{"id":25229199,"url":"https://github.com/alirezasaharkhiz9/computer-vision","last_synced_at":"2026-03-10T06:03:26.484Z","repository":{"id":258510195,"uuid":"860392023","full_name":"alirezasaharkhiz9/Computer-Vision","owner":"alirezasaharkhiz9","description":"This is my undergraduate project at Ferdowsi University of Mashhad, focusing comprehensively on computer vision.","archived":false,"fork":false,"pushed_at":"2025-03-28T00:17:26.000Z","size":113999,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-05T14:12:59.196Z","etag":null,"topics":["cnn","computer-vision","deep-learning","image-classification","image-generation","image-manipulation","image-segmentation","keras","object-detection","python","pytorch-lightning"],"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/alirezasaharkhiz9.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-09-20T10:54:05.000Z","updated_at":"2025-03-28T00:17:29.000Z","dependencies_parsed_at":"2025-02-04T12:40:32.537Z","dependency_job_id":null,"html_url":"https://github.com/alirezasaharkhiz9/Computer-Vision","commit_stats":null,"previous_names":["alirezasaharkhiz9/undergraduate-project-computer-vision","alirezasaharkhiz9/computer-vision"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alirezasaharkhiz9/Computer-Vision","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alirezasaharkhiz9%2FComputer-Vision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alirezasaharkhiz9%2FComputer-Vision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alirezasaharkhiz9%2FComputer-Vision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alirezasaharkhiz9%2FComputer-Vision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alirezasaharkhiz9","download_url":"https://codeload.github.com/alirezasaharkhiz9/Computer-Vision/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alirezasaharkhiz9%2FComputer-Vision/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30326878,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"last_error":"SSL_read: 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":["cnn","computer-vision","deep-learning","image-classification","image-generation","image-manipulation","image-segmentation","keras","object-detection","python","pytorch-lightning"],"created_at":"2025-02-11T10:47:28.135Z","updated_at":"2026-03-10T06:03:26.455Z","avatar_url":"https://github.com/alirezasaharkhiz9.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Undergraduate Project - Computer Vision\r\n\r\n### Overview\r\n\r\nThis undergraduate project focuses on exploring and developing advanced techniques in **computer vision**, structured into two main sections: **Classical Computer Vision** and **Modern Deep Learning-based Computer Vision**. The project begins by covering the fundamentals of image processing, video analysis, and classical object detection algorithms. In the second part, using cutting-edge tools like PyTorch, **convolutional neural networks** (CNN) will be implemented. The project also delves into modern techniques such as transfer learning, **pre-trained models**, and the emerging **Vision Transformers**. Furthermore, efficient object detection with YOLO and facial recognition using deep learning will be thoroughly explored.\r\n\r\n### Table of Contents\r\n\r\n1.  [Project Structure](#project-structure)\r\n2.  [Modern CV vs Classical CV](#modern-cv-vs-classical-cv)\r\n3.  [Roadmap](#roadmap)\r\n4.  [Requirements](#requirements)\r\n5.  [References](#references)\r\n\r\n### Project Structure\r\n\r\nThe project will be organized into the following sections:\r\n#### 1. [ **Classical Computer Vision** ](https://github.com/alirezasaharkhiz9/undergraduate-project-computer-vision/tree/main/Classical%20Computer%20Vision)\r\n- [***Image Processing***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Classical%20Computer%20Vision/Image%20Processing)\r\n  \r\n  - [Image processing](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Classical%20Computer%20Vision/Image%20Processing/ImageProcessing.ipynb)\r\n- [***Video Processing***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Classical%20Computer%20Vision/Video%20Processing)\r\n  - [Working with Video](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Classical%20Computer%20Vision/Video%20Processing/WorkingWithVideo.ipynb)\r\n- [***Object Detection***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Classical%20Computer%20Vision/Object%20Detection)\r\n  - [Object Detection](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Classical%20Computer%20Vision/Object%20Detection/ObjectDetection.ipynb)\r\n- [***Face Detection***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Classical%20Computer%20Vision/Face%20Detection)\r\n  - [Face Detection](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Classical%20Computer%20Vision/Face%20Detection/FaceDetection.ipynb)\r\n- [***OCR***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Classical%20Computer%20Vision/OCR)\r\n  - [Text Detection](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Classical%20Computer%20Vision/OCR/TextDetection.ipynb)\r\n  \r\n#### 2. [ **Modern Computer Vision - Deep Learning** ](https://github.com/alirezasaharkhiz9/undergraduate-project-computer-vision/tree/main/Modern%20Computer%20Vision)\r\n- [***Image Classification***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Image%20Classification)\r\n  \r\n  - [Cnn Model theory](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Classification/CnnModelTheory.ipynb)\r\n\r\n  - [Cnn With Keras (Normal, Pneumonia and Tuberculosis Lungs)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Classification/CnnWithKeras.ipynb)\r\n  - [CNN With Pytorch Lightning (Fundus Glaucoma Detection)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Classification/CnnWithPytorchLightning.ipynb)\r\n  - [Residual Network With Pytorch Lightning (Normal, Pneumonia and Tuberculosis Lungs)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Classification/ResidualNetworkWithPytorchLightning.ipynb)\r\n\r\n- [***Image Manipulation***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Image%20Manipulation)\r\n\r\n  - [AutoEncoder With Keras (The main objective of creating this dataset is to create autoencoder network that can colorized grayscale