Malaysian food recognition and calorie counter application

Muhammad, Nor Aziah Amirah Nor; Lee, Chin Poo; Lim, Kian Ming; Razak, Siti Fatimah Abdul

doi:10.1109/scored.2017.8305442

Cited by 10 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Food tracking apps for smartphones have grown in popularity recently. The increased demand for mobile apps that allowed users to easily log or monitor their daily food intake was influenced by society's increased awareness of the benefits of eating healthy food [11]. However, these app has two limitations: less engagement and limited Malaysian food database.…”

Section:  Issn: 2302-9285mentioning

confidence: 99%

Mobile game model for monitoring Malaysian food calories intake using image recognition

et al. 2023

View full text Add to dashboard Cite

Two important problems related to food consumption were reported in Malaysia: Malaysia was the sixth rank in Asia for the highest adult obesity rate; and the United Nation reported that Malaysian consumed an average of 2,910 calories per day. An imbalanced diet and high intake of calorie-dense food problems that need attention to reduce obesity. These problems affect national economies by lowering productivity, increasing disability, raising health care expenses, and shortening life spans. Although, there are food calorie tracking applications available, however, existing apps are less engaging and to recognize Malaysian food due to its not versatile databases. This can be solved using game technologies. Hence, this study will propose mobile game model as a solution to the underlying problems. There are 4 phases in the method: expert validation, initial model, expert verification, and final model. The proposed parameters were validated by dietitians, and nutritionists. The model was verified by game experts. A low fidelity prototype was developed based on the proposed model to assist the expert verification process. The model was finalized based on the expert’s feedback. The proposed game model resolves the limited recognition of Malaysian food and monitoring the food calories intake in an engaging way.

show abstract

Section:  Issn: 2302-9285mentioning

confidence: 99%

Mobile game model for monitoring Malaysian food calories intake using image recognition

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Where automatic food image recognition is available, it is not in the context of TD2M management. For instance, [24] used artificial neural network to recognise five different types of Malaysian traditional dessert: curry puff, 'kuih ketayap', 'kuih kosui', red tortoise cake, and 'putu piring'. Calories were subsequently computed from the detected food images but no implication of T2DM management was documented.…”

Section: B Food Journaling Apps Development In Malaysiamentioning

confidence: 99%

Mobile Food Journalling Application with Convolutional Neural Network and Transfer Learning: A Case for Diabetes Management in Malaysia

Chew¹,

Sebastian²,

Raman³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Diabetes is an ever worsening problem in modern society, placing a heavy burden on healthcare systems. Due to the association between obesity and diabetes, food journaling mobile applications are an effective approach for managing and improving the outcome of diabetics. Due to the efficacy of nutritional tracking and management in managing diabetes, we implemented a deep learning-based Convolutional Neural Network food classification model to aid with food logging. The model is trained on a subset of the Food-101 and Malaysian Food 11 datasets, including web-scraped images, with a focus on food items found locally in Malaysia. In our experiments, we explore how fine-tuning of the image dataset improves the performance of the model.

show abstract

“…In particular, an ensemble‐based network is proposed to jointly exploit the features extracted through three different deep models, AlexNet [37], GoogLeNet [38], and ResNet [39]. In [35], the authors focus on recognising five different classical Malaysian food items using handcrafted features. Similarly, in [36], the authors target Vietnamese food recognition with five different food types.…”

Section: Related Workmentioning

confidence: 99%

“…More recently, some works also focused on the recognition of regional foods [34][35][36]. In [34], a multi-layered deep CNN is proposed to recognise Indian meals wherein the accuracy is compared against handcrafted features, such as BoW and SURF.…”

Section: Related Workmentioning

confidence: 99%

Automatic food recognition system for middle‐eastern cuisines

et al. 2020

View full text Add to dashboard Cite

The concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose‐level. As a consequence, there is an ever‐increasing need for automatic tools able to help diabetics to manage their diet and also help physicians to better analyse the effects of various types of food on the glucose‐level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose‐level using glucose measuring sensors. For food recognition, we rely on several feature extraction and classification techniques individually and jointly using an early and three different late fusion techniques, namely (i) Particle Swarm Optimisation (PSO), (ii) Genetic Algorithms (GA) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several handcrafted and deep features and compare the results against state‐of‐the‐art. In addition, we collect a large‐scale dataset containing images from several types of local Middle‐Eastern food, which is intended to become a powerful support tool for future research in the domain.

show abstract

Malaysian food recognition and calorie counter application

Cited by 10 publications

References 4 publications

Mobile game model for monitoring Malaysian food calories intake using image recognition

Mobile game model for monitoring Malaysian food calories intake using image recognition

Mobile Food Journalling Application with Convolutional Neural Network and Transfer Learning: A Case for Diabetes Management in Malaysia

Automatic food recognition system for middle‐eastern cuisines

Contact Info

Product

Resources

About