Development of Korean Food Image Classification Model Using Public Food Image Dataset and Deep Learning Methods

Chun, Minki; Jeong, Hyeonhak; Lee, Hyun-Min; Yoo, Taewon; Jung, Hyunggu

doi:10.1109/access.2022.3227796

Cited by 20 publications

(6 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Inception backbone of the InceptionResnetV2 was assumed to contribute to its high accuracy since it extracted the complex and informative image features (Wang et al, 2023). The excellent performance of InceptionResnetV2 result aligned with the findings of Chun et al (2022) which stated that InceptionResnetV2 outperformed Resnet50 in extracting food image features. The EfficientNetV2S backbone consisted of MBConv and Fused-MBConv blocks, which reduced the number of parameters while maintaining accuracy (Chollet, 2017;Tan and Le, 2021).…”

Section: The Top Performing Model Selectionsupporting

confidence: 76%

Enzyme dosage detection to degrade feathers in edible bird’s nests: A comparative convolutional neural networks study

Liana,

Arifiandika,

Rohmatulloh

et al. 2023

AFSSAAE

View full text Add to dashboard Cite

Edible Bird’s Nest (EBN), a costly food product made from swiftlet’s saliva, has encountered a longstanding problem of plucking the swiftlet’s feather from the nests. The destructive and inefficient manual process of plucking the feathers can be substituted with a serine protease enzyme alternative. Accurate detection of enzyme dosage is crucial for ensuring efficient feather degradation with cost-effective enzyme usage. This research employed the transfer learning method using pretrained Convolutional Neural Networks (Pt-CNN) to detect enzyme dosage based on EBN’s images. This study aimed to compare the image classification mechanisms, architectures, and performance of three Pt-CNN: Resnet50, InceptionResnetV2, and EfficientNetV2S. InceptionResnetV2, using parallel convolutions and residual networks, significantly contributes to learning rich informative features. Consequently, the InceptionResnetV2 model achieved the highest accuracy of 96.18%, while Resnet50 and EfficientNetV2S attained only 30.44% and 17.82%, respectively. The differences in architecture complexity, parameter count, dataset characteristics, and image resolution also play a role in the performance disparities among the models. The study’s findings aid future researchers in streamlining model selection when facing limited datasets by understanding the reasons for the model’s performance and contributing to a non-destructive and quick solution for EBN’s cleaning process.

show abstract

Section: The Top Performing Model Selectionsupporting

confidence: 76%

Enzyme dosage detection to degrade feathers in edible bird’s nests: A comparative convolutional neural networks study

Liana,

Arifiandika,

Rohmatulloh

et al. 2023

AFSSAAE

View full text Add to dashboard Cite

show abstract

“…It is important to note that other similar datasets have been developed to address specific but related challenges. For example, Chun et al [ 42 ] developed a custom dataset based on Korean food images for classification purposes. This dataset, generated using a web scraper, consists of 150,610 food images.…”

Section: Background and Related Researchmentioning

confidence: 99%

“…InceptionNet was used the most in research by Chun et al. [ 42 ] and Chaitanya et al. [ 23 ], with results of 81% and 97%, respectively.…”

Section: Background and Related Researchmentioning

confidence: 99%

“…Results from the literature indicate that an increased number of classes may decrease accuracy, as evidenced by two different studies that investigated performance across various classes [ 23 , 42 ]. This presents the idea that the accuracy of a model not only depends on the pre-trained CNN architecture but also on the data size, the number of classes, and their distribution in the dataset.…”

Section: Background and Related Researchmentioning

confidence: 99%

See 1 more Smart Citation

Fine-Grained Food Image Recognition: A Study on Optimising Convolutional Neural Networks for Improved Performance

