Which level for face recognition display higher accuracy of response?
Best insight from top research papers
Face recognition accuracy varies based on the methods employed. Research by Dinariyah and Alamsyah demonstrated that using 90% training and testing images in the YALE database resulted in 100% accuracy, showcasing high performance. On the other hand, the study by Talab, Awang, and Najim showed that their Efficient Sub-Pixel Convolutional Neural Network achieved 95.3% accuracy on the Yale face database, indicating a significant level of accuracy. These findings suggest that utilizing a higher percentage of training and testing images, such as 90%, can lead to superior face recognition accuracy levels. Additionally, considering advanced techniques like deep learning models can further enhance accuracy in face recognition tasks.
Answers from top 4 papers
More filters
| Papers (4) | Insight |
|---|---|
18 Jul 2022 | Class-level adaptive training for face recognition displays higher accuracy by addressing imbalanced datasets and assigning adaptive margins based on class quantity and sample difficulty. |
1 Citations | Forensic facial examiners show higher accuracy in face recognition compared to super-recognizers, as indicated by their use of a 7-point identity judgment scale and higher agreement in judgments. |
01 Jun 2021 5 Citations | The highest accuracy in face recognition was achieved at 100% using 90% training and testing images in the YALE database, surpassing the 98.75% accuracy in the AT&T database. |
29 Jun 2019 17 Citations | The proposed Efficient Sub-Pixel Convolutional Neural Network achieved higher accuracy for face recognition at super-low resolution levels compared to traditional methods. |
Related Questions
How does face recognition influence buying behavior?5 answersFace recognition technology significantly impacts buying behavior in various domains. It enhances consumer experiences by enabling personalized services based on facial features. Moreover, in ticketing systems, face recognition restricts unauthorized ticket purchases, curbing speculative reselling during peak times. Additionally, face recognition is pivotal in monitoring and preventing illegal buying and selling activities, ensuring accountability and deterring fraudulent behaviors. Furthermore, the adoption of Face Recognition Payment (FRP) services is influenced by factors like relative advantage, performance expectancy, and social influence, shaping consumer intentions to use this innovative payment mode. Overall, face recognition technology plays a crucial role in enhancing security, personalization, and efficiency in various buying scenarios, ultimately influencing consumer behavior positively.
Subordinate level in face recognition demonstrated a lower average reaction of time?5 answersSubordinate-level face recognition typically shows faster reaction times compared to basic-level or superordinate-level categorization, especially for faces, objects of expertise, or atypical objects. This advantage in subordinate-level processing is influenced by the discriminability of faces within the stimulus set. Additionally, the neural mechanisms underlying subordinate-level representations of faces involve enhanced neural magnitude and size in the fusiform area, supporting the privileged status of peer faces in identity recognition for emerging adults. Furthermore, expertise in face recognition relies on different spatial frequency information compared to expertise in object recognition, with face categorization at the subordinate level emphasizing low spatial frequencies, while expert car categorization focuses more on high spatial frequencies.
Does basic level in object recognition demonstrated a higher accuracy rate of response?5 answersThe accuracy rate of response in object recognition varies across different levels of categorization. Studies have shown that the basic level in object recognition does not consistently demonstrate a higher accuracy rate compared to other levels. While some research suggests a temporal advantage of the basic level over the subordinate level, other studies challenge this notion, indicating that the superordinate level may have a stability advantage in visual object categorization tasks. Additionally, expert recognition at the subordinate level relies on internal object information, with crucial details being processed within a midrange of spatial frequencies. These findings collectively highlight the complexity of object recognition processes and the nuanced relationships between different levels of categorization in terms of accuracy rates.
How does SEGTRAN improve the accuracy of face recognition systems compared to traditional convolutional neural networks?4 answersSEGTRAN improves the accuracy of face recognition systems compared to traditional convolutional neural networks by using several improvement techniques. These techniques include adopting a less computationally costly approach, transfer learning, and hyper-parameter fine-tuning. By implementing these techniques, the base MobileNet-V1 model's Top-1 accuracy of 70.6% and Top-5 accuracy of 89.5% have been improved. The training accuracy has been increased to 95%, and accuracies of 96.4%, 98.0%, and 99.1% have been achieved on different face recognition datasets. This improvement in accuracy demonstrates the effectiveness of SEGTRAN and highlights the need for further research into improvement techniques for convolutional neural networks.
How can a face recognition app be used to improve attendance?5 answersA face recognition app can improve attendance by automating the attendance tracking process, eliminating the need for manual methods and reducing errors. The app uses advanced image processing techniques to detect and recognize faces in real-time, storing the attendance data in a database such as an Excel sheet. This allows for remote access to the attendance information. The app leverages the unique characteristics of the human face to accurately identify individuals, ensuring accurate attendance records. Additionally, the app can overcome the limitations of traditional attendance systems, such as ambiguity and challenges in enforcing attendance regulations. By utilizing face recognition technology, the app promotes efficiency, hygiene, and safety in various environments.
What Face Recognition Technology?5 answersFace recognition technology is a biometric tool used for person identification and verification. It utilizes artificial intelligence to recognize faces that are already stored in a database. This technology plays an important role in computer vision and has been widely used in various fields. The process of face recognition involves capturing an image or video stream containing a human face, detecting and tracking the face in the image, and then recognizing the face based on its characteristics. The effectiveness of the system depends on the quality and characteristics of the captured face image. Face recognition can be used for identification purposes and has applications in monitoring, security, and access control. It is a technique of biometric that can improve the efficiency and accuracy of face recognition and prevent spoofing attacks.