{"id":29127299,"url":"https://github.com/erenisci/computer-vision","last_synced_at":"2026-04-13T09:32:38.404Z","repository":{"id":305656073,"uuid":"995985549","full_name":"erenisci/computer-vision","owner":"erenisci","description":"Comprehensive computer vision portfolio featuring face detection, object tracking, deep learning models, YOLO, GANs, and advanced image processing techniques.","archived":false,"fork":false,"pushed_at":"2025-07-21T09:16:52.000Z","size":68452,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-07-21T11:22:27.000Z","etag":null,"topics":["autoencoders","classification","cnn","computer-vision","deep-dream","deep-learning","face-detection","face-recognition","gans","haar-cascade","image-segmentation","object-detection","object-tracking","opencv","python","style-transfer","yolo"],"latest_commit_sha":null,"homepage":"","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/erenisci.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-04T09:38:49.000Z","updated_at":"2025-07-21T09:16:56.000Z","dependencies_parsed_at":"2025-07-21T11:32:59.037Z","dependency_job_id":null,"html_url":"https://github.com/erenisci/computer-vision","commit_stats":null,"previous_names":["erenisci/computer-vision"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/erenisci/computer-vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erenisci%2Fcomputer-vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erenisci%2Fcomputer-vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erenisci%2Fcomputer-vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erenisci%2Fcomputer-vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/erenisci","download_url":"https://codeload.github.com/erenisci/computer-vision/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/erenisci%2Fcomputer-vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31746294,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T09:16:15.125Z","status":"ssl_error","status_checked_at":"2026-04-13T09:16:05.023Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["autoencoders","classification","cnn","computer-vision","deep-dream","deep-learning","face-detection","face-recognition","gans","haar-cascade","image-segmentation","object-detection","object-tracking","opencv","python","style-transfer","yolo"],"created_at":"2025-06-30T00:36:42.613Z","updated_at":"2026-04-13T09:32:38.400Z","avatar_url":"https://github.com/erenisci.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Computer Vision\n\nThis repository includes a structured collection of **computer vision projects and exercises**, covering a full spectrum of concepts and implementations, such as:\n\n- **Face Detection and Recognition**\n\n  - Understanding the intuition behind **Cascade** and **HOG (Histogram of Oriented Gradients)** classifiers.\n  - Implementing face detection using **OpenCV** and **Dlib**.\n  - Detecting additional objects like **cars, clocks, eyes, and full human bodies**.\n  - Comparing the performance of **Haarcascade, HOG, and CNN-based detectors**.\n  - Detecting and recognizing faces using **images and live webcam feeds**.\n  - Exploring the **LBPH (Local Binary Patterns Histograms)** algorithm for face recognition.\n\n- **Object Tracking**\n\n  - Learning the intuition behind **KCF (Kernelized Correlation Filters)** and **CSRT (Discriminative Correlation Filter with Channel and Spatial Reliability)** trackers.\n  - Tracking objects in videos using the **OpenCV tracking API**.\n\n- **Neural Networks and Image Classification**\n\n  - Gaining a solid understanding of neural network theory, including **perceptrons, activation functions, weight updates, backpropagation, and gradient descent**.\n  - Implementing **dense (fully connected) neural networks** for image classification.\n  - Extracting pixels and engineered features from images to build effective models.\n\n- **Convolutional Neural Networks (CNNs)**\n\n  - Learning the theory and practical implementation of CNNs using **Python and TensorFlow**.\n  - Applying **transfer learning and fine-tuning** for high-accuracy classification.\n  - Using CNNs to classify **human emotions** (happy, anger, disgust, fear, surprise, neutral) in images and videos.\n\n- **Advanced Deep Learning Techniques**\n  - Compressing images using **linear and convolutional autoencoders**.\n  - Detecting objects in images and videos using **YOLO (You Only Look Once)**.\n  - Recognizing **gestures and actions** in video sequences.\n  - Generating **hallucinogenic images** with **Deep Dream**.\n  - Applying **style transfer** to blend the style of famous artworks into photos.\n  - Creating entirely new, synthetic images using **Generative Adversarial Networks (GANs)**.\n  - Performing **image segmentation** to extract meaningful structures and regions from images and videos.\n\nThis repository serves as a **comprehensive, hands-on portfolio** for mastering fundamental and advanced computer vision concepts.\n\n---\n\n### Repository Structure\n\n#### 00 - Face Detection\n\n- `face_detection.camera.py` – Real-time face detection using a webcam.\n- `face_detection.ipynb` – Face detection on static images.\n\n#### 01 - Face Recognition\n\n- `face_recognition.camera.py` – Real-time face recognition.\n- `face_recognition.ipynb` – Face recognition on images.\n- `preprocess_for_camera.ipynb` – Preprocessing for building a face recognition dataset.\n\n#### 02 - Object Tracking\n\n- `csrt_object_tracking.py` – Object tracking using CSRT tracker.\n- `kcf_object_tracking.py` – Object tracking using KCF tracker.\n\n#### 03 - Neural Network Image Classification\n\n- `neural_network_for_image_classification.ipynb` – Basic neural network for image classification.\n- `homework.ipynb` – Related assignment.\n\n#### 04 - Convolutional Neural Network (CNN) Classification\n\n- `convolutional_neural_network_for_image_classification.ipynb` – CNN for image classification.\n- `homework.ipynb` – Related assignment.\n\n#### 05 - Transfer Learning and Fine-Tuning\n\n- `transfer_learning.ipynb` – Transfer learning using pre-trained models.\n- `homework.ipynb` – Related assignment.\n\n#### 06 - Classification of Emotions\n\n- `classification_of_emotions.ipynb` – Classifying emotions from facial expressions.\n- `homework.ipynb` – Related assignment.\n\n#### 07 - Autoencoders for Image Compression\n\n- `autoencoders_for_image_compression.ipynb` – Image compression with autoencoders.\n- `homework.ipynb` – Related assignment.\n\n#### 08 - Object Detection with YOLO\n\n- `object_detection_with_yolo.ipynb` – Object detection using YOLO.\n\n#### 09 - Recognition of Gestures and Actions\n\n- `recognition_of_gestures_and_actions.ipynb` – Gesture and action recognition.\n\n#### 10 - Deep Dream\n\n- `deep_dream.ipynb` – Visual transformations using Google’s DeepDream.\n\n#### 11 - Style Transfer\n\n- `style_transfer.ipynb` – Applying artistic style transfer to images.\n\n#### 12 - Generative Adversarial Networks (GANs)\n\n- `gans.ipynb` – Generating synthetic images with GANs.\n- `homework.ipynb` – Related assignment.\n\n#### 13 - Image Segmentation\n\n- `image_segmentation.ipynb` – Performing image segmentation tasks.\n\n---\n\n## Notes\n\n- Each directory in this repository is **self-contained** and can be run independently.\n- Camera-based scripts (`*_camera.py`) are designed for **real-time execution**.\n- All examples are provided for **educational purposes** to practice computer vision techniques.\n\n---\n\n## Course Source\n\nThese projects were developed as part of the  \n**[Udemy - Computer Vision Masterclass](https://www.udemy.com/course/computer-vision-masterclass/)**,  \nwhich covers both foundational and advanced topics in computer vision.\n\n---\n\n## License\n\nThis repository is intended **solely for educational use**.  \nAll scripts and notebooks are based on course exercises and are meant to help students explore  \nimage processing, machine learning, and computer vision concepts.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferenisci%2Fcomputer-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferenisci%2Fcomputer-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferenisci%2Fcomputer-vision/lists"}