{"id":13609144,"url":"https://github.com/matthewearl/deep-anpr","last_synced_at":"2025-05-15T21:06:33.587Z","repository":{"id":44448997,"uuid":"57903947","full_name":"matthewearl/deep-anpr","owner":"matthewearl","description":"Using neural networks to build an automatic number plate recognition system","archived":false,"fork":false,"pushed_at":"2019-11-14T22:40:30.000Z","size":42,"stargazers_count":1843,"open_issues_count":99,"forks_count":699,"subscribers_count":119,"default_branch":"master","last_synced_at":"2024-10-29T17:39:50.989Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/matthewearl.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}},"created_at":"2016-05-02T16:29:33.000Z","updated_at":"2024-10-03T12:48:06.000Z","dependencies_parsed_at":"2022-08-29T14:20:27.074Z","dependency_job_id":null,"html_url":"https://github.com/matthewearl/deep-anpr","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/matthewearl%2Fdeep-anpr","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthewearl%2Fdeep-anpr/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthewearl%2Fdeep-anpr/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matthewearl%2Fdeep-anpr/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/matthewearl","download_url":"https://codeload.github.com/matthewearl/deep-anpr/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254422761,"owners_count":22068678,"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":[],"created_at":"2024-08-01T19:01:32.775Z","updated_at":"2025-05-15T21:06:33.565Z","avatar_url":"https://github.com/matthewearl.png","language":"Python","funding_links":[],"categories":["Python","Python (1887)"],"sub_categories":[],"readme":"# Deep ANPR\n\nUsing neural networks to build an automatic number plate recognition system.\nSee [this blog post](http://matthewearl.github.io/2016/05/06/cnn-anpr/) for an\nexplanation.\n\n**Note: This is an experimental project and is incomplete in a number of ways,\nif you're looking for a practical number plate recognition system this project\nis not for you.** If however you've read the above blog post and wish to tinker\nwith the code, read on.  If you're really keen you can tackle some of the\nenhancements on the Issues page to help make this project more practical.\nPlease comment on the relevant issue if you plan on making an enhancement and\nwe can talk through the potential solution.\n\nUsage is as follows:\n\n1. `./extractbgs.py SUN397.tar.gz`: Extract ~3GB of background images from the [SUN database](http://groups.csail.mit.edu/vision/SUN/)\n   into `bgs/`. (`bgs/` must not already exist.) The tar file (36GB) can be [downloaded here](http://vision.princeton.edu/projects/2010/SUN/SUN397.tar.gz).\n   This step may take a while as it will extract 108,634 images.\n\n2. `./gen.py 1000`: Generate 1000 test set images in `test/`. (`test/` must not\n    already exist.) This step requires `UKNumberPlate.ttf` to be in the\n    `fonts/` directory, which can be\n    [downloaded here](http://www.dafont.com/uk-number-plate.font).\n\n3. `./train.py`: Train the model. A GPU is recommended for this step. It will\n   take around 100,000 batches to converge. When you're satisfied that the\n   network has learned enough press `Ctrl+C` and the process will write the\n   weights to `weights.npz` and return.\n\n4. `./detect.py in.jpg weights.npz out.jpg`: Detect number plates in an image.\n\nThe project has the following dependencies:\n\n* [TensorFlow](https://tensorflow.org)\n* OpenCV\n* NumPy\n\nDifferent typefaces can be put in `fonts/` in order to match different type\nfaces.  With a large enough variety the network will learn to generalize and\nwill match as yet unseen typefaces. See\n[#1](https://github.com/matthewearl/deep-anpr/issues/1) for more information.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatthewearl%2Fdeep-anpr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatthewearl%2Fdeep-anpr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatthewearl%2Fdeep-anpr/lists"}