Merge pull request #589 from ananyag309/update

Skin-Cancer-Detection
UppuluriKalyani · Oct 26, 2024 · be2a630 · be2a630
2 parents 1a866d3 + 0595dd9
commit be2a630
Show file tree

Hide file tree

Showing 9 changed files with 51 additions and 0 deletions.
diff --git a/Prediction Models/Skin Cancer Detection/Output-1.png b/Prediction Models/Skin Cancer Detection/Output-1.png
diff --git a/Prediction Models/Skin Cancer Detection/Output-2.png b/Prediction Models/Skin Cancer Detection/Output-2.png
diff --git a/Prediction Models/Skin Cancer Detection/Output-3.png b/Prediction Models/Skin Cancer Detection/Output-3.png
diff --git a/Prediction Models/Skin Cancer Detection/Output-4.png b/Prediction Models/Skin Cancer Detection/Output-4.png
diff --git a/Prediction Models/Skin Cancer Detection/Output-5.png b/Prediction Models/Skin Cancer Detection/Output-5.png
diff --git a/Prediction Models/Skin Cancer Detection/Output-6.png b/Prediction Models/Skin Cancer Detection/Output-6.png
diff --git a/Prediction Models/Skin Cancer Detection/readme.md b/Prediction Models/Skin Cancer Detection/readme.md
@@ -0,0 +1,41 @@
+# Skin Cancer Detection
+
+This project focuses on detecting skin cancer using a Convolutional Neural Network (CNN) model trained on images of skin lesions. The aim is to classify skin lesions into two categories: benign (non-cancerous) and malignant (cancerous), which can help in the early detection of skin cancer and potentially save lives.
+
+## 📋 Problem Description
+
+Skin cancer is a prevalent form of cancer, and early detection can significantly increase the chances of successful treatment. Traditional diagnostic methods can be costly and may not always catch early signs. This project aims to automate the detection of skin cancer from dermoscopic images, providing a quick and reliable diagnosis.
+
+## 🧠 Model Overview
+
+The model is based on a Convolutional Neural Network (CNN), which is well-suited for image classification tasks. The architecture includes layers for convolution, pooling, and fully-connected neural networks, enabling the model to learn important features from the images and classify them into either benign or malignant.
+
+## 📁 Dataset
+
+The dataset used contains labeled images of skin lesions, categorized as benign or malignant. Each image is preprocessed to a standard size suitable for input to the model (e.g., 128x128 pixels).
+
+### Data Preparation:
+- **Data Augmentation:** Techniques like rotation, zoom, and horizontal flipping are used to increase the diversity of the training data.
+- **Splitting:** The data is split into training and validation sets to assess the model's performance.
+
+## 🚀 Installation and Setup
+
+### Prerequisites
+
+Ensure you have the following dependencies installed:
+- Python 3.x
+- TensorFlow
+- Keras
+- NumPy
+- Matplotlib
+- scikit-learn
+- Jupyter Notebook (optional, for running `.ipynb` files)
+
+### Installation
+
+Clone the repository and install the required dependencies:
+
+```bash
+git clone https://github.com/yourusername/skin-cancer-detection.git
+cd skin-cancer-detection
+pip install -r requirements.txt
diff --git a/Prediction Models/Skin Cancer Detection/requirements.txt b/Prediction Models/Skin Cancer Detection/requirements.txt
@@ -0,0 +1,9 @@
+numpy==1.23.5
+pandas==1.5.3
+matplotlib==3.7.2
+scikit-learn==1.3.0
+tensorflow==2.13.0
+keras==2.13.1
+Pillow==9.4.0
+opencv-python==4.8.0.76
+jupyter==1.0.0  # If you want to use Jupyter Notebook
diff --git a/Prediction Models/Skin Cancer Detection/skin-cancer-detection.ipynb b/Prediction Models/Skin Cancer Detection/skin-cancer-detection.ipynb