Improved approximated median filter algorithm for real-time computer vision applications

Appiah, Obed; Asante, Michael; Hayfron-Acquah, J. B.

doi:10.1016/j.jksuci.2020.04.005

Cited by 20 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an arithmetic moving average calculated by adding recent RSS values, and dividing that value by the number of time periods in the calculation average N. Even if this is the most adopted filtering technique, it is not enough to stabilize the RSS values. To this purpose, we introduce the p-percentile filter [32]. Generally, this approach is adopted in computer vision to remove outliers without degrading the resulting image.…”

Section: Proximity Detection Algorithmsmentioning

confidence: 99%

Detecting Proximity with Bluetooth Low Energy Beacons for Cultural Heritage

Barsocchi

Girolami

Rosa

2021

Sensors

View full text Add to dashboard Cite

The RE.S.I.STO project targets visitors of Pisa medieval city, with the goal of providing high-quality digital contents accessible with smart devices. We describe the design, implementation and the test phases of the RE.S.I.STO application, whose goal is to automatically detect the proximity between visitors and artworks. Proximity is detected with a set of algorithms based on the analysis of Bluetooth Low Energy beacons. We detail our experimental campaigns which reproduce several museum layouts of increasing complexity at two pilot sites, and we compute the performance of the implemented algorithms to detect the nearby artworks. In particular, we test our solution in a wide open space located in our research institute and by performing a real deployment at the Camposanto Monumentale located in Pisa (Italy). The obtained performance varies in the range of 40% to perfect accuracy, according to the complexity of the considered museum layouts. We also describe a set of stress and stability tests aimed at verifying the robustness of the application during the data collection process. Our results show that the mobile application is able to reduce the beacon loss rate, with an average value of 77% of collected beacons.

show abstract

Section: Proximity Detection Algorithmsmentioning

confidence: 99%

Detecting Proximity with Bluetooth Low Energy Beacons for Cultural Heritage

Barsocchi

Girolami

Rosa

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Employing the process of contrast stretching can maximize the image of the motif with the extension of the YCbCr color space [26], [27]. Furthermore, from the results of the contrast enhancement process above, the researcher carried out a noise reduction process (removing noise in the image of Songket motifs), in which researchers can use the median filter method [28]- [30], with the function of removing pixel noise and replacing it with pixels that are around it the ASP method is presented in Equation 1, and the coordinate formula of ASP is presented in Equation 2.…”

Section: Methodsmentioning

confidence: 99%

Development of Affine Transformation Method in the Reconstruction of Songket Motif

Ramadhanu¹,

Na’am²,

Nurcahyo³

et al. 2022

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Songket is one of the clothes with a high artistic value besides Batik originating from Indonesia. Songket is widely used at weddings and other traditional formal events. Songket is the result of a traditional craft consisting of the main ingredients of cloth made of cotton and silk threads by inserting the feed (basic material) transversely on the Lunsing (yeast cloth). The quality of Songket art is found in the motifs on the Songket. This research has a conceptual outline in terms of improving the quality of Songket cloth and making it easier for craftsmen and artists to spare their art for the reconstruction process of the Silungkang Songket motif. This research aims to get a new Songket motif with a more modern and aesthetic motif but still has its original characteristics and identity. Based on these objectives, the researchers focused and motivated to develop the motif of one of the types of Songket in Indonesia, namely Silungkang Songket, in the form of a more modernized motif. This research develops a digital image transformation method named Affine Segmentation Point (ASP) to produce modernized Songket motifs. The basis of the developed ASP method is the Affine transformation. Songket image input was used as data and created a new motif in this study: a Songket image with the Rangkiang Lumbung Padi Besar motif. The results of this study can create excellent Songket motifs and modernization. The new motifs produced have been tested by Songket experts, Songket observers, Songket craftsmen, and Songket sellers with an interest rate of 97.5%. The method developed is very precise and can be used to develop other high-value artistic motifs on traditional cloth.

show abstract

“…i Median filtering [3]: This technique highlights the edges of the image and reduces the background noise in the image by introducing blurry effects from the neighborhood analysis. It plays a significant role in increasing the accuracy of the proposed system and decreasing the training time of the proposed system.…”

Section: Dataset Pre-processingmentioning

confidence: 99%

“…It plays a significant role in increasing the accuracy of the proposed system and decreasing the training time of the proposed system. In the proposed system, a nested optimized median filter [3] was implemented to achieve better results. ii Threshold: This technique performs lightweight image segmentation of the background and foreground in the text-CAPTCHA image.…”

Section: Dataset Pre-processingmentioning

confidence: 99%

Multiview deep learning-based attack to break text-CAPTCHAs

Yusuf

Srivastava

Singh

et al. 2022

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Completely Automated Public Turing Test To Tell Computer and Humans Apart (CAPTCHA) is a computer program that prevents malicious computer users. Text-CAPTCHA schemes utilize less-computational costs. Hence, they are the most popularly used. This paper investigates the effectiveness of state-of-the-art (SOTA) text-CAPTCHA schemes, proposes a Multiview deep learning system to break them, and highlights their weaknesses. Rather than the usual single-view feature extraction, the proposed model explores correlational features from multiple views to increase the model’s generalization and classification accuracy. The model combines convolutional neural networks and recurrent networks to preserve the input text-CAPTCHA’s spatial and sequential order. The proposed system has successfully achieved average accuracies ranging from 93.6% to 100%, and the average time to break a text-CAPTCHA scheme ranges from 0.0032 to 0.21 seconds on eight different datasets. Furthermore, an ablation study on 71 human users was conducted to evaluate the effectiveness of the schemes. The results demonstrated that the proposed system effectively outperforms the human users whom the schemes were designed to serve. Lastly, when compared with existing systems, the proposed system outperforms existing SOTA systems with an accuracy gap of almost 40% higher.

show abstract

Improved approximated median filter algorithm for real-time computer vision applications

Cited by 20 publications

References 20 publications

Detecting Proximity with Bluetooth Low Energy Beacons for Cultural Heritage

Detecting Proximity with Bluetooth Low Energy Beacons for Cultural Heritage

Development of Affine Transformation Method in the Reconstruction of Songket Motif

Multiview deep learning-based attack to break text-CAPTCHAs

Contact Info

Product

Resources

About