Indian Currency Notes Classification

[aaradhyasinghgaur]

Closes :- #779 Approach I'd taken :- 1. Utilizing Multiple Network Architectures:

To classify different currency notes such as - 1)Ten Rupee Notes 2)Twenty Rupee Notes 3)Fifty Rupee Notes 4)Hundred Rupee Notes 5)Two Hundred Rupee Notes 6)Five Hundred Rupee Notes, and, 7)Two Thousand Rupee Notes. I will employ five distinct deep learning network architectures:

• DenseNet121

• Xception

• VGG16

• ResNet50

• InceptionV3

  2. Data Augmentation Techniques: To enhance the accuracy and robustness of the models, we will apply various data augmentation techniques such as:

• Rotation

• Zooming

• Flipping (horizontal and vertical)

• Shearing

• Brightness adjustments

These techniques will artificially expand the dataset and help prevent overfitting.

3. Model Performance Comparison: I will evaluate and compare the performance of each model using the following metrics and visualizations:

   • Accuracy Score: To measure the overall correctness of the models.
   • Loss Graph: To visualize the loss during training and validation phases.
   • Accuracy Graph: To track accuracy improvements over epochs.
   • Confusion Matrix: To provide a detailed breakdown of model performance across different diamond shapes, highlighting precision, recall, and F1 score for each category.

4. Exploratory Data Analysis (EDA): Before training the models, I will perform comprehensive exploratory data analysis (EDA) on the dataset to understand its structure. This will include:

   • Distribution of images across different diamond shapes.
   • Image quality and resolution consistency.
   • Identifying any class imbalances.
   • Visualizing sample images from each category.
   6. README File: A README file will be created to document the entire process according to the READMe template.

@Niketkumardheeryan @invigorzz313 kindly review my pr and assign suitable lablel (Level-3) for it if possible cause I have trained the dataset using 5 different models , used data-augmentation techniques to increase the accuracy of models in various conditions , added custom layesr , done EDA analysis which takes a lot of time and computational resources.

In case of no problems kindly merge it to the repo sir . thank you for your time.

[aaradhyasinghgaur]

@Niketkumardheeryan sir kindly review my pr and in case of no problems kindly merge it with suitable labels.

[aaradhyasinghgaur]

@invigorzz313 kindly review my pr and in case of no problems kindly merge it too with suitable label.

[Niketkumardheeryan]

@aaradhyasinghgaur you have made same mistake, please add readme.m file in main folder, and delete it from there .

[aaradhyasinghgaur]

Okay sir... I'll do it right now.

[invigorzz313]

@aaradhyasinghgaur The requirements.txt file should be properly written. You could optionally include versions but the descriptions should be commented.