{"id":20434776,"url":"https://github.com/netcodez/image-classification-convolutional-neural-network","last_synced_at":"2025-03-05T06:26:30.785Z","repository":{"id":206884392,"uuid":"717906996","full_name":"Netcodez/Image-classification-Convolutional-Neural-Network","owner":"Netcodez","description":"Deep learning: Image Classification using a Convolutional Neural Network","archived":false,"fork":false,"pushed_at":"2023-11-13T00:16:11.000Z","size":390,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-15T19:27:50.464Z","etag":null,"topics":["computer-vision","convolutional-neural-networks","deep-learning","image-classification","image-processing","image-recognition"],"latest_commit_sha":null,"homepage":"https://netcodez.github.io/Image-classification-Convolutional-Neural-Network/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Netcodez.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-11-13T00:04:31.000Z","updated_at":"2023-11-13T00:19:30.000Z","dependencies_parsed_at":"2023-11-13T01:24:55.040Z","dependency_job_id":"5abcef2e-4b65-48dd-bdad-c8cde34102bf","html_url":"https://github.com/Netcodez/Image-classification-Convolutional-Neural-Network","commit_stats":null,"previous_names":["netcodez/image-classification--cnn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Netcodez%2FImage-classification-Convolutional-Neural-Network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Netcodez%2FImage-classification-Convolutional-Neural-Network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Netcodez%2FImage-classification-Convolutional-Neural-Network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Netcodez%2FImage-classification-Convolutional-Neural-Network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Netcodez","download_url":"https://codeload.github.com/Netcodez/Image-classification-Convolutional-Neural-Network/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241977333,"owners_count":20051802,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","convolutional-neural-networks","deep-learning","image-classification","image-processing","image-recognition"],"created_at":"2024-11-15T08:28:52.682Z","updated_at":"2025-03-05T06:26:30.761Z","avatar_url":"https://github.com/Netcodez.png","language":"Jupyter Notebook","readme":"# Project Title: American Sign Language (ASL) Image Classification\nDeep learning: Image Classification using a Convolutional Neural Network\n\n## Overview\nAmerican Sign Language (ASL) serves as a primary means of communication for many deaf individuals. This project delves into the development of a convolutional neural network (CNN) designed to classify images of ASL letters. The primary goal is to construct a model capable of recognizing individual letters, laying the groundwork for the creation of a sign language translation system.\n\n## Project Structure\n\n### 1. Introduction to ASL\n- Brief overview of American Sign Language and its significance.\n- Discussion on the relevance of computer vision systems in translating sign language to spoken language.\n\n### 2. Data Loading and Preprocessing\n- Utilization of a pre-shuffled dataset containing images of ASL letters.\n- Loading, examining, and preprocessing the data for model training.\n\n### 3. Visualizing the Training Data\n- Displaying a selection of training images along with their corresponding labels (letters).\n\n### 4. Dataset Examination\n- Analyzing the distribution of letters in the training and test datasets to ensure balance.\n\n### 5. One-Hot Encoding\n- Transforming categorical labels into one-hot encoded vectors for model training.\n\n### 6. Model Definition\n- Building a CNN to classify ASL images with convolutional and pooling layers.\n- Model summary to provide an overview of the network architecture.\n\n### 7. Model Compilation\n- Compiling the model with an appropriate loss function, optimizer, and evaluation metric.\n\n### 8. Model Training\n- Fitting the model to the training data and evaluating its performance on the validation set.\n\n### 9. Model Testing\n- Evaluating the trained model on the test dataset to assess its accuracy.\n\n### 10. Visualizing Misclassifications\n- Identifying and displaying images that were misclassified by the model for further analysis.\n\n## How to Use\n1. Ensure you have the necessary dependencies installed (e.g., TensorFlow, NumPy, Matplotlib).\n2. Execute the provided code cells in a Jupyter notebook or an equivalent environment.\n3. Follow the step-by-step instructions for data loading, preprocessing, model training, and evaluation.\n4. Examine the model's performance on the test set and visualize misclassifications.\n\n## Conclusion\nThe CNN model for ASL image classification gives an accuracy of 93% on the test set. Further enhancements and refinements can be explored to improve the model's accuracy and robustness using Dropuouts or Batch Normalization including considering more epochs during the training process.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnetcodez%2Fimage-classification-convolutional-neural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnetcodez%2Fimage-classification-convolutional-neural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnetcodez%2Fimage-classification-convolutional-neural-network/lists"}