Optimal Extraction Method of Feature Points in Key Frame Image of Mobile Network Animation

Yin, Tao; Lv, Zhihan

doi:10.1007/s11036-022-02070-x

Cited by 3 publications

(3 citation statements)

References 20 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be recognized using various features, including its shape, texture, size, intensity, statistical aspects, and many more [19]. The process of feature extraction begins with the counting of the number of points or pixels that are encountered during each check [20]. Next, the checking process is carried out in various directions by tracing the Cartesian coordinates of the digital image being analyzed.…”

Section: Feature Extractionmentioning

confidence: 99%

A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets

Adhinata¹,

Ramadhan²,

Fauzi³

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Agriculture is the primary sector in Indonesia for meeting people's daily food demands. One of the agricultural commodities that replace rice is potatoes. Potato growth needs to be protected from weeds that compete for nutrients. Spraying using pesticides can cause environmental pollution, affecting cultivated plants. Currently, agricultural technology is being developed using an Artificial Intelligence (AI) approach to classifying crops. The classification process using AI depends on the number of datasets obtained. The number of datasets obtained in this research is not too large, so it requires a particular approach regarding the AI method used. This research aims to use a combination of feature extraction methods with local and deep feature approaches with supervised machine learning to classify of small datasets. The local feature method used in this research is Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG), while the deep feature method used is MobileNet and MobileNetV2. The famous Support Vector Machine (SVM) uses the classification method to separate two data classes. The experimental results showed that the local feature HOG method was the fastest in the training process. However, the most accurate result was using the MobileNetV2 deep feature method with an accuracy of 98%. Deep features produced the best accuracy because the feature extraction process went through many neural network layers. This research can provide insight on how to analyze a small number of datasets by combining several strategies

show abstract

Section: Feature Extractionmentioning

confidence: 99%

A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets

Adhinata¹,

Ramadhan²,

Fauzi³

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…The first section of this issue includes five papers, which focuses on the image processing under mobile network environment, including feature learning and recognition, key frame extraction, trajectory analysis, and quick search [6][7][8][9][10].…”

Section: Intelligent Image Processing In Mobile Networkmentioning

confidence: 99%

Intelligence Information Processing Applications in Meta World

Luo

Wang

2022

Mobile Netw Appl

View full text Add to dashboard Cite

“…After introducing feature matching into the automatic tracking method of marker points in moving image sequences, Cheng [22] established the image deformation model based on the basic principle that the corresponding line segments on both the image to be registered and the reference image are collinear, which realized the full automation of the sequence image registration process through automatic extraction and matching of line segment features. In order to effectively extract the feature points of mobile network animation images and accurately reflect the main contents of videos, Yin and Lv [23] proposed an optimized method for extracting the feature points of key frame images of the mobile network animation, which selected the key frames according to the content changes of animation videos and described the feature points of key frame images of the videos using the scale invariant feature transform algorithm. The study estimated the local feature points of images using the constrained optimization method, which achieved the optimal extraction of feature points of key frame images in mobile network animation.…”

Section: Introductionmentioning

confidence: 99%

Calibration Method of Feature Point Layout in Prefabricated Buildings Based on Image Recognition Technology

Sun¹,

Yang²,

Ji³

2023

View full text Add to dashboard Cite

Compared with other types of buildings, it is more difficult and demanding to calibrate the image layout of irregular prefabricated buildings. How to effectively extract the layout calibration feature information of the prefabricated buildings and how to ensure the accuracy of the calibration method have become the main problems to be solved in the field of image recognition. Therefore, this paper studied the calibration method of feature point layout of prefabricated buildings based on image recognition technology. Based on the task of extracting feature points in the above prefabricated building images, this paper proposed a new feature extraction network suitable for these feature points, and described its principle in detail. With the help of deep learning technology, this paper enhanced the feature description of prefabricated building image blocks based on feature point location information, and introduced in detail the constructed algorithm model of feature point extraction and description. The experimental results verified the feature point extraction model was effective in calibrating the feature point layout of the prefabricated buildings.

show abstract

Optimal Extraction Method of Feature Points in Key Frame Image of Mobile Network Animation

Cited by 3 publications

References 20 publications

A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets

A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets

Intelligence Information Processing Applications in Meta World

Calibration Method of Feature Point Layout in Prefabricated Buildings Based on Image Recognition Technology

Contact Info

Product

Resources

About