FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W579432862> ?p ?o ?g. }

• W579432862 abstract "This thesis is dedicated to the active research topic of generic Visual Object Categorization(VOC), which can be widely used in many applications such as videoindexation and retrieval, video monitoring, security access control, automobile drivingsupport etc. Due to many realistic difficulties, it is still considered to be one ofthe most challenging problems in computer vision and pattern recognition. In thiscontext, we have proposed in this thesis our contributions, especially concerning thetwo main components of the methods addressing VOC problems, namely featureselection and image representation.Firstly, an Embedded Sequential Forward feature Selection algorithm (ESFS)has been proposed for VOC. Its aim is to select the most discriminant forobtaining a good performance for the categorization. It is mainly based on thecommonly used sub-optimal search method Sequential Forward Selection (SFS),which relies on the simple principle to add incrementally most relevant features.However, ESFS not only adds incrementally most relevant in each stepbut also merges them in an embedded way thanks to the concept of combinedmass functions from the evidence theory which also offers the benefit of obtaining acomputational cost much lower than the one of original SFS.Secondly, we have proposed novel image representations to model the visualcontent of an image, namely Polynomial Modeling and Statistical Measures basedImage Representation, called PMIR and SMIR respectively. They allow to overcomethe main drawback of the popular bag of features method which is the difficultyto fix the optimal size of the visual vocabulary. They have been tested along withour proposed region based and SIFT. Two different fusion strategies, earlyand late, have also been considered to merge information from different channelsrepresented by the different types of features.Thirdly, we have proposed two approaches for VOC relying on sparse representation,including a reconstructive method (R_SROC) as well as a reconstructiveand discriminative one (RD_SROC). Indeed, sparse representation model has beenoriginally used in signal processing as a powerful tool for acquiring, representingand compressing the high-dimensional signals. Thus, we have proposed to adaptthese interesting principles to the VOC problem. R_SROC relies on the intuitiveassumption that an image can be represented by a linear combination of trainingimages from the same category. Therefore, the sparse representations of images arefirst computed through solving the l1 norm minimization problem and then usedas new feature vectors for images to be classified by traditional classifiers such asSVM. To improve the discrimination ability of the sparse representation to betterfit the classification problem, we have also proposed RD_SROC which includes adiscrimination term, such as Fisher discrimination measure or the output of a SVMclassifier, to the standard sparse representation objective function in order to learna reconstructive and discriminative dictionary. Moreover, we have also proposedChapter 0. Abstractto combine the reconstructive and discriminative dictionary and the adapted purereconstructive dictionary for a given category so that the discrimination power canfurther be increased.The efficiency of all the methods proposed in this thesis has been evaluated onpopular image datasets including SIMPLIcity, Caltech101 and Pascal2007." @default.
• W579432862 created "2016-06-24" @default.
• W579432862 creator A5050865694 @default.
• W579432862 date "2010-12-14" @default.
• W579432862 modified "2023-09-24" @default.
• W579432862 title "Contributions to generic visual object categorization" @default.
• W579432862 cites W116877356 @default.
• W579432862 cites W1484228140 @default.
• W579432862 cites W1485625483 @default.
• W579432862 cites W1491105865 @default.
• W579432862 cites W1500053687 @default.
• W579432862 cites W1500595752 @default.
• W579432862 cites W1502050276 @default.
• W579432862 cites W1512921847 @default.
• W579432862 cites W1521568703 @default.
• W579432862 cites W1533452257 @default.
• W579432862 cites W1550206324 @default.
• W579432862 cites W1563088657 @default.
• W579432862 cites W1566497823 @default.
• W579432862 cites W1592774159 @default.
• W579432862 cites W1594031697 @default.
• W579432862 cites W1597283066 @default.
• W579432862 cites W1600301529 @default.
• W579432862 cites W1603829220 @default.
• W579432862 cites W1608462934 @default.
• W579432862 cites W1625255723 @default.
• W579432862 cites W1634005169 @default.
• W579432862 cites W1663973292 @default.
• W579432862 cites W1833977909 @default.
• W579432862 cites W1917380066 @default.
• W579432862 cites W193425649 @default.
• W579432862 cites W1949116567 @default.
• W579432862 cites W1956559956 @default.
• W579432862 cites W1969294188 @default.
• W579432862 cites W1976645892 @default.
• W579432862 cites W1976709621 @default.
• W579432862 cites W1980911747 @default.
• W579432862 cites W1986931325 @default.
• W579432862 cites W1988790447 @default.
• W579432862 cites W1989085630 @default.
• W579432862 cites W1991977971 @default.
• W579432862 cites W2001619934 @default.
• W579432862 cites W2006500012 @default.
• W579432862 cites W2008353316 @default.
• W579432862 cites W2009052723 @default.
• W579432862 cites W2014915963 @default.
• W579432862 cites W2017337590 @default.
• W579432862 cites W2017537431 @default.
• W579432862 cites W2021121949 @default.
• W579432862 cites W2030536784 @default.
• W579432862 cites W2031823405 @default.
• W579432862 cites W2038567802 @default.
• W579432862 cites W2050834445 @default.
• W579432862 cites W2056758595 @default.
• W579432862 cites W2059412355 @default.
• W579432862 cites W2066380143 @default.
• W579432862 cites W2069929276 @default.
• W579432862 cites W2069959554 @default.
• W579432862 cites W2072026441 @default.
• W579432862 cites W2082855665 @default.
• W579432862 cites W2085207288 @default.
• W579432862 cites W2087327261 @default.
• W579432862 cites W2090700914 @default.
• W579432862 cites W2091715611 @default.
• W579432862 cites W2093191240 @default.
• W579432862 cites W2093641078 @default.
• W579432862 cites W2097018403 @default.
• W579432862 cites W2098152234 @default.
• W579432862 cites W2099641086 @default.
• W579432862 cites W2102024628 @default.
• W579432862 cites W2102129292 @default.
• W579432862 cites W2102831150 @default.
• W579432862 cites W2104170135 @default.
• W579432862 cites W2104862701 @default.
• W579432862 cites W2104978738 @default.
• W579432862 cites W2105464873 @default.
• W579432862 cites W2105568170 @default.
• W579432862 cites W2107034620 @default.
• W579432862 cites W2107473989 @default.
• W579432862 cites W2107743791 @default.
• W579432862 cites W2107835995 @default.
• W579432862 cites W2109200236 @default.
• W579432862 cites W2109449402 @default.
• W579432862 cites W2109464092 @default.
• W579432862 cites W2109868644 @default.
• W579432862 cites W2111219934 @default.
• W579432862 cites W2111308925 @default.
• W579432862 cites W2112020727 @default.
• W579432862 cites W2112072024 @default.
• W579432862 cites W2115429828 @default.
• W579432862 cites W2115706991 @default.
• W579432862 cites W2116948717 @default.
• W579432862 cites W2118286367 @default.
• W579432862 cites W2119387367 @default.
• W579432862 cites W2119479037 @default.
• W579432862 cites W2119747362 @default.
• W579432862 cites W2119821739 @default.
• W579432862 cites W2122315118 @default.
• W579432862 cites W2122922389 @default.
• W579432862 cites W2124628561 @default.

• next