landscape images)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Manipulation/AutoEncoderWithKeras.ipynb)\r\n\r\n- [***Image Generation***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Image%20Generation)\r\n\r\n  - [DCGAN With Keras (GAN using the MNIST dataset)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Generation/DCGANWithKeras.ipynb)\r\n\r\n- [***Image Segmentation***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Image%20Segmentation)\r\n\r\n  - [Lungs Segmentation Using U-Net architecture](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Segmentation/LungsSegmentationUsingU_Net.ipynb)\r\n\r\n  - [Tumor Segmentation Using Yolo v11](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Image%20Segmentation/TumorSegmentationUsingYolo.ipynb)\r\n\r\n- [***Object Detection***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Object%20Detection)\r\n\r\n  - [Object Detection Using YOLO v5 (road-detection)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Detection/ObjectDetectionUsingYOLOv5.ipynb)\r\n\r\n  - [Object Detection Using YOLO v8 (Bone Fracture Detection)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Detection/ObjectDetectionUsingYOLOv8.ipynb)\r\n  - [Object Detection Using YOLO v11 (Tumor Detection)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Detection/TumorDetectionUsingYolov11.ipynb)\r\n\r\n- [***Object Tracking***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Object%20Tracking)\r\n\r\n  - [Object Tracking With YOLO v11](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Tracking/ObjectTrackingWithYolo.ipynb) - [Download Result Video](https://raw.githubusercontent.com/alirezasaharkhiz9/undergraduate-project-computer-vision/main/Modern%20Computer%20Vision/Object%20Tracking/ObjectTrackingWithYolo.avi)\r\n\r\n  - [Tracking and Counting With YOLO v11](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Tracking/TrackingAndCounting.ipynb) - [Download Result Video](https://raw.githubusercontent.com/alirezasaharkhiz9/undergraduate-project-computer-vision/main/Modern%20Computer%20Vision/Object%20Tracking/TrackingAndCounting.mp4)\r\n  - [Speed Estimation With YOLO v11](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Tracking/SpeedEstimation.ipynb) - [Download Result Video](https://raw.githubusercontent.com/alirezasaharkhiz9/undergraduate-project-computer-vision/main/Modern%20Computer%20Vision/Object%20Tracking/SpeedEstimation.avi)\r\n  - [Heat Maps With Yolo v11](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Object%20Tracking/HeatMapsWithYolo.ipynb) - [Download Result Video](https://raw.githubusercontent.com/alirezasaharkhiz9/undergraduate-project-computer-vision/main/Modern%20Computer%20Vision/Object%20Tracking/heatmap_output.avi\r\n)\r\n- [***Pose Estimation***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Pose%20Estimation)\r\n\r\n  - [Pose Estimation With Yolo v11 (human pose estimation)](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Pose%20Estimation/PoseEstimationWithYolo.ipynb)\r\n- [***Face Recognition***](https://github.com/alirezasaharkhiz9/Computer-Vision/tree/main/Modern%20Computer%20Vision/Face%20Recognition)\r\n\r\n  - [Facial Recognition With Deep Face](https://github.com/alirezasaharkhiz9/Computer-Vision/blob/main/Modern%20Computer%20Vision/Face%20Recognition/FacialRecognitionWithDeepFace.ipynb)\r\n\r\n### Modern CV vs Classical CV\r\n\r\n| **Topic**                          | **Classical Computer Vision**                                                | **Modern Computer Vision (Using Deep Learning)**                                                                |\r\n|-----------------|-----------------------|---------------------------------|\r\n| **Definition and Core Principles** | Based on hand-crafted algorithms and engineered features.                    | Based on deep neural networks and learning from large datasets.                                                 |\r\n| **Feature Extraction Method**      | Features are extracted manually using algorithms like SIFT, SURF, and HOG.   | Features are automatically learned by convolutional neural networks (CNNs).                                     |\r\n| **Accuracy**                       | Accuracy is usually limited and optimization for complex problems is harder. | Generally achieves much higher accuracy, especially in complex tasks like image recognition and classification. |\r\n| **Amount of Data Required**        | Requires less data, but models are usually less optimized.                   | Requires large amounts of data for effective learning.                                                          |\r\n| **Computational Complexity**       | Generally lighter and simpler in computation.                                | Heavier in computation and requires powerful hardware (GPUs).                                                   |\r\n\r\n\r\n### Roadmap\r\n\r\nThe project will progress through the following phases:\r\n1. **Phase 1**: Implementing Classical Computer Vision Techniques\r\n2. **Phase 2**: Building and Training Deep Learning Models with PyTorch and tensorflow, keras\r\n\r\n\r\n### Requirements\r\n\r\nTo run the project, you'll need:\r\n\r\n-   Python 3.x\r\n-   tools: Jupyter Lab, Colab, lightning studio\r\n-   Required libraries listed in requirements.txt.\r\n\r\nYou can install the dependencies using:\r\n\r\n``` bash\r\npip install -r requirements.txt\r\n```\r\n\r\n### References:\r\n\r\n- Ayyadevara, V. K., \u0026 Reddy, Y. (2024). Modern Computer Vision with PyTorch - Second Edition: A practical roadmap from deep learning fundamentals to advanced applications and Generative AI (2nd ed.). Packt Publishing.\r\n- Elgendy, M. (2020). Deep Learning for Vision Systems (1st ed.). Manning.\r\n- Ratan, R. D. (2024). Modern Computer Vision GPT, PyTorch, Keras, OpenCV4 in 2024! Next-Gen Computer Vision: YOLOv8, DINO-GPT4V, OpenCV4, Face Recognition, GenerativeAI, Diffusion Models \u0026 Transformers [Online course]. Udemy.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falirezasaharkhiz9%2Fcomputer-vision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falirezasaharkhiz9%2Fcomputer-vision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falirezasaharkhiz9%2Fcomputer-vision/lists"}