{"id":24433915,"url":"https://github.com/hako/dissertation","last_synced_at":"2025-04-12T15:08:45.520Z","repository":{"id":50627991,"uuid":"113603689","full_name":"hako/dissertation","owner":"hako","description":":mortar_board: :scroll: This repository holds my final year and dissertation project during my time at the University of Lincoln titled 'Deep Learning for Emotion Recognition in Cartoons'.","archived":false,"fork":false,"pushed_at":"2021-07-27T23:00:02.000Z","size":47695,"stargazers_count":25,"open_issues_count":0,"forks_count":19,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-12T15:08:36.700Z","etag":null,"topics":["cartoons","convolutional-neural-networks","deep-learning","deep-neural-networks","dissertation","emotion","emotion-recognition","haar-features","machine-learning","python","tex"],"latest_commit_sha":null,"homepage":"https://hako.github.io/dissertation","language":"TeX","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hako.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2017-12-08T18:11:13.000Z","updated_at":"2024-05-03T18:56:12.000Z","dependencies_parsed_at":"2022-09-22T20:50:29.380Z","dependency_job_id":null,"html_url":"https://github.com/hako/dissertation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hako%2Fdissertation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hako%2Fdissertation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hako%2Fdissertation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hako%2Fdissertation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hako","download_url":"https://codeload.github.com/hako/dissertation/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248586235,"owners_count":21128997,"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":["cartoons","convolutional-neural-networks","deep-learning","deep-neural-networks","dissertation","emotion","emotion-recognition","haar-features","machine-learning","python","tex"],"created_at":"2025-01-20T16:51:08.699Z","updated_at":"2025-04-12T15:08:45.499Z","avatar_url":"https://github.com/hako.png","language":"TeX","funding_links":[],"categories":[],"sub_categories":[],"readme":"# dissertation\n\n![](https://github.com/hako/dissertation/raw/master/media/header.png)\n\nThis repository holds my final year project during my time at the [University of Lincoln](http://lincoln.ac.uk) titled *'Deep Learning for Emotion Recognition in Cartoons'*.\n\n[PDF](https://github.com/hako/dissertation/raw/master/dissertation.pdf) [HTML](https://hako.github.io/dissertation/)\n\n#### Abstract\n\n*Emotion Recognition is a field that computers are getting very good at identifying; whether it's through images, video or audio. Emotion Recognition has shown promising improvements when combined with classifiers and Deep Neural Networks showing a validation rate as high as 59% and a recognition rate of 56%.*\n\n*The focus of this dissertation will be on facial based emotion recognition. This consists of detecting facial expressions in images and videos. While the majority of research uses human faces in an attempt to recognise basic emotions, there has been little research on whether the same deep learning techniques can be applied to faces in cartoons.*\n\n*The system implemented in this paper, aims to classify at most three emotions (happiness, anger and surprise) of the 6 basic emotions proposed by psychologists Ekman and Friesen, with an accuracy of \u003cb\u003e80%\u003c/b\u003e for the 3 emotions. Showing promise of applications of deep learning and cartoons. This project is an attempt to examine if emotions in cartoons can be detected in the same way that human faces can.*\n\n#### Dataset\n\nThe dataset used in this dissertation is a collection of **4,800** *Tom \u0026 Jerry* face images. \n\n[Tom \u0026 Jerry Image Dataset (15MB)](http://hakob.yt/tajidataset)\n\n#### Requirements\n\n+ [Python 2.7](https://python.org)\n+ [OpenCV 3.2+](http://opencv.org/)\n+ [TensorFlow 1.1+ CPU/GPU (GPU Recommended)](https://tensorflow.org)\n+ [Jupyter Notebook (Optional)](http://jupyter.org)\n+ Linux: `sudo apt-get install python-dev python-tk`\n\n#### Install\n\n```\ngit clone https://github.com/hako/dissertation\ncd dissertation\nsudo pip install -r requirements.txt\n```\n\n#### Usage\n\nDownload the above dataset, the folder must be named `datasets`. Below you can get started with the tools below.\n\n##### Training / Classification / Visualisation\n\nIf you just want to train/classify or visualise the output of the network, use this tool:\n\n```\ntraining: (and show summary or results)\nusage: train.py -t [-v|-s]\n\nclassification:\nusage: train.py -c image.jpg\n\nvisualisation:\nusage: train.py -V\n```\n\n##### Segmentation\n\nIncluded in this repo are two [Haar cascade](https://en.m.wikipedia.org/wiki/Viola%E2%80%93Jones_object_detection_framework) files trained to detect *Tom \u0026 Jerry* faces. Note that if you choose this tool, you have to obtain the *Tom \u0026 Jerry* videos yourself.\n\nIf you want to segment the *Tom \u0026 Jerry* videos into images, use this tool:\n\n```\npython segmentation.py\n```\n\n##### Notebook\n\nIf you're the type that likes interactivity and experimentation, both the `segmentation.py` and the `train.py` files have their own Jupyter Notebooks in the `notebooks/` folder. If you're using this, make sure the video and image datasets are in the folder.\n\n#### Special Thanks\nI would like to thank the following:\n\n+ Professor Stefanos Kollias\n+ My family and friends\n+ The University of Lincoln Library\n\n#### Citation\nHill, J.W., (2017). *Deep Learning for Emotion Recognition in Cartoons*\n\n##### bibtex\n\n```bibtex\n@mastersthesis{hill17,\n  author            = {John Wesley Hill},\n  title             = {Deep Learning for Emotion Recognition in Cartoons},\n  school            = {University of Lincoln},\n  year              = {2017},\n  document_type     = {Bachelor's Thesis},\n  type              = {Bachelor Thesis},\n}\n```\n\n#### Notes\n\nExperiment Environment:\n\nOS: Ubuntu GNU/Linux 16.04 LTS (x64)\n\nGPU: Nvidia GeForce GTX 970\n\n_Tom \u0026 Jerry_ © Warner Bros. Entertainment, Inc\n\n#### License\nBSD\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhako%2Fdissertation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhako%2Fdissertation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhako%2Fdissertation/lists"}