AN OTSU image segmentation based on fruitfly optimization algorithm

Huang, Chunyan; Li, Xiaorui; Wen, Yunliang

doi:10.1016/j.aej.2020.06.054

Cited by 86 publications

(35 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cermet coating detection was possible by automatic methods chosen based on visual observation of their accuracy in surface layer detection. Among the available algorithms for automating thresholds [ 32 , 33 , 34 , 35 , 36 , 37 , 38 ], RenyiEntropy was selected because only this counted out the threshold values with acceptable accurateness of detection of the coating area, represented by red highlighted areas ( Figure 13 and Figure 14 ).…”

Section: Resultsmentioning

confidence: 99%

“…For detection of the cermet coating for both types of specimens, an algorithm was chosen which, in this case, gave the best detection result among the other testing methods, such as Li, Otsu, maximum entropy, and Yen, which are available in the Fiji algorithm’s library [ 38 ]. The visualisation of detection effects is presented in Figure 13 and Figure 14 .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Nano X-ray Tomography Application for Quantitative Surface Layer Geometry Analysis after Laser Beam Modification

et al. 2022

View full text Add to dashboard Cite

Analysis of the geometrical structure of the surface of materials is an issue already widely recognised and included in international standards. The authors present the possibilities of extending the analysis of the coatings’ geometrical structure through X-ray nanotomography imaging, three-dimensional image processing, and stereological methods. Analysis of the state of the art reveals that there are no scientific rapports (indexed by Scopus) on the application X-ray nanotomography for analysis of the geometry of a coating. The presented study shows that this imaging technique can be applied and provide additional information on the quality of the layer. The comparative tests were carried out on samples with a cermet coating before and after laser treatment, including standard tests of the surface geometry and the analysis of three-dimensional images obtained from nanotomography. A set of parameters describing the compactness and thickness distribution of the applied coating is proposed, which facilitates the qualitative assessment of the application process and improvements through the additional processing of technological layers. The obtained results show that although the average thickness values before and after laser treatment did not differ significantly, their distribution on the sample surface was different, as presented in the visualisation. The determined stereological parameter NV (number of objects per unit volume) allowed for the assessment of the layer compactness, and as the analyses showed, this value decreased by more than two times after laser treatment. The analysis of the degree of sample coverage by the cermet layer showed that it increased from 70% to 95% after laser treatment, which confirms the treatment’s positive effect on the layer’s quality. This research shows that three-dimensional analysis significantly enriches the information about the geometry of the surface layer, providing data which other research techniques are unable to acquire.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Nano X-ray Tomography Application for Quantitative Surface Layer Geometry Analysis after Laser Beam Modification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This algorithm takes maximum betweenclass variance between object of interest (foreground) and background (non-region of interest). It performs this division based on gray level characteristics of the Image [14] as expressed in Eq.1.…”

Section: Our Methodsmentioning

confidence: 99%

Double Channel CNN Based Tomato Plant Leaf Disease Detection

Kumar

2021

QUESTRJ

View full text Add to dashboard Cite

Early blight, late blight, bacterial spot, leaf mold, spider mites, yellow leaf curl virus and Septoria leaf spot are the most common diseases of tomato plant which cause major loss to agriculture sector. Diagnosis and prognosis at early stage are prime challenges to save life of tomato crop. This research presents a state-of-the-art Double-Channel Convolution Neural Network (D-CNN) model for diagnoses of 8 different Classes of Tomato Plant Leaves. The proposed model integrates two separate Convolutional Neural Network (CNN) channels with similar number of Conv Layers and Parameters. One Channel processes the pre-processed Red-Green-Blue (RGB) data, whereas the second channel processes the region segmented data obtained by applying a Multi-Otsu Thresholding algorithm. We verified the proposed model on the Plant Village dataset which consists of more than 16,000 images of tomato plant leaves. The proposed model attains an overall accuracy of 94% after 200 iterations, comparatively 3.2% faster than Support Vector Machine (SVM), 2.2% faster than Probabilistic Neural Network (PNN), and 8% faster than Residual Neural Network (ResNet-50).

show abstract

“…The Otsu approach is straightforward to use and offers a quick processing time for choosing thresholds that automatically determine which classes have the greatest variance [37,38].…”

Section: The Otsu Approachesmentioning

confidence: 99%

Image segmentation-based optimization algorithms: A Review

Mohamed

Mahmoud²,

Hemeida³

2022

Aswan University Journal of Sciences and Technology

View full text Add to dashboard Cite

Image segmentation is the division of a digital image into multiple subgroups of pixels known as Image Objects. This procedure can minimize the complexity of the image, making image analysis easier. Image Segmentation is one of the most crucial areas in computer vision and one of the oldest research questions. There are many useful applications of image processing such as image sharpening, blurring, grayscale conversion, and edges detection that can be utilized in different domains. Digital image processing employing neural networks has gained popularity recently because of the expansion of artificial intelligence algorithms and its ecosystem. It can be used in a wide range of industries, including security, banks, the military, agriculture, law enforcement, manufacturing, and medicine.

show abstract

AN OTSU image segmentation based on fruitfly optimization algorithm

Cited by 86 publications

References 5 publications

Nano X-ray Tomography Application for Quantitative Surface Layer Geometry Analysis after Laser Beam Modification

Nano X-ray Tomography Application for Quantitative Surface Layer Geometry Analysis after Laser Beam Modification

Double Channel CNN Based Tomato Plant Leaf Disease Detection

Image segmentation-based optimization algorithms: A Review

Contact Info

Product

Resources

About