{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/scene-recognition-by-combining-local-and","title":"Scene Recognition by Combining Local and Global Image Descriptors","arxiv_id":"1702.06850","date":"2017-02-21","proceeding":null,"authors":["Jobin Wilson","Muhammad Arif"],"abstract":"Object recognition is an important problem in computer vision, having diverse\napplications. In this work, we construct an end-to-end scene recognition\npipeline consisting of feature extraction, encoding, pooling and\nclassification. Our approach simultaneously utilize global feature descriptors\nas well as local feature descriptors from images, to form a hybrid feature\ndescriptor corresponding to each image. We utilize DAISY features associated\nwith key points within images as our local feature descriptor and histogram of\noriented gradients (HOG) corresponding to an entire image as a global\ndescriptor. We make use of a bag-of-visual-words encoding and apply Mini- Batch\nK-Means algorithm to reduce the complexity of our feature encoding scheme. A\n2-level pooling procedure is used to combine DAISY and HOG features\ncorresponding to each image. Finally, we experiment with a multi-class SVM\nclassifier with several kernels, in a cross-validation setting, and tabulate\nour results on the fifteen scene categories dataset. The average accuracy of\nour model was 76.4% in the case of a 40%-60% random split of images into\ntraining and testing datasets respectively. The primary objective of this work\nis to clearly outline the practical implementation of a basic\nscrene-recognition pipeline having a reasonable accuracy, in python, using\nopen-source libraries. A full implementation of the proposed model is available\nin our github repository.","url_abs":"http://arxiv.org/abs/1702.06850v1","url_pdf":"http://arxiv.org/pdf/1702.06850v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"scene-recognition-by-combining-local-and","repo_url":"https://github.com/flytxtds/scene-recognition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"scene-recognition","task_name":"Scene Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}