Matches in SemOpenAlex for { <https://semopenalex.org/work/W32654608> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W32654608 abstract "Object recognition is of fundamental importance in computer vision. In a few years, pedestrian detection, car detection, and more generally scene recognition will likely be reliable enough to allow fully-automated car navigation, and the human driver will be relegated to the back seat to sip his coffee.In this thesis we are interested in recognizing individual objects and categories. In order to reduce the volume of information one has to process, images are characterized by sets of features. These features, also called interest points, are targeted at image locations with high local information content. Various systems for detecting interest points and for describing the local image appearance near these points, have been proposed in the last two decades. We investigate which combinations from this plethora of detectors and descriptors, are most suited for object recognition tasks.On to the problem of object recognition, we are first interested in recognizing individual objects. In a few years, one can imagine that customers in shops, will take with their cell phone a picture of a product that looks interesting, send it to a remote server with a huge database of individual objects, and get back information about that specific product. We propose a system for individual object recognition, inspired from previous work on coarse-to-fine recognition. All steps of the recognition process are translated into principled probabilistic terms, which allows us to outperform a state-of-the-art commercial system for individual recognition.Regarding categories, faces are probably the category that has received the most attention in computer vision literature. Here we propose a system to recognize images of the same individual in large databases of images. This can be of high interest when looking for images of a given person over the internet. Our method's advantage is that it works on real-world images, as opposed to the face databases from the literature, collected in laboratories with controlled lighting, pose and background conditions.Finally, we are interested in recognition of object categories in general. Using support vector machines for the classification task, we propose a features-based kernel that improves recognition performance on object categories." @default.
- W32654608 created "2016-06-24" @default.
- W32654608 creator A5059608264 @default.
- W32654608 date "2008-01-01" @default.
- W32654608 modified "2023-09-27" @default.
- W32654608 title "Probabilistic, features-based object recognition" @default.
- W32654608 doi "https://doi.org/10.7907/ygyx-xx55." @default.
- W32654608 hasPublicationYear "2008" @default.
- W32654608 type Work @default.
- W32654608 sameAs 32654608 @default.
- W32654608 citedByCount "0" @default.
- W32654608 crossrefType "dissertation" @default.
- W32654608 hasAuthorship W32654608A5059608264 @default.
- W32654608 hasConcept C111919701 @default.
- W32654608 hasConcept C132900626 @default.
- W32654608 hasConcept C14551309 @default.
- W32654608 hasConcept C153180895 @default.
- W32654608 hasConcept C154945302 @default.
- W32654608 hasConcept C159437735 @default.
- W32654608 hasConcept C207347870 @default.
- W32654608 hasConcept C2524010 @default.
- W32654608 hasConcept C2776151529 @default.
- W32654608 hasConcept C2781238097 @default.
- W32654608 hasConcept C31972630 @default.
- W32654608 hasConcept C33923547 @default.
- W32654608 hasConcept C41008148 @default.
- W32654608 hasConcept C49937458 @default.
- W32654608 hasConcept C64876066 @default.
- W32654608 hasConcept C90673727 @default.
- W32654608 hasConcept C98045186 @default.
- W32654608 hasConceptScore W32654608C111919701 @default.
- W32654608 hasConceptScore W32654608C132900626 @default.
- W32654608 hasConceptScore W32654608C14551309 @default.
- W32654608 hasConceptScore W32654608C153180895 @default.
- W32654608 hasConceptScore W32654608C154945302 @default.
- W32654608 hasConceptScore W32654608C159437735 @default.
- W32654608 hasConceptScore W32654608C207347870 @default.
- W32654608 hasConceptScore W32654608C2524010 @default.
- W32654608 hasConceptScore W32654608C2776151529 @default.
- W32654608 hasConceptScore W32654608C2781238097 @default.
- W32654608 hasConceptScore W32654608C31972630 @default.
- W32654608 hasConceptScore W32654608C33923547 @default.
- W32654608 hasConceptScore W32654608C41008148 @default.
- W32654608 hasConceptScore W32654608C49937458 @default.
- W32654608 hasConceptScore W32654608C64876066 @default.
- W32654608 hasConceptScore W32654608C90673727 @default.
- W32654608 hasConceptScore W32654608C98045186 @default.
- W32654608 hasLocation W326546081 @default.
- W32654608 hasOpenAccess W32654608 @default.
- W32654608 hasPrimaryLocation W326546081 @default.
- W32654608 hasRelatedWork W108856365 @default.
- W32654608 hasRelatedWork W120285558 @default.
- W32654608 hasRelatedWork W1585910451 @default.
- W32654608 hasRelatedWork W1976349993 @default.
- W32654608 hasRelatedWork W2040002737 @default.
- W32654608 hasRelatedWork W2166853275 @default.
- W32654608 hasRelatedWork W2277790293 @default.
- W32654608 hasRelatedWork W2460559109 @default.
- W32654608 hasRelatedWork W2595067051 @default.
- W32654608 hasRelatedWork W2605147985 @default.
- W32654608 hasRelatedWork W2748816939 @default.
- W32654608 hasRelatedWork W2912559722 @default.
- W32654608 hasRelatedWork W29294420 @default.
- W32654608 hasRelatedWork W2967870022 @default.
- W32654608 hasRelatedWork W3006949615 @default.
- W32654608 hasRelatedWork W3171618005 @default.
- W32654608 hasRelatedWork W84015304 @default.
- W32654608 hasRelatedWork W1546274004 @default.
- W32654608 hasRelatedWork W2122372491 @default.
- W32654608 hasRelatedWork W2591243219 @default.
- W32654608 isParatext "false" @default.
- W32654608 isRetracted "false" @default.
- W32654608 magId "32654608" @default.
- W32654608 workType "dissertation" @default.