{"id":18917021,"url":"https://github.com/biswadeep-roy/human-emotion-detection-using-deep-learning","last_synced_at":"2026-05-08T13:04:41.528Z","repository":{"id":198462697,"uuid":"700844290","full_name":"biswadeep-roy/Human-Emotion-Detection-using-Deep-Learning","owner":"biswadeep-roy","description":"This project implements a deep learning model for the detection of human emotions in images. It uses Convolutional Neural Networks (CNNs) to classify images into three emotional categories: angry, happy, and sad.","archived":false,"fork":false,"pushed_at":"2023-12-01T06:12:01.000Z","size":1219,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-31T15:25:51.097Z","etag":null,"topics":["python","python3","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/biswadeep-roy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-10-05T12:10:22.000Z","updated_at":"2023-12-21T06:37:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"dfc52981-4a84-4167-ac4c-b6228d130a86","html_url":"https://github.com/biswadeep-roy/Human-Emotion-Detection-using-Deep-Learning","commit_stats":null,"previous_names":["biswadeep-roy/human-emotion-detection-using-deep-learning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/biswadeep-roy%2FHuman-Emotion-Detection-using-Deep-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/biswadeep-roy%2FHuman-Emotion-Detection-using-Deep-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/biswadeep-roy%2FHuman-Emotion-Detection-using-Deep-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/biswadeep-roy%2FHuman-Emotion-Detection-using-Deep-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/biswadeep-roy","download_url":"https://codeload.github.com/biswadeep-roy/Human-Emotion-Detection-using-Deep-Learning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239914929,"owners_count":19717759,"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":["python","python3","tensorflow"],"created_at":"2024-11-08T10:23:29.643Z","updated_at":"2026-03-11T17:30:18.985Z","avatar_url":"https://github.com/biswadeep-roy.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Human-Emotion-Detection-using-Deep-Learning\nThis project implements a deep learning model for the detection of human emotions in images. It uses Convolutional Neural Networks (CNNs) to classify images into three emotional categories: angry, happy, and sad.\n\n![image](https://github.com/biswadeep-roy/Human-Emotion-Detection-using-Deep-Learning/assets/74821633/fbb5eabe-0dc9-46eb-92fb-b049ac031958)\n\n\n## Dataset\nThe dataset used in this project is the \"Human Emotions Dataset\" available on Kaggle. It consists of labeled images representing different emotions.\n\n### Dataset Link\n[Human Emotions Dataset](https://www.kaggle.com/muhammadhananasghar/human-emotions-datasethes)\n\n## Model Architecture\nThe model architecture is based on a modified LeNet-5 CNN architecture. It includes layers for data preprocessing, convolution, batch normalization, max-pooling, dropout, and fully connected layers. Regularization techniques are used to prevent overfitting.\n\n## Configuration\nThe project is configured with various hyperparameters, including batch size, image size, learning rate, and dropout rate, which can be adjusted as needed.\n\n## Training\nThe model is trained using TensorFlow and Keras. The training dataset is shuffled and preprocessed, and the model's performance is evaluated using a validation dataset.\n\n## Usage\nTo use this project, follow these steps:\n\n1. Clone the repository:\n\u003cbr/\u003e\n`git clone https://github.com/biswadeep-roy/Human-Emotion-Detection-using-Deep-Learning/`\n\u003cbr/\u003e\n`cd human-emotion-detection`\n\u003cbr/\u003e\n\n\n2. Install the required libraries:\n\n`pip install -r requirements.txt`\n\n\n3. Download and unzip the dataset (or use your own dataset) into the appropriate directories:\n- Training data: `/content/dataset/Emotions Dataset/Emotions Dataset/train`\n- Validation data: `/content/dataset/Emotions Dataset/Emotions Dataset/test`\n\n4. Adjust the configuration in the code as needed.\n\n5. Train the model.\n\n\n6. Evaluate the model.\n\n\n\n7. Make predictions on new data:\n\n\n\n\n## Results and Outcomes\n# Model Performance\nThe model achieved a significant level of accuracy in classifying human emotions in images.\nTraining and validation metrics, such as accuracy and loss, can be found in the training logs.\n# Key Outcomes\nSuccessful implementation of a modified LeNet-5 architecture for emotion detection.\nEfficient preprocessing of image data, including resizing and rescaling.\nEffective use of regularization techniques to prevent overfitting.\nDeployment of a TensorFlow-based deep learning model.\n# Challenges Faced\nMention any challenges you encountered during the project, such as data quality issues, overfitting, or performance optimization.\n# Future Improvements\nProvide insights into potential future improvements or enhancements for the project.\nIdeas may include fine-tuning hyperparameters, exploring different architectures, or incorporating real-time emotion detection from a video stream.\n# Acknowledgments\nExpress gratitude to any contributors, libraries, or datasets that played a significant role in achieving the project's outcomes.\n# Visualizations\nInclude any relevant visualizations, such as confusion matrices or ROC curves, to showcase the model's performance.\n\n## Author\n- (https://github.com/biswadeep_roy)\n\n## License\nThis project is licensed under the MIT License - see the [MIT](LICENSE) file for details.\n\nFeel free to reach out if you have any questions or suggestions!\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbiswadeep-roy%2Fhuman-emotion-detection-using-deep-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbiswadeep-roy%2Fhuman-emotion-detection-using-deep-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbiswadeep-roy%2Fhuman-emotion-detection-using-deep-learning/lists"}