Abstract

Applications involving ingredient recognition are very limited and most do not work in less ideal conditions like the ones faced in a typical kitchen. The main reason for this is the dataset that the existing models are based on. These datasets do not account for real-world factors like noise, blur, etc. in the input image since they are trained on images obtained from controlled and nearly idealistic environments. For these reasons, a new dataset was created, consisting of real-world images which represent the scenarios users are most likely to face during daily use. A simple and robust system was developed that aims to address this issue. A multi-label classification model was built to identify multiple ingredients present in a single image. A personalized recommendation system that recommends a list of South Indian recipes to users based on the ingredients identified was also developed.

References

• Zhang, Lin, Jianbo Zhao, Si Li, Boxin Shi, and Ling-Yu Duan. "From Market to Dish: Multi-ingredient Image Recognition for Personalized Recipe Recommendation." In 2019 IEEE International Conference on Multimedia and Expo (ICME), pp. 1252-1257. IEEE, 2019.
• Yeh, Chih-Kuan, Wei-Chieh Wu, Wei-Jen Ko, and Yu- Chiang Frank Wang. "Learning deep latent space for multi-label classification." In Thirty-First AAAI Conference on Artificial Intelligence. 2017.
• Garrido-Merchán, Eduardo C., and Alejandro Albarca- Molina. "Suggesting cooking recipes through simulation and bayesian optimization." In International Conference on Intelligent Data Engineering and Automated Learning, pp. 277-284. Springer, Cham, 2018.
• Rocha, Anderson, Daniel C. Hauagge, Jacques Wainer, and Siome Goldenstein. "Automatic fruit and vegetable classification from images." Computers and Electronics in Agriculture 70, no. 1 (2010): 96-104.
• He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep residual learning for image recognition." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778. 2016.
• Szegedy, Christian, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. "Rethinking the inception architecture for computer vision." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818-2826. 2016.
• Nguyen, Long D., Dongyun Lin, Zhiping Lin, and Jiuwen Cao. "Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation." In 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5. IEEE, 2018.
• Huang, Gao, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. "Densely connected convolutional networks." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708. 2017.
• ratingcollector.net, Website created for collecting ratings from users. URL: www.ratingcollector.net [Last accessed: July 2020]
• Sarwar, Badrul, George Karypis, Joseph Konstan, and John Riedl. "Item-based collaborative filtering recommendation algorithms." In Proceedings of the 10th international conference on World Wide Web, pp. 285- 295. 2001.
• He, Xiangnan, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. "Neural collaborative filtering." In Proceedings of the 26th international conference on world wide web, pp. 173-182. 2017.
• Dziugaite, Gintare Karolina, and Daniel M. Roy. "Neural network matrix factorization." arXiv preprint arXiv:1511.06443 (2015).
• Krishna, Vaibhav, Tian Guo, and Nino Antulov-Fantulin. "Is Simple Better? Revisiting Non-linear Matrix Factorization for Learning Incomplete Ratings." In 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 1289-1293. IEEE, 2018.