Probabilistic contextual models for object class recognition in uncontrived images.

Hasanat, Mozaherul Hoque Abul (2011) Probabilistic contextual models for object class recognition in uncontrived images. PhD thesis, Universiti Sains Malaysia.

Preview

PDF Download (7MB) | Preview

Abstract

Konteks merupakan suatu elemen penting dalam mendapatkan penjelasan yang bererti untuk sesuatu imej bagi kedua-dua sistem visual biologi dan buatan. Tesis ini mencadangkan permodelan hubungan konteks di antara objek dunia nyata di dalam imej yang tidak dibuat-buat bagi meningkatkan prestasi pengecaman kelas objek. Dua model kebarangkalian dicadangkan iaitu Semantic Context Model (SCM) dan Spatial Context Model (SpCM) - untuk memodelkan hubungan kontekstual semantik dan ruangan peringkat tinggi. Context is a vital element in deriving meaningful explanation of an image for both biological, as well as, artificial vision systems. This thesis proposes to model contextual relation among real-world objects in uncontrived images in order to improve object class recognition performance. Two probabilistic models are proposed – Semantic Context Model (SCM), and Spatial Context Model (SpCM) to model high-level semantic and spatial contextual relations respectively.

Item Type:	Thesis (PhD)
Subjects:	R Medicine > RM Therapeutics. Pharmacology > RM300-666 Drugs and their actions
Divisions:	Pusat Penyelidikan Dadah dan Ubat-ubatan (Centre for Drug Research) > Thesis
Depositing User:	Mr Erwan Roslan
Date Deposited:	26 Nov 2018 06:51
Last Modified:	26 Nov 2018 06:51
URI:	http://eprints.usm.my/id/eprint/43011

Actions (login required)

View Item