A Simplified CNNs Visual Perception Learning Network Algorithm for Foods Recognition

Xiao, Lei; Lan, Tian; Xu, Dezhi; Gao, Weizhe; Li, Ce

doi:10.1016/j.compeleceng.2021.107152

Cited by 12 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can show the change information of the vertices. Literature [ 21 , 22 ] summarizes the current research status of human motion recognition, including video-based, sensor-based, and radio-frequency-based research status. Literature [ 23 ] analyzed the basic principles of CNN and established a structure based on CNN.…”

Section: Related Workmentioning

confidence: 99%

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Zhong

Dong

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This paper constructs a sports action recognition model based on deep learning (DL) and clustering extraction algorithm. For the input detection image frame, athletes’ movements are detected through DL network, and then athletes’ sports movements are fused. Moreover, it expands new knowledge and improves learning ability through automatic learning training set. The neural network (NN) is applied to the sample set containing images of nonathletes, and the negative training sample set is iteratively enhanced according to the generated false positives, and the results are optimized by clustering method. Simulation experiments show that compared with other algorithms, the clustering extraction algorithm in this paper has achieved superior performance in recognition rate and false alarm rate, and the recognition speed is faster. The aim is to extract the athletes’ training postures through the analysis of sports movements, so as to assist coaches to train athletes more professionally and provide some reference for sports movement recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Zhong

Dong

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…anks to the development of deep learning architectures [7][8][9][10][11][12], the availability of massive data samples [13][14][15][16][17], and the upgrade of computational hardware, end-to-end approaches help boost the performance of dish recognition [18][19][20][21][22][23][24][25][26][27]. Wu exploits the semantic relationship among finegrained food categories, and a multitask learning procedure is added to a convolutional neural network (CNN) [27].…”

Section: Introductionmentioning

confidence: 99%

“…e model outperforms the other evaluated deep networks on the dataset with accuracy of 91.3%, and time cost of 0.4 ms per image. Xiao presented a simple perception learning model [26]. ey design a jumping convolution module to extract image features of food regions for reducing the CNN complexity, and in addition, a preprocessing step by image editing is used to get different visual cues of dish images.…”

Section: Introductionmentioning

confidence: 99%

“…Meanwhile, according to the dish types presented on one plate, the methods can be generally grouped into single and mixed dish recognition approaches, and most methods concentrate on the classification of single dish types [2][3][4][5][6][18][19][20][21][22][23][24][25][26][27]. In comparison to a single dish scenario, a mixed dish contains various dish types overlaid on one plate, and this kind of food is popular in China, Singapore, and other Southeast and Eastern Asian regions [28].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…In recent years, with the deepening of deep learning research, a huge breakthrough in CNN network structure has been made. In terms of spatial feature extraction, the network continuously deepens, forms the inception structure module, as shown in Figure 2, which greatly reduces the quantities of network parameters, realizes the multiscale processing fusion of images, and obtains a better feature representation [12][13][14][15].…”

Section: Network Profilementioning

confidence: 99%

The Motor Action Analysis Based on Deep Learning

Zhang

2022

Scientific Programming

View full text Add to dashboard Cite

For the slow speed and low accuracy of slow motor action recognition methods, this study proposes a motor action analysis method based on the CNN network and the softmax classification model. First, in order to obtain motor action feature information, by using static spatial features of BN-inception based on CNN network extracted actions and high-dimensional features of 3D ConvNet, then based on softmax classifier structure and realizing taxonomic recognition of the motor actions. Finally, through the decision-layer fusion and time semantic continuity optimization strategy, the motion action recognition accuracy is further improved and the more efficient motion action classification recognition is realized. The results show that the proposed method can complete the motor action analysis and achieve the classification recognition accuracy to 83.11%, which has certain practical value.

show abstract

A Simplified CNNs Visual Perception Learning Network Algorithm for Foods Recognition

Cited by 12 publications

References 13 publications

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

Accurate Real-Life Chinese Dish Recognition

The Motor Action Analysis Based on Deep Learning

Contact Info

Product

Resources

About