Boyd,

Nnamoko,

Lopes

2024

J. Imaging

View full text Add to dashboard Cite

Addressing the pressing issue of food waste is vital for environmental sustainability and resource conservation. While computer vision has been widely used in food waste reduction research, existing food image datasets are typically aggregated into broad categories (e.g., fruits, meat, dairy, etc.) rather than the fine-grained singular food items required for this research. The aim of this study is to develop a model capable of identifying individual food items to be integrated into a mobile application that allows users to photograph their food items, identify them, and offer suggestions for recipes. This research bridges the gap in available datasets and contributes to a more fine-grained approach to utilising existing technology for food waste reduction, emphasising both environmental and research significance. This study evaluates various (n = 7) convolutional neural network architectures for multi-class food image classification, emphasising the nuanced impact of parameter tuning to identify the most effective configurations. The experiments were conducted with a custom dataset comprising 41,949 food images categorised into 20 food item classes. Performance evaluation was based on accuracy and loss. DenseNet architecture emerged as the top-performing out of the seven examined, establishing a baseline performance (training accuracy = 0.74, training loss = 1.25, validation accuracy = 0.68, and validation loss = 2.89) on a predetermined set of parameters, including the RMSProp optimiser, ReLU activation function, ‘0.5’ dropout rate, and a 160×160 image size. Subsequent parameter tuning involved a comprehensive exploration, considering six optimisers, four image sizes, two dropout rates, and five activation functions. The results show the superior generalisation capabilities of the optimised DenseNet, showcasing performance improvements over the established baseline across key metrics. Specifically, the optimised model demonstrated a training accuracy of 0.99, a training loss of 0.01, a validation accuracy of 0.79, and a validation loss of 0.92, highlighting its improved performance compared to the baseline configuration. The optimal DenseNet has been integrated into a mobile application called FridgeSnap, designed to recognise food items and suggest possible recipes to users, thus contributing to the broader mission of minimising food waste.

show abstract

“…However, it is extremely challenging to perform food image analyses. For instance, the identification of food products in images is still a challenging process due to low inter-class variance and high intra-class variance [3]. Furthermore, many food classes have not yet been effectively classified.…”

Section: Introductionmentioning

confidence: 99%

Bio-Inspired Spotted Hyena Optimizer with Deep Convolutional Neural Network-Based Automated Food Image Classification

Mahgoub,

Aldehim,

Almalki

et al. 2023

Biomimetics

View full text Add to dashboard Cite

Food image classification, an interesting subdomain of Computer Vision (CV) technology, focuses on the automatic classification of food items represented through images. This technology has gained immense attention in recent years thanks to its widespread applications spanning dietary monitoring and nutrition studies to restaurant recommendation systems. By leveraging the developments in Deep-Learning (DL) techniques, especially the Convolutional Neural Network (CNN), food image classification has been developed as an effective process for interacting with and understanding the nuances of the culinary world. The deep CNN-based automated food image classification method is a technology that utilizes DL approaches, particularly CNNs, for the automatic categorization and classification of the images of distinct kinds of foods. The current research article develops a Bio-Inspired Spotted Hyena Optimizer with a Deep Convolutional Neural Network-based Automated Food Image Classification (SHODCNN-FIC) approach. The main objective of the SHODCNN-FIC method is to recognize and classify food images into distinct types. The presented SHODCNN-FIC technique exploits the DL model with a hyperparameter tuning approach for the classification of food images. To accomplish this objective, the SHODCNN-FIC method exploits the DCNN-based Xception model to derive the feature vectors. Furthermore, the SHODCNN-FIC technique uses the SHO algorithm for optimal hyperparameter selection of the Xception model. The SHODCNN-FIC technique uses the Extreme Learning Machine (ELM) model for the detection and classification of food images. A detailed set of experiments was conducted to demonstrate the better food image classification performance of the proposed SHODCNN-FIC technique. The wide range of simulation outcomes confirmed the superior performance of the SHODCNN-FIC method over other DL models.

show abstract

Development of Korean Food Image Classification Model Using Public Food Image Dataset and Deep Learning Methods

Cited by 20 publications

References 46 publications

Enzyme dosage detection to degrade feathers in edible bird’s nests: A comparative convolutional neural networks study

Enzyme dosage detection to degrade feathers in edible bird’s nests: A comparative convolutional neural networks study

Fine-Grained Food Image Recognition: A Study on Optimising Convolutional Neural Networks for Improved Performance

Bio-Inspired Spotted Hyena Optimizer with Deep Convolutional Neural Network-Based Automated Food Image Classification

Contact Info

Product

Resources

About