[{“box”:0,”content”:”[if 992 equals=”Open Access”]n
n
Open Access
nn
n
n[/if 992]n
n
n
n
n
n
Sakshi Londhe, Smita Palnitkar, Vishnupriya Kannadkar, Shubhangi Magar,
n
- n t
n
n
n[/foreach]
n
n[if 2099 not_equal=”Yes”]n
- [foreach 286] [if 1175 not_equal=””]n t
- Student, Assistant Professor, Student, Student Department of Electronics & Telecommunication Engineering, Smt. Kashibai Navale College of Engineering (SKNCOE), SPPU, Pune, Department of Electronics & Telecommunication Engineering, Smt. Kashibai Navale College of Engineering (SKNCOE), SPPU, Pune, Department of Electronics & Telecommunication Engineering, Smt. Kashibai Navale College of Engineering (SKNCOE), SPPU, Pune, Department of Electronics & Telecommunication Engineering, Smt. Kashibai Navale College of Engineering (SKNCOE), SPPU, Pune Maharashtra, Maharashtra, Maharashtra, Maharashtra India, India, India, India
n[/if 1175][/foreach]
n[/if 2099][if 2099 equals=”Yes”][/if 2099]n
Abstract
nIn the deep learning era, image understanding is advancing in sophistication, encompassing both semantic interpretation and the generation of meaningful image descriptions. To achieve this, deep neural networks must undergo specific cross-model training; these networks must be both simple enough to handle a wide range of inputs and complex enough to encode the fine contextual information associated with the image. An appropriate example of the previously described picture comprehension problem is the conversion of a food image to its preparation instructions. This study introduces a novel method that employs cross-model training of CNN, LSTM, and Bi-Directional LSTM to obtain a compressed representation of cooking instructions from a recipe image. Variable instruction length and the quantity of instructions per recipe is the biggest problem in this. The system addresses challenges such as varying instructions, differing numbers of instructions per recipe, and the presence of multiple food items in the image. The model successfully shrinks instructions with high similarity to original instructions, especially on Indian cuisine data. This model can be useful for information retrieval and automatic recipe recommendations.
These results highlight the potential of deep learning in recipe generation from food images, offering a promising solution for culinary enthusiasts seeking convenient access to cooking instruction.
n
Keywords: Training, Image Coding, Deep Learning, Context Modeling Neural Network, Information Retrieval, CNN, LSTM.
n[if 424 equals=”Regular Issue”][This article belongs to Journal of Operating Systems Development & Trends(joosdt)]
n
n
n
n
n
nn[if 992 equals=”Open Access”] Full Text PDF Download[/if 992] n
nn[if 379 not_equal=””]n
Browse Figures
n
n[/if 379]n
References
n[if 1104 equals=””]n
- Salvador A, Drozdzal M, Giró-i-Nieto X, Romero A. Inverse cooking: Recipe generation from food images. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019 (pp. 10453-10462).
- Salvador A, Hynes N, Aytar Y, Marin J, Ofli F, Weber I, Torralba A. Learning cross-modal embeddings for cooking recipes and food images. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 3020-3028).
- Gao X, Feng F, He X, Huang H, Guan X, Feng C, Ming Z, Chua TS. Hierarchical attention network for visually-aware food recommendation. IEEE Transactions on Multimedia. 2019 Oct 4;22(6):1647-59.
- Chen JJ, Ngo CW, Chua TS. Cross-modal recipe retrieval with rich food attributes. InProceedings of the 25th ACM international conference on Multimedia 2017 Oct 23 (pp. 1771-1779).
- Li J, Monroe W, Ritter A, Galley M, Gao J, Jurafsky D. Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541. 2016 Jun 5.
- Carvalho M, Cadène R, Picard D, Soulier L, Thome N, Cord M. Cross-modal retrieval in the cooking context: Learning semantic text-image embeddings. InThe 41st International ACM SIGIR Conference on Research & Development in Information Retrieval 2018 Jun 27 (pp. 35-44).
- Fujii T, Sei Y, Tahara Y, Orihara R, Ohsuga A. “Never fry carrots without chopping” Generating Cooking Recipes from Cooking Videos Using Deep Learning Considering Previous Process. International Journal of Networked and Distributed Computing. 2019 Jul;7(3):107-12.
- Pinel F, Varshney LR, Bhattacharjya D. A culinary computational creativity system. Computational creativity research: Towards creative machines. 2015:327-46.
- Teng CY, Lin YR, Adamic LA. Recipe recommendation using ingredient networks. InProceedings of the 4th annual ACM web science conference 2012 Jun 22 (pp. 298-307).
- C K Srinivasa, Harshitha S, et al. Recipe Finder Web Application Using Convolutional Neural Network. International Journal of Research Publication and Reviews. 2024;5(5):10071-10076.
nn[/if 1104][if 1104 not_equal=””]n
- [foreach 1102]n t
- [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]
n[/foreach]
n[/if 1104]
nn
nn[if 1114 equals=”Yes”]n
n[/if 1114]
n
n
n
Journal of Operating Systems Development & Trends
n
n
n
n
n
n
| Volume | 11 | |
| [if 424 equals=”Regular Issue”]Issue[/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] | 02 | |
| Received | July 3, 2024 | |
| Accepted | July 31, 2024 | |
| Published | August 8, 2024 |
n
n
n
n
n
n nfunction myFunction2() {nvar x = document.getElementById(“browsefigure”);nif (x.style.display === “block”) {nx.style.display = “none”;n}nelse { x.style.display = “Block”; }n}ndocument.querySelector(“.prevBtn”).addEventListener(“click”, () => {nchangeSlides(-1);n});ndocument.querySelector(“.nextBtn”).addEventListener(“click”, () => {nchangeSlides(1);n});nvar slideIndex = 1;nshowSlides(slideIndex);nfunction changeSlides(n) {nshowSlides((slideIndex += n));n}nfunction currentSlide(n) {nshowSlides((slideIndex = n));n}nfunction showSlides(n) {nvar i;nvar slides = document.getElementsByClassName(“Slide”);nvar dots = document.getElementsByClassName(“Navdot”);nif (n > slides.length) { slideIndex = 1; }nif (n (item.style.display = “none”));nArray.from(dots).forEach(nitem => (item.className = item.className.replace(” selected”, “”))n);nslides[slideIndex – 1].style.display = “block”;ndots[slideIndex – 1].className += ” selected”;n}n”}]