A Novel Shape Representation Method for Complex Trademark Image

Ye, Ben Haobin; Cai, Zhanchuan; Lan, Ting; Xiao, Youqing

doi:10.1109/access.2019.2912230

Cited by 6 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the Gibbs phenomenon that occurs in Fourier series can be overcome by V-system, and the V-descriptors for CT image feature extraction are designed in this paper. Secondly, the definition of V-system is briefly presented [28]. Finally, the pre-treatment of lung contours is also reviewed.…”

Section: Related Workmentioning

confidence: 99%

“…B. Definition of V-system V-system can overcome the Gibbs phenomenon, which has been verified in [26]- [28]. Therefore, we adopt it to construct V-descriptors for the lung feature extraction.…”

Section: A Gibbs Phenomenon In Contour Reconstructionmentioning

confidence: 99%

“…In this paper, a new digital feature descriptor for COVID-19 diagnosis using V-system is proposed. V-system is a generation of the Haar basis function, which combines with the sequences of piecewise polynomials of different degrees [26]- [28]. V-descriptors designed from V-system not only effectively decompose and represent multiple lesions quickly but also overcome the Gibbs phenomenon [29]- [32].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors

Yuan

Cai

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Digital image feature recognition is significant to industrial information applications, such as bioengineering, medical diagnosis, and machinery industry. In order to supply an effective and reasonable technology of the severity assessment mission of COVID-19, we propose a new method that identifies rich features of lung infections from a chest CT image, and then assesses the severity of COVID-19 based on the extracted features. First, in a chest CT image, the lung contours are corrected for the segmentation of bilateral lungs. Then, the lung contours and areas are obtained from the lung regions. Next, the coarseness, contrast, roughness, and entropy texture features are extracted to confirm the COVID-19 infected regions, and then the lesion contours are extracted from the infected regions. Finally, the texture features and V-descriptors are fused as an assessment descriptor for the COVID-19 severity estimation. In the experiments, we show the feature extraction and lung lesion segmentation results based on some typical COVID-19 infected CT images. In the lesion contour reconstruction experiments, the performance of V-descriptors is compared with some different methods, and various feature scores indicate that the proposed assessment descriptor reflects the infected ratio and the density feature of the lesions well, which can estimate the severity of COVID-19 infection more accurately.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Gibbs Phenomenon In Contour Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors

Yuan

Cai

et al. 2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the time retrieval and recognition, processes are very critical tasks. So, to rectify the shape of an image by using an orthogonal representation to obtain accurate results [14]. The color and shape features are most important for matching trademark images in an efficient manner [15].…”

Section: Research Backgroundmentioning

confidence: 99%

An Automatic Image Registration Methods for Multi-Domain Images by using Geometric Relationships

Dharani*,

Aroquiaraj

2019

IJITEE

View full text Add to dashboard Cite

In the internet technology world, all the information is considered as an image format only. Because one image is equal to a thousand words. Automatically increasing the image database size, high resolution and including multi-domain concepts. The human perception of getting the required image is very poor during the image retrieval process. In this case, the image retrieval system is consists of many problems like more time consuming, irrelevant results of the user. Registration is necessary to be able to compare or integrate the data obtained from different measurements of the query image. Image registration is that the method of reworking totally different sets of knowledge into one organization and orienting 2 or additional pictures of constant scene. This method involves designating one image because the reference image, conjointly known as the mounted image, and applying geometric transformations or native displacements to the opposite pictures so they align with the reference. To solve the above problems by using an automatic image registration methods. In this paper, we are mainly focusing the automatic image registration methods for multi-domain images for better human understating of required results. Finally, evaluate the performance of image registration methods with length, counts of matched points and uniformly distributed points of multi-domain images for better understanding.

show abstract

Commodity classification in livestreaming marketing based on a conv-transformer network

Zhang,

Wang

2023

Multimed Tools Appl

View full text Add to dashboard Cite

A Novel Shape Representation Method for Complex Trademark Image

Cited by 6 publications

References 35 publications

Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors

Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors

An Automatic Image Registration Methods for Multi-Domain Images by using Geometric Relationships

Commodity classification in livestreaming marketing based on a conv-transformer network

Contact Info

Product

Resources

About