Attention aware cross faster RCNN model and simulation

Xiong, Jiang; Zhu, Liehuang; Ye, Lingfeng; Li, Jinhong

doi:10.1007/s11276-021-02645-8

Cited by 4 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By integrating extracted features, proposed regions, bounding boxes, and prediction into seamless learning, Faster-RCNN has been accelerated in visual object analysis. Notably, in the task of dish recognition, Faster-RCNN has been used as a food identifier of dishes in a food image [50,51], and in [52], its architecture has been modified by crossconnected layers to capture low-and high-level messages, and an attention mechanism is additionally used to make the model highlight the contexture of the dish regions. It should be mentioned that some deep networks are kept on update, such as YOLO, and their capacity is kept on improving.…”

Section: Discussionmentioning

confidence: 99%

Accurate Real-Life Chinese Dish Recognition

Lan

Wan

Pang

et al. 2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

Deep learning is a new research direction in the field of machine learning, which was introduced into machine learning to bring it closer to its original goal. Accurate dish recognition becomes increasingly important in the multimedia community since it can help cuisine recommendation, calorie management, service improvement, and other food computing tasks. Many novel approaches have been developed on web recipes and menu pictures, while few are concerned real-life dish image analysis. In this study, a deep learning-based prototype system is deployed in a Chinese canteen, and 28 dish types, 16,904 images, and 45,061 instances have been collected. Specifically, in the prototype system, three practical issues are explored, including the backbone network selection, the training strategy determination, and the minimum number of samples for model upgrading. Experimental results suggest that fine-tuned Faster-RCNN can serve as the backbone network of the prototype system since it outperforms the other four fine-tuned networks on dish recognition (accuracy, 98.10%; recall, 97.20%; MAP (mean average precession), 98.30%) and satisfies real-time requirement (0.15 second per image). Meanwhile, the transferred backbone network achieves superior results (MAP, 96.48%) over the same architecture trained from image scratches (MAP, 87.84%). On model upgrading, a good (MAP, 91.34%) to better (MAP, 96.48%) outcome is obtained when the training size is increased from 50 to 200 samples per dish type, and 150 and more instances should be annotated if a new dish type is added to the system's recognition list. Conclusively, the real-life deployment and evaluation of the prototype system indicate that deep learning is full of potential to enhance customer experience through accurate daily dish recognition.

show abstract

Section: Discussionmentioning

confidence: 99%

Accurate Real-Life Chinese Dish Recognition

Lan

Wan

Pang

et al. 2022

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

show abstract

“…It is suitable for detecting small and medium-sized power network faults. Gao S et al proposed a fault diagnosis method [2][3] using Faster R-CNN for catenary suspension chord. It has a high detection accuracy by training with a large number of sample data.…”

Section: Introductionmentioning

confidence: 99%

A fault diagnosis method for power grid based on image feature extraction

Wan

Song

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In order to solve the problem that the traditional power grid fault diagnosis along the railway requires a lot of manpower and material resources, this paper proposes a fault diagnosis method on the power grid along the railway based on image feature extraction. A variable function family series method is designed to extract features of faults. For the fault image denoising, a convolution filter method is used, and the number of 2 denoising layers is selected. At the same time, extracting the decomposition coefficient features and energy features of power grid image faults. Moreover, the matching diagnosis method is given. The fault is finally identified based on the similarity. To compare with the existing fault diagnosis methods, the correct diagnosis rate of the fault diagnosis method proposed is more than 92%. From experimental comparison results, this diagnosis effect not only has higher precision, stronger anti-interference ability, but also has faster diagnosis speed.

show abstract