A fast and memory-efficient two-pass connected-component labeling algorithm for binary images

Bataineh, Bilal

doi:10.3906/elk-1703-351

Cited by 8 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Halıcı and Demirhan [36] worked on multi-person real-time pose tracking with the global nearest neighbor method. Bataineh [24] examined the performance results were shared the resource needs of CCL algorithms. Without regard to, considering the resource capacity of mobile devices, these algorithms were not preferred in our study.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Study on Remote Detection of Turkey Digital Identity Card Hologram Element

2024

View full text Add to dashboard Cite

Technological advances and the pandemic have caused an explosion in demand for remote services. In critical processes such as banking, insurance and notary public, the service to be provided remotely has to be provided as quickly and safely as the service provided in presence. In such sensitive processes, the identity card authenticity detection must be done accurately and securely. One of the techniques used in accuracy detection is the use of mobile devices that support contactless chip technology. However, the number of mobile devices using this method is limited today. This situation hinders the effective and widespread use of remotely provided services and resources. Therefore, a different solution method was needed that would be an alternative to contactless chip technology, remove the obstacles to widespread use and reduce incidents such as counterfeiting. In this study, it was investigated whether the hologram, which is one of the security elements in the identity, can be used in determining the accuracy of Turkey's digital identity cards. For this purpose, a special function and program has been developed on the MATLAB application by using 2-D neighborhood methods to detect the crescent on the hologram. 227 digital ID cards were first evaluated on a mobile device over certain threshold values such as color level and similarity ratio. Then, each card used in the test was examined one by one with the naked eye. Approximately 99.56% similar results were obtained between the test findings made over the application and the findings obtained after the controls made with the naked eye. It has been concluded that the secure hologram image, one of the security elements on the digital ID card with this high success rate, can be used as computer aided in remote services. With this solution method, it has contributed to overcome an important obstacle in front of services that are thought to be provided remotely in many fields such as banks, notaries and education.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It makes recommendations for high performance by comparing the work done by Bataineh [24] on image-analysis and pattern-recognition algorithms. In the study of Zaitsev [25] on d-dimensional cellular automata, he examined the theoretical background of edge detection algorithms and made some suggestions.…”

Section: Literaturementioning

confidence: 99%

A Study on Remote Detection of Turkey Digital Identity Card Hologram Element

2024

View full text Add to dashboard Cite

show abstract

“…After moving object detection, connected region labeling algorithms can be employed to obtain the coordinates of moving regions. Many works are reported in the literature, e.g., [ 24 , 25 , 26 , 27 , 28 , 29 , 30 ], for labeling connected components. However, these methods suffer from high computational complexity.…”

Section: Related Workmentioning

confidence: 99%

Real-Time Moving Object Detection in High-Resolution Video Sensing

Zhu

Wei

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper addresses real-time moving object detection with high accuracy in high-resolution video frames. A previously developed framework for moving object detection is modified to enable real-time processing of high-resolution images. First, a computationally efficient method is employed, which detects moving regions on a resized image while maintaining moving regions on the original image with mapping coordinates. Second, a light backbone deep neural network in place of a more complex one is utilized. Third, the focal loss function is employed to alleviate the imbalance between positive and negative samples. The results of the extensive experimentations conducted indicate that the modified framework developed in this paper achieves a processing rate of 21 frames per second with 86.15% accuracy on the dataset SimitMovingDataset, which contains high-resolution images of the size 1920 × 1080.

show abstract

“…The unlabeled dataset is essentially divided into labeled groups regardless of the presence of similar patterns [8,9]. These labeled clusters can be used simply to process and analyze large and complex datasets in many applications, such as healthcare [10,11], renewable energy [12,13], image segmentation [14][15][16], data analysis [1,9], social network analysis [17,18], security [19,20], finance and business [21,22], and much more. Many studies on clustering algorithms have been conducted.…”

Section: Introductionmentioning

confidence: 99%

Fast Component Density Clustering in Spatial Databases: A Novel Algorithm

Bataineh

2022

Information

View full text Add to dashboard Cite

Clustering analysis is a significant technique in various fields, including unsupervised machine learning, data mining, pattern recognition, and image analysis. Many clustering algorithms are currently used, but almost all of them encounter various challenges, such as low accuracy, required number of clusters, slow processing, inability to produce non-spherical shaped clusters, and unstable performance with respect to data characteristics and size. In this research, a novel clustering algorithm called the fast component density clustering in spatial databases (FCDCSD) is proposed by utilizing a density-based clustering technique to address the aforementioned existing challenges. First, from the smallest to the largest point in the spatial field, each point is labeled with a temporary value, and the adjacent values in one component are stored in a set. Then, all sets with shared values are merged and resolved to obtain a single value that is representative of the merged sets. These values represent final cluster values; that is, the temporary equivalents in the dataset are replaced to generate the final clusters. If some noise appears, then a post-process is performed, and values are assigned to the nearest cluster based on a set of rules. Various synthetic datasets were used in the experiments to evaluate the efficiency of the proposed method. Results indicate that FCDCSD is generally superior to affinity propagation, agglomerative hierarchical, k-means, mean-shift, spectral, and density-based spatial clustering of applications with noise, ordering points for identifying clustering structures, and Gaussian mixture clustering methods.

show abstract

A fast and memory-efficient two-pass connected-component labeling algorithm for binary images

Cited by 8 publications

References 19 publications

A Study on Remote Detection of Turkey Digital Identity Card Hologram Element

A Study on Remote Detection of Turkey Digital Identity Card Hologram Element

Real-Time Moving Object Detection in High-Resolution Video Sensing

Fast Component Density Clustering in Spatial Databases: A Novel Algorithm

Contact Info

Product

Resources

About