Thai fast food image classification using deep learning

Hnoohom, Narit; Yuenyong, Sumeth

doi:10.1109/ecti-ncon.2018.8378293

Cited by 38 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Proposed a model for the classification of Thai fast food based on deep learning [62]. The model used the GoogleNet model with some convolutional, pooling layers and inception layers.…”

Section: _______________________________________________________________________________________________ Volume XX 2017mentioning

confidence: 99%

Breast Cancer Classification From Histopathological Images Using Patch-Based Deep Learning Modeling

et al. 2021

View full text Add to dashboard Cite

Accurate detection and classification of breast cancer is a critical task in medical imaging due to the complexity of breast tissues. Due to automatic feature extraction ability, deep learning methods have been successfully applied in different areas, especially in the field of medical imaging. In this study, a novel patchbased deep learning method called Pa-DBN-BC is proposed to detect and classify breast cancer on histopathology images using the Deep Belief Network (DBN). Features are extracted through an unsupervised pre-training and supervised fine-tuning phase. The network automatically extracts features from image patches. Logistic regression is used to classify the patches from histopathology images. The features extracted from the patches are fed to the model as input and the model presents the result as a probability matrix as either a positive sample (cancer) or a negative sample (background). The proposed model is trained and tested on the whole slide histopathology image dataset having images from four different data cohorts and achieved an accuracy of 86%. Consequently, the proposed method is better than the traditional ones, as it automatically learns the best possible features and experimental results show that the model outperformed the previously proposed deep learning methods.

show abstract

“…Proposed a model for the classification of Thai fast food based on deep learning [62]. The model used the GoogleNet model with some convolutional, pooling layers and inception layers.…”

Section: _______________________________________________________________________________________________ Volume XX 2017mentioning

confidence: 99%

Breast Cancer Classification From Histopathological Images Using Patch-Based Deep Learning Modeling

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In various studies, images of local food were acquired to create a dataset. Phat et al collected 2315 images of Vietnamese food divided into five different classes [15]. The images were obtained from the web.…”

Section: Food Datasetsmentioning

confidence: 99%

Traditional food knowledge of Indonesia: a new high-quality food dataset and automatic recognition system

et al. 2020

View full text Add to dashboard Cite

Traditional food knowledge is the collective cultural wisdom of food systems that is passed down through generations [1]. Food systems involve the processes of production, processing, distribution, and consumption of food [2]. Hence, the sociocultural, economic, and health aspects of a specific ethnic group of a specific region can be inferred based on the traditional food knowledge. Traditional food knowledge helps in maintaining cultural diversity and ensuring food security for the community [1]. According to Sharif, the cultural identity of an ethnic community or region corresponds to the

show abstract

“…Hidden Layer Hidden Layer As shown in figure 2, the input image convolution operation through multiple convolution kernels, map with three characteristics, and then in the feature maps to four adjacent pixels sum for a set of calculating mean, again through the weighted value, and paranoia, is obtained by the activation function three features of the second map, the map again by different convolution kernels after convolution get the third layer, the layer after with the same action on the second floor for the fourth floor. Finally, the obtained pixel values are stretched and rasterized to obtain a one-dimensional vector input into the traditional neural network, and the output is obtained through classification [3] .…”

Section: Input Layermentioning

confidence: 99%

The Research on Recognition of Cultural Relics Material Information Based on Image

Wang¹,

Yuan²,

Hou³

2019

dtcse

View full text Add to dashboard Cite

In the process of realizing the virtualization of cultural relics, it is of certain significance to improve the research on the authenticity of cultural relics. and the way to realize it is to make the model of the virtualization of cultural relics match the perception of the corresponding real material. To solve this problem, an image-based classification algorithm for cultural relics material information is proposed, in which the material information should include the material of great majority of the cultural relics surface. In this process, the main purpose is to judge the metallicity and the reflectivity of the cultural relics surface. Through these surface material information, relevant programs can restore the real appearance of cultural relics in a better way. These classifications can be realized by depth learning. After random selection of pictures, the model can finally converge to about 95% of the material accuracy.

show abstract

Thai fast food image classification using deep learning

Cited by 38 publications

References 9 publications

Breast Cancer Classification From Histopathological Images Using Patch-Based Deep Learning Modeling

Breast Cancer Classification From Histopathological Images Using Patch-Based Deep Learning Modeling

Traditional food knowledge of Indonesia: a new high-quality food dataset and automatic recognition system

The Research on Recognition of Cultural Relics Material Information Based on Image

Contact Info

Product

Resources

About