Artwork Image Recognition

[aditya0929]

Pull Request for DL-Simplified 💡

Issue Title : Artwork Image Recognition #356

• Info about the related issue (Aim of the project) : to predict correct artwork image labels corresponding to their corresponding artwork images
• Name: Aditya Narayan Jha
• GitHub ID: https://github.com/aditya0929
• Email ID: [email protected]
• Idenitfy yourself: (Mention in which program you are contributing in. Eg. For a JWOC 2022 participant it's, JWOC Participant) ssoc-2023

Closes: #356

Describe the add-ons or changes you've made 📃

I started developing a CNN model from scratch but it didn't give me any good accuracy results so further ahead i went with a different approach of dealing with the dataset using RESNET models, out of all the models I had tried RESNET152V2 gave the best accuracy in the first 11 iterations itself so that was the one I considered.

InceptonV3 has generally proved good on larger dataset giving a constant decent accuracy and that why i chose inception rather than other models.

lastly i chose xception as it is a preferred choice over other models due to its exceptional performance in image classification tasks. With its innovative depth-wise separable convolutions, Xception achieves high accuracy while maintaining a smaller model size, making it ideal for resource-constrained environments. Its efficiency, accuracy, and versatility make it a compelling option for various image recognition challenges.

Type of change ☑️

What sort of change have you made:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Code style update (formatting, local variables)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested? ⚙️

i had predicted 5 image labels for each of the models and all of them came to be the exactly true and in accordance to their respective accuracy score .
i had taken the classification score and f1 score into consideration where it depicted individual accuracy of each classes of all three models .

Here are the predicted labels

Accuracy Comparison

Model	Accuracy
Xception	94%
InceptionV3	94%
ResNet152V2	97%

Checklist: ☑️

• My code follows the guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly wherever it was hard to understand.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added things that prove my fix is effective or that my feature works.
• Any dependent changes have been merged and published in downstream modules.

[github-actions]

Our team will soon review your PR. Thanks @aditya0929 :)

[abhisheks008]

Your PR is approved and ready to be merged.
@aditya0929