The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

Automated Catalogue Management and Image Quality Assessment using CNN and Deep Learning

Submitted by Souradip Chakraborty (@souradip) on Monday, 3 June 2019

Session type: Short talk of 20 mins

Abstract

Catalogue management is a very important aspect in the field of ecommerce as it helps the visitors in efficiently selecting the necessary interest items. In every retail website, all the items in the catalogue are in a particular order and orientation of different categories whose manual grouping and ordering takes a lot of time. Secondly, image quality assessment plays a very important part in catalogue management since the quality of the images sent by the vendor are not always of adequate quality which when displayed on the website results in customer dissatisfaction.

In this work, we have developed an entire pipeline where the first task is to automatically classify the various orientations (front view, side view, top view etc.) of the images sent by the vendor using transfer learning. In the second part of our pipeline, we have eased the process of catalogue management with the image quality assessment of the vendor images using Structural similarity index and Deep learning techniques.

Outline

•Introduction on application of advanced analytics in Retail and at Walmart Labs
In this introductory session, main emphasis will be on the significance of Analytics in retail and e-commerce domain. (some examples).

•Research Problem to be presented -

1.Research Topic - Automated Catalog Management and Image Quality Assessment using Computer Vision and Deep Learning.

2.Business Problem In this section, the business problem will be discussed and why catalog management and image quality assessments are critical to business and how it can impact business.

3.Methodology and Analysis- This is the most important section as in this section, the algorithmic flow of the process will be discussed in details along with certain state of the art methodologies in Computer vision and image processing will also be illustrated.

4.Algorithms and Illustration with Python Implementation –

•Image Features and Attributes -The first step will be on extraction of image features like Histogram of oriented gradient based features, simple Fourier transformed features, Kernel PCA features etc.

•Advanced Feature Extraction and Deep Learning- This section will mainly focus on how advanced and much more informative features are being extracted from images using pre-trained Convolution Neural Network models.

•Image orientation Classification - This section will illustrate on how using the features extracted, image orientation classification is being done. Also, which machine learning models to use for the final classification will also be discussed.

•Image Quality Assessment - This section will be on a very important and research topic i.e. image quality assessment. It will focus on shortcomings of various normally used quality metric like MSE, SNR etc. and the primary shortcomings of the metric.
The metric Structural similarity index will be introduced with its advantages.

Conclusion on Image Quality Enhancement.

Requirements

Basic knowledge of Machine Learning,Deep Learning, Computer Vision and Transfer Learning.

Speaker bio

Currently working as a Statistical Analyst at Walmart Labs in International Sourcing domain. Selected as the Youngest Technical Speaker in the very prestigious Analytics Vidhya’s Data Hack Summit 2018 and Target Talks AI‘2019.
I have over 5 US patents filed (as a part of Walmart Labs) in the field of AI and Machine Learning applications in Retail Domain.
I have also been a part of ANZ Bank, Tata Steel Research and Development and Petrabytes Corp. in the field of Data Science and research.
Current field of research interest lies in Deep Learning,Machine Learning,Computer Vision and Natural Language Processing.
Did my Masters from Indian Statistical Institute Bangalore (Batch Topper) and have publications in ISI Journal in the field of Multivariate Statistical Quality Control.(Technical Report)
Apart from that I have publications in the field of Advanced Recommender systems using Natural Language Processing ,Computer Vision and Mathematical Morphology , also an IEEE publication in Stability Analysis of Network Control System.
Did my graduation from Jadavpur University in the field of Electronics engineering and have worked as a research analytical engineer in Amec Foster Wheeler Pvt Ltd for 2 years and received special mention from Clients like Exxon Mobil.

Links

Slides

https://drive.google.com/file/d/1GHQIhRXjuFVmD5SmDS6Jr1JK6KnV2MOT/view?usp=sharing

Comments

  • Abhishek Balaji (@booleanbalaji) Reviewer 6 months ago

    Hi Souradip,

    Thank you for submitting a proposal. We need to see more details in your slides and a preview video to evaluate your proposal. Your slides must cover the following:

    • Problem statement/context, which the audience can relate to and understand. The problem statement has to be a problem (based on this context) that can be generalized for all.
    • What were the tools/frameworks available in the market to solve this problem? How did you evaluate these, and what metrics did you use for the evaluation? Why did you pick the option that you did?
    • Explain how the situation was before the solution you picked/built and how it changed after implementing the solution you picked and built? Show before-after scenario comparisons & metrics.
    • What compromises/trade-offs did you have to make in this process?
    • What is the one takeaway that you want participants to go back with at the end of this talk? What is it that participants should learn/be cautious about when solving similar problems?

    We need your updated slides and preview video by Jun 17, 2019 to evaluate your proposal. If we do not receive an update, we’d be moving your proposal for evaluation under a future event.

  • Abhishek Balaji (@booleanbalaji) Reviewer 5 months ago

    Rejected since proposer hasnt responded to comments or uploaded preview video. Will be considered for a future event if updated.

Login with Twitter or Google to leave a comment