1.C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data Mining Knowl., vol. 2, no. 2, pp. 121–167, 1998.
He stated that the method used is kernel mapping to construct SVM. Training is used for very large datasets is an unsolved problem. Some work has been done on training a multiclass SVM in one step.
2. K. Muller, S. Mika, G. Ratsch, K. Tsuda, and B. Scholkopf, "An introduction to kernel-based learning," IEEE Trans. Neural Netw., vol. 12, no. 2, pp. 181–201, Mar. 2001.
He stated about discriminant analysis, and kernel principal component analysis are used as examples for successful kernel-based learning methods. Here full treatment of all available literature was not attempted. Kernel-based learning is indeed highly competitive.
3. Yuto Maruyama, Gamhewage C. de Silva, Toshihiko Yamasaki and KiyoharuAizawa,
" Personalization of Food Image Analysis", IEEE Xplore, November 2010.
He stated on the Bayesian network the results of the analysis will be improved. The accuracy level is up to 92%. Results are easily modified when the analysis contains an error.
4. Ms. Ankita A. Podutwar, Prof. Pragati D. Pawar, Prof. Abhijeet V. Shinde, "A Food Recognition System for Calorie Measurement", International Journal of Advanced Research in Computer and Communication Engineering, Vol. 6, Issue 1, January 2017.Technique used for segmentation is by Fuzzy C means and classification by SVM. The average accuracy obtained is 89%. Group of images is detected and segmented.
5. Ms. Ankita A. Podutwar, Prof. Abhijeet V. Shinde, "Calorie and Nutrition Measurement Based on Food Image Processing", International Journal of Recent Trends in Engineering & Research (IJRTER) Volume 02, Issue 04; April – 2016.Diaware, semi-automatic, mobile diet data recorder system are proposed in this paper. The result is based on 92.6%. This system was developed to identify the food image is good or rotten.
6.ParisaPouladzadeh, ShervinShirmohammadi, and Rana Al-Maghrabi. Measuring Calorie and Nutrition From Food Image. IEEE Transactions on Instrumentation and Measurement, Vol. 63, NO. 8, August 2014. He stated that train accuracy will not be high as expected. Dataset uses 300 images of food.
7.S. Jasmine Minija , W.R. Sam Emmanuel. Food image Classification using Sphere Shaped Support Vector Machine. Proceedings of the international conference on inventive Computing and Informatics. (ICICI 2017). He stated that the technique used for feature extraction is local and global extraction and for segmentation uses SS-SVM. Train the dataset of accuracy 95%. The dataset contains 100 images.
8.ManpreetkourBasantsinghSardar, Dr. Sayyad D. Ajij. Fruit Recognition and its Calorie Measurement: An Image Processing Approach. International Journal of Engineering and Computer Science ISSN: 2319-7242 Volume 5 issue 10 Oct. 2016. He stated that train the dataset of accuracy 94.98%. For training uses 125 images and 5 real classes. Uses multi-SVM classifier for a good result. Take approximately 35 seconds to compute the result.
9.Patrick McAllister, HuiruZheng, Anne MoorheadSemi-automated system for predicting calories in photographs of meals2015 IEEE International Conference on Engineering, Technology, and Innovation/ International Technology.
He stated that the training dataset has an error of 11.82%. K-means clustering is used for the segmentation of images. Classify the type of food and won't identify the type of food in International Management Conference (ICE/ITMC)
10.AbdulhamidHaidar, Haiwei Dong and NikolaosMavridis. Image-Based Date Fruit Classification IEEE Conference on Ultra Modern Telecommunications and Systems, 2012. He stated that the top accuracies ranged between 89% and 99%. The technique used for feature extraction in computer vision and pattern recognition. Nearest neighbor methods are not accurate.
11.Parish pouladzadeh, Gregorio Villalobos, Rana almaghrabi, Shervin shrimp Hammadi, " a novel SVM based food recognition method for calorie measuring applications " IEEE international conference on multimedia and expo workshops,2012He states that identifying food items in an image by using image processing and segmentation, food classification using SVM, food portion area measurement, and calorie measurement based on food portion and nutritional tables.
12.Geeta Shroff, Asim smallage, "neural networks based food recognition and calorie calculation for diabetes patients," diawear technical report, pp.1-8, March 2009
It states using a MATLAB and hardware interfacing controller for measuring the mass with a high megapixel camera and precision sensor to take liquid food using SVM, food portion area measurement and the results indicated reasonable accuracy of our method in area measurement.
13.Y. Yang, Y. Yue, Z. Wei, J . Robert, W. Jia, and M. Sun ." food volume calculation in different imaging scenarios."In 2011 IEEE 37th annual northeast bioengineering conference (NEBEC). April 2011, pp 1-2. He claims the FRS is an application directly related to the dietary intake assessment applications that take advantage of image processing and pattern recognition to calculate the volume of the food in any selected image and thus estimate the number of calories and nutrient values.
14.V Hema Latha reddy, Soumya Kumari, visit Muralidharan, Karan Gigoo and Bhushan S. Thakare, "State of the Art Literature Survey 2018 on Food Recognition and Calorie Measurement", International Conference on Communications and Cyber-Physical Engineering (ICCCE 2019), 2019. They addressed the effectiveness of CNNsfor food image recognition and detection. By building a food image dataset from images uploaded by a large number of real users through observation of trained convolution kernels, they confirmed that color features are essential to food image recognition applied.