classification using the characteristics of the leaf. Several approaches have been proposed, and the majority focused on global shape features. However, one challenge that faces this task is the high interclass similarity amongst the leaves of different species in terms of the global shape. Furthermore, there always has been an obstacle against full automation as several approaches require user intervention to align the leaf. Therefore, a new set of Quartile Features (QF) is proposed in this paper to describe the partial shape of the leaf, in addition to an automated alignment approach to automate the system. The QF are extracted from the horizontal and vertical leaf quartiles to describe the partial shape of the leaf and the relations among its parts. The well-known Flavia dataset has been selected for the evaluation of the proposed system. The experimental results indicate the ability of the proposed alignment algorithm to align leaves with different shapes and maintain a correct classification accuracy regardless of the orientation of the input leaf samples. Furthermore, the proposed QF indicated promising results by increasing the accuracy of the classification by a range of approximately 26% to 30% when combined with Hu's Moment Invariants, using k-fold cross-validation technique.

show abstract

Section: Performance Comparisonmentioning

confidence: 82%

“…In [12], MI are combined with Centroid Radii to classify 3 types of plants. MI are also employed in [13] as an input to an SVM classifier, and in [14] to differentiate the weed from the crop using a Nearest Neighbor Classifier (1-NN). Zernike Moment Invariants (ZMI) are another category of invariant moments.…”

Section: Related Workmentioning

confidence: 99%

Automated Leaf Alignment and Partial Shape Feature Extraction for Plant Leaf Classification

Hamid

Al-Haddad

2019

ELCVIA

View full text Add to dashboard Cite

show abstract

“…The main objective was to achieve appropriate discrimination between the two weed groups under varying conditions of lighting and soil background texture. Bo et al [7] introduced a novel method of weed recognition based on the invariant moments. The features of the soybean leaf were obtained, and the soybean leaf was recognized using the nearest neighbor classifier.…”

Section: Related Workmentioning

confidence: 99%

A Novel Angular Texture Pattern (ATP) Extraction Method for Crop and Weed Discrimination Using Curvelet Transformation

Prema¹,

Murugan²

2016

ELCVIA

View full text Add to dashboard Cite

Weed management is the most significant process in the agricultural applications to improve the crop productivity rate and reduce the herbicide application cost. Existing weed detection techniques does not yield better performance due to the complex background and illumination variation. Hence, there arises a need for the development of effective weed identification technique. To overcome this drawback, this paper proposes a novel Angular Texture Pattern (ATP) Extraction Method for crop and weed discrimination using curvelet transformation. In our proposed work, Adaptive Median Filter (AMF) is used for filtering the impulse noise from the image. Plant image identification is performed using green pixel extraction and K-means clustering. Wrapping based Curvelet transform is applied to the plant image. Feature extraction is performed to extract the angular texture pattern of the plant image. Particle Swarm Optimization (PSO)-based Differential Evolution Feature Selection (DEFS) approach is applied to select the optimal features. Then, the selected features are learned and passed through an RVM-based classifier to find out the weed. Edge detection and contouring is performed to identify the weed in the plant image. The fuzzy rule-based approach is applied to detect the low, medium and high levels of the weed patchiness. From the experimental results, it is clearly observed that the accuracy of the proposed approach is higher than the existing Support Vector Machine (SVM) based approaches. The proposed approach achieves higher accuracy, sensitivity, specificity, Hausdorff distance, Jaccard distance and Dice distance.

show abstract

“…In 1962, the ϕ only has measure and shift invariance , not has rotating invariance, and remains constantly just in the mirror symmetry. At present, moment technology has attracted the attention of many researchers and appeared a variety of moments [4] . These moments have become a kind of very important method of the image processing and computer vision field, which has been successfully applied in pattern recognition, image description, boundary detection, object oriented and image analysis and so on.…”

Section: Advanced Materials Research Vols 706-708mentioning

confidence: 99%

Fault Diagnosis of Rolling Bearing Based on S Transform and Image of Invariant Moments

Guo

Wang

Peng

et al. 2013

AMR

View full text Add to dashboard Cite

According the characteristics of rolling bearing fault information are nonlinear and non-stationary, the method of time-frequency is often used to make the one dimensional time signal map into two dimensional time and frequency function, and describe the energy density of signal at different times and frequency simultaneously. A method of fault diagnosis based on S transformation and image Hu of invariant moments was put forward in this paper. First of all the measured rolling bearing signals have been S transformed, and time-frequency spectrum which is got is expressed as two dimensional image, then Hu geometric moment invariant of the S transformation spectrum is calculated and the simulation research is carried out using invariant moment principle in image processing. The results show that this method can distinguish the inner ring, outer ring and bearing roller fault intuitively and accurately and measure rolling bearing fault diagnosis efficiently.

show abstract

Research on weed recognition method based on invariant moments

Cited by 5 publications

References 2 publications

Automated Leaf Alignment and Partial Shape Feature Extraction for Plant Leaf Classification

Automated Leaf Alignment and Partial Shape Feature Extraction for Plant Leaf Classification

A Novel Angular Texture Pattern (ATP) Extraction Method for Crop and Weed Discrimination Using Curvelet Transformation

Fault Diagnosis of Rolling Bearing Based on S Transform and Image of Invariant Moments

Contact Info

Product

Resources

About