Hybrid ML Recommender System for Visually Similar Product Images

Authors

  • Bagyalakshmi V Principal Scientist, Tata Consultancy Services, Chennai, India
  • Gaurav Sharma Principal Scientist, Tata Consultancy Services, Chennai, India
  • Meghna Mahajan Domain Consultant, Tata Consultancy Services, Bangalore, India
  • Muzzammil Ahmed Data Science Developer, Tata Consultancy Services, Chennai, India
  • Kalyan Prakash Baishya AI&ML Architect, Tata Consultancy Services, Pune, India
  • Kuruvilla Abraham Senior Data Scientist, Tata Consultancy Services, Delhi, India

DOI:

https://doi.org/10.26438/ijcse/v9i11.4550

Keywords:

CNN (Convolution Neural Network), AI (Artificial Intelligence), Image Processing, Clustering

Abstract

Fashion industry and innovation go hand in hand & technology could not be left far behind when it comes to innovation. Retail fashion is one of the early adopters of artificial intelligence when it comes to product development. AI based applications provides ease of search and shop for products. Either in the form of visual based search or suggesting products from same category with different attributes, retailers are providing every possible easement to customers for bet- ter shopping experience. With AI onboard, there is a huge infrastructure cost associated as well. In computer vision (AI), model training requires a good image data with labels & high-capacity platform for starters. Considering these facts, only using transformed feature vector of product images to generate clusters based on feature similarity can reduce the data de- pendency. Additionally, distance metric can be used to compute the feature distances & retrieval of top-k similar images by reverse indexing of image features to their corresponding images.

References

[1] B. P. Amiruddin and R. E. Abdul Kadir, "CNN Architectures Performance Evaluation for Image Classification of Mosquito in Indonesia", 2020 International Seminar on Intelligent Technology and Its Applications (ISITIA), 2020, pp. 223-227, doi: 10.1109/ISITIA49792.2020.9163732.

[2] Aayush Kumar Singh, Abhishek Kumar and Kuldeep. "Image to Image Search using K-means Clustering". International Journal of Computer Applications (0975 – 8887) Volume 182 – No. 46, pp. - March 2019

[3] D. M. Chan, R. Rao, F. Huang and J. F. Canny, “T-SNE-CUDA: GPU-Accelerated T-SNE and its Applications to Modern Data", 2018 30th International Symposium on Computer Architecture and High-Performance Computing (SBAC-PAD), 2018, pp. 330-338, doi: 10.1109/CAHPC.2018.8645912.

[4] Yash Baid, Avinash Dhole, "Food Image Classification Using Deep Learning Techniques", International Journal of Computer Sciences and Engineering, Vol.9, Issue.7, pp.11-15, 2021

[5] Astha Pathak, Avinash Dhole, "Image classification Method in detecting Lungs Cancer using CT images: A Review", Interna-tional Journal of Computer Sciences and Engineering, Vol.9, Is-sue.5, pp.37-42, 2021.

Downloads

Published

2021-11-30
CITATION
DOI: 10.26438/ijcse/v9i11.4550
Published: 2021-11-30

How to Cite

[1]
B. V, G. Sharma, M. Mahajan, M. Ahmed, K. P. Baishya, and K. Abraham, “Hybrid ML Recommender System for Visually Similar Product Images”, Int. J. Comp. Sci. Eng., vol. 9, no. 11, pp. 45–50, Nov. 2021.

Issue

Vol. 9 No. 11 (2021): IJCSE November Edition

Section

Technical Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.