A Double Filtered GIST Descriptor for Face Recognition

Vinay, A.; Gagana, B; Shekhar, Vinay S.; Anil, B C; Murthy, K. N. Balasubramanya; Natarajan, S.

doi:10.1016/j.procs.2016.03.068

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, 32 × 16 = 512 GIST features are extracted from each image. GIST has been successfully applied for indoor/outdoor scene recognition [60] [61], traffic scene classification [62], and face recognition [63][64].…”

Section: Gistmentioning

confidence: 99%

A comparative study of rice variety classification based on deep learning and hand-crafted features

et al. 2020

View full text Add to dashboard Cite

Rice is vital to people all around the world. The demand for an efficient method in rice seed variety classification is one of the most essential tasks for quality inspection. Currently, this task is done by technicians based on experience by investigating the similarity of colour, shape and texture of rice. Therefore, we propose to find an appropriate process to develop an automation system for rice recognition. In this paper, several hand-crafted descriptors and Convolutional Neural Networks (CNN) methods are evaluated and compared. The experiment is simulated on the VNRICE dataset on which our method shows a significant result. The highest accuracy obtained is 99.04% by using DenNet21 framework.

show abstract

Section: Gistmentioning

confidence: 99%

A comparative study of rice variety classification based on deep learning and hand-crafted features

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The use of this type of device as a limb prosthesis was described. This direction gave potential for the development of transgressive ideas such as trans-or post-humanism (Matos et al, 2016;Vinay et al, 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

Wearable Technology in the Perception of Young Consumers

Gregor

Gwiaździński

2020

Marketing of Scientific and Research Organizations

View full text Add to dashboard Cite

The paper presents the issues of wearable technology, their role and use in the current economy. Ubiquitous digital transformation and universal access to broadband Internet are the foundation for the creation of interoperable ecosystems, where wearable technology is responsible for communication often in the relationship between machine to machine and machine to human. The authors researched the level of knowledge about these devices and the degree of their use. It turned out that despite the knowledge of worn devices and relatively positive attitudes, the degree of their use is low. The article is theoretical and empirical.

show abstract

“…It seems that these two kinds of features can play an important role as an exclusive feature in describing an image, so we choose Color and Edge descriptor along with Gist descriptor which includes all of the visual information levels, such as low level information (color, contour), intermediate level (shape, texture) and high level information (activation of semantic knowledge). Since Gist includes both perceptual and conceptual features, besides traffic sign recognition it can be used in different areas such as face recognition [39], fingerprint, and Iris. It can enrich our feature space for recognition phase.…”

Section: Proposed Descriptormentioning

confidence: 99%

A novel fusion mixture of active experts algorithm for traffic signs recognition

Ahangi

Langroudi

Yazdanpanah

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

Traffic sign recognition is an important problem in today's applications. In this paper, by combining ensemble and active learning methods, a novel fusion mixture of active experts algorithm is proposed for this problem. The active learning algorithm is a popular method for reducing the number of samples. The primary goal of active learning is diminishing complexity, increasing the convergence rate, speeding up training process, and decreasing the cost of samples labeling. The active learning, hence, chooses informative samples to train. In addition, ensemble methods are a combination of simple classifiers for improving accuracy. Each classifier tries to learn a region of dataset better than other regions that all opinions are considered on ensemble methods as an ultimate decision. The mixture of experts is one of the most modern hybrid methods in which the training process takes a relatively long time, and it is a problem for large datasets. Our proposed Mixture of Active Experts tries to solve this problem. It decreases the training time process and increases the speed of convergence for finding optimal weights by selecting only informative samples in active learning phase. It is also applicable for online situations, in which the model should be trained continuously. The results of different experiments on German Traffic Sign Recognition Benchmark dataset demonstrate that the proposed method shows 96.69% accuracy and achieved the 6th rank among all the state of the art algorithms using smaller number (only 60%) of training samples.

show abstract

A Double Filtered GIST Descriptor for Face Recognition

Cited by 9 publications

References 17 publications

A comparative study of rice variety classification based on deep learning and hand-crafted features

A comparative study of rice variety classification based on deep learning and hand-crafted features

Wearable Technology in the Perception of Young Consumers

A novel fusion mixture of active experts algorithm for traffic signs recognition

Contact Info

Product

Resources

About