Performance Analysis of Forgery Detection with CNN and Sand Cat Swarm Optimization
implementation plan
Step 1: Initially, we load and collect the data from the SROIE datasetv2 image dataset.
Step 2: Then, we pre-process the collected data using Grayscale Conversion,Image Resizing Normalization and Morphological Operation techniques.
Step 3: Next, we detect Original and tampered text using Convolutional Neural Network (CNN) Detectron2 Training algorithm.
Step 4: Next, we perform Foreground Extraction using GrabCut algorithm with Gaussian Mixture Model (GMM).
Step 5: Next, we extract the features using GLCM with the Local Binary Pattern (LBP) method.
Step 6: Next, we classify the original and tampered image using CNN with VGGNet architecture.
Step 7: Next, we optimize the images using Sand-Cat-Swarm-based Optimization Method (SCSO)
Step 8: Finally, we plot performance for the following metrics:
8.1: Number of epochs vs. Accuracy (%)
8.2: Number of epochs vs. Precision (%)
8.3: Number of epochs vs. Recall (%)
8.4: Number of epochs vs. F1-score (%)
8.5: True positive rate (FPR) vs. False positive rate (TPR)
Software requirement:
1. Development Tool: Python 3.11.4 or above
2. Operating System: Windows 10 (64-bit) or above
Dataset:
Link :- https://www.kaggle.com/datasets/urbikn/sroie-datasetv2
Note
1) If the plan does not meet your requirements, provide detailed steps, parameters, models, or expected results in advance. Once implemented, changes won’t be possible without prior input; otherwise, we’ll proceed as per our implementation plan.
2) If the plan satisfies your requirement, Please confirm with us.
3) Project based on Simulation only, not a real time project.
4) If you have any changes in the Dataset , kindly provide before implementation.
5) Please understand that any modifications made to the confirmed implementation plan will not be made after the project development.
We perform with an Existing Approach : Reference 17: Title :- Image Forgery Detection by CNN and Pretrained VGG16 Model
