Variational Exemplar-Based Image Colorization

Abstract:-
Interest point detection is an important research area in the field of image
processing and computer vision. In particular, image retrieval and object
categorization heavily rely on interest. Point detection from which local image
descriptors are computed for image matching. The use of color may therefore provide
selective search reducing the total number of interest points used for image matching.
This paper proposes color interest points for sparse image representation. A large-scale
eperiment, it is shown that the proposed color interest point detector has higher
repeatability than a luminance-based one. !urthermore, in the contet of image
retrieval, a reduced and predictable number of color features show an increase in
performance compared to state-of-the-art interest points. The contributions of this
paper are twofold. !irst, we introduce a variational formulation."odeling the color
selection problem under spatial constraints and propose a minimization scheme, which
computes a local "inima of the defined non conve energy. #econd, we combine
GLOBALSOFT TECHNOLOGIES
IEEE PROJECTS & SOFTWARE DEVELOPMENTS
IEEE FINAL YEAR PROJECTS|IEEE ENGINEERING PROJECTS|IEEE STUDENTS PROJECTS|IEEE
BULK PROJECTS|BE/BTECH/ME/MTECH/MS/MCA PROJECTS|CSE/IT/ECE/EEE PROJECTS
CELL: +91 9!9" #9$"% +91 99&&' #"(% +91 9!9" "(9$% +91 9($1! !$!$1
V)*)+: ,,,-.)/012304546738+*-649 M0)1 +6:)333.)/01*3:546738+*;9:0)1-86:
GLOBALSOFT TECHNOLOGIES
IEEE PROJECTS & SOFTWARE DEVELOPMENTS
IEEE FINAL YEAR PROJECTS|IEEE ENGINEERING PROJECTS|IEEE STUDENTS PROJECTS|IEEE
BULK PROJECTS|BE/BTECH/ME/MTECH/MS/MCA PROJECTS|CSE/IT/ECE/EEE PROJECTS
CELL: +91 9!9" #9$"% +91 99&&' #"(% +91 9!9" "(9$% +91 9($1! !$!$1
V)*)+: ,,,-.)/012304546738+*-649 M0)1 +6:)333.)/01*3:546738+*;9:0)1-86:
different patch-based features and distances in order to construct a consistent set of
possible color candidates. A first category of colorization algorithms re$uires
a huge amount of user intervention to manually add initial colors to the grayscale
image. The colorization process is then performed by propagating the input color data
to the whole image. !irst, several color candidates are computed using different
features and associated metrics. The final color is then obtained by solving a
variational model which allows the automatic selection of the best candidates
while adding some regularization in the solution.
Existing System:-
The candidate selection and color regularization problems are
simultaneously solved through a variational energy
minimization.
Natural images contain diferent types of complex structures,
redundancies and textures.
The problem of selecting the best color to transfer among the
set of possible colors is solved, for each pixel independently,
using a dimensional reduction.
We focus on the image colorization problem which involves
consistent and spatially coherent image results.
Proposed System:
%e eplore methods for learning local image descriptors from training data %e
describe a set of building bloc&s for constructing descriptors which can be
combined together.
%e consider both linear and nonlinear transforms with dimensionality
reduction.
These techni$ues have state-of-the-art performance in all of our test scenarios'
have been used to design local feature descriptors for a robust structure.
The color interest point detectors are presented and a scale selection method is
proposed.
Hardware e!"irements:-
#(#T)" * Pentium I+ ,.- ./z
/A01 1I#2 * -3 .4
0A" * ,56 "4
So#tware e!"irements:-
7perating system * %indows 8P Professional
I1) * "icrosoft +isual #tudio .9et ,335
:oding ;anguage * :< .9)T