added background, added confusion matrix

This commit is contained in:
aj 2019-11-28 14:32:16 +00:00
parent 066bfdf3ad
commit de1d6b3464
4 changed files with 666 additions and 29 deletions

View File

@ -32,6 +32,28 @@ DESCRIPTOR_FOLDER = 'descriptors';
% DESCRIPTOR_SUBFOLDER='spatialColour';
DESCRIPTOR_SUBFOLDER='spatialColourTexture';
CATEGORIES = ["Farm Animal"
"Tree"
"Building"
"Plane"
"Cow"
"Face"
"Car"
"Bike"
"Sheep"
"Flower"
"Sign"
"Bird"
"Book Shelf"
"Bench"
"Cat"
"Dog"
"Road"
"Water Features"
"Human Figures"
"Coast"
];
%% 1) Load all the descriptors into "ALLFEAT"
%% each row of ALLFEAT is a descriptor (is an image)
@ -60,8 +82,9 @@ end
% get counts for each category for PR calculation
CAT_HIST = histogram(ALLCATs).Values;
CAT_TOTAL = length(CAT_HIST);
run_total = 100;
run_total = 1;
AP_values = zeros([1, run_total]);
for run=1:run_total
%% 2) Pick an image at random to be the query
@ -91,6 +114,8 @@ for run=1:run_total
query_row = dst(1,:);
query_category = query_row(1,3);
fprintf('category was %s', CATEGORIES(query_category))
%calculate PR for each n
for i=1:NIMG
@ -105,7 +130,7 @@ for run=1:run_total
row = rows(n, :);
category = row(3);
if category == query_category;
if category == query_category
correct_results = correct_results + 1;
else
incorrect_results = incorrect_results + 1;
@ -142,7 +167,7 @@ for run=1:run_total
P_rel_n(i) = precision * i_result_relevant;
end
sum_P_rel_n = sum(P_rel_n)
sum_P_rel_n = sum(P_rel_n);
average_precision = sum_P_rel_n / CAT_HIST(1,query_category);
AP_values(run) = average_precision;
@ -156,10 +181,33 @@ for run=1:run_total
title('PR Curve');
xlabel('Recall');
ylabel('Precision');
%% 7) Visualise the results
%% These may be a little hard to see using imgshow
%% If you have access, try using imshow(outdisplay) or imagesc(outdisplay)
confusion_matrix = zeros(CAT_TOTAL);
SHOW=15; % Show top 15 results
dst=dst(1:SHOW,:);
outdisplay=[];
for i=1:size(dst,1)
img=imread(ALLFILES{dst(i,2)});
img=img(1:2:end,1:2:end,:); % make image a quarter size
img=img(1:81,:,:); % crop image to uniform size vertically (some MSVC images are different heights)
outdisplay=[outdisplay img];
%populate confusion matrix
confusion_matrix(query_category, dst(i,3)) = confusion_matrix(query_category, dst(i,3)) + 1;
end
figure(3)
imgshow(outdisplay);
axis off;
end
%% 7 Calculate MAP
%% 8 Calculate MAP
figure(4)
histogram(AP_values);
title('Average Precision Distribution');
@ -175,21 +223,3 @@ plot(1:run_total, AP_values);
title('Average Precision Per Run');
xlabel('Run');
ylabel('Average Precision');
%% 8) Visualise the results
%% These may be a little hard to see using imgshow
%% If you have access, try using imshow(outdisplay) or imagesc(outdisplay)
SHOW=15; % Show top 15 results
dst=dst(1:SHOW,:);
outdisplay=[];
for i=1:size(dst,1)
img=imread(ALLFILES{dst(i,2)});
img=img(1:2:end,1:2:end,:); % make image a quarter size
img=img(1:81,:,:); % crop image to uniform size vertically (some MSVC images are different heights)
outdisplay=[outdisplay img];
end
figure(3)
imgshow(outdisplay);
axis off;

View File

@ -5,6 +5,9 @@
\save_transient_properties true
\origin unavailable
\textclass article
\begin_preamble
\rfoot{6420013}
\end_preamble
\use_default_options true
\maintain_unincluded_children false
\language english
@ -43,9 +46,11 @@
\use_package stackrel 1
\use_package stmaryrd 1
\use_package undertilde 1
\cite_engine basic
\cite_engine_type default
\cite_engine biblatex
\cite_engine_type authoryear
\biblio_style plain
\biblatex_bibstyle ieee
\biblatex_citestyle ieee
\use_bibtopic false
\use_indices false
\paperorientation portrait
@ -71,7 +76,7 @@
\dynamic_quotes 0
\papercolumns 1
\papersides 1
\paperpagestyle default
\paperpagestyle fancy
\tracking_changes false
\output_changes false
\html_math_output 0
@ -134,6 +139,7 @@ An application of computer vision and visual media processing is that of
These measured features can be arranged as a data structure or descriptor
and a visual search system can be composed of the extraction and comparison
of these descriptors.
It is an example of content based image retrieval or CBIR.
\end_layout
\begin_layout Subsection
@ -175,7 +181,7 @@ Visual search is used in consumer products to generate powerful results
\end_layout
\begin_layout Section
Theoretical Implementations
Descriptors
\end_layout
\begin_layout Subsection
@ -400,6 +406,23 @@ For a spatial colour descriptor the average RGB values for each cell can
total value.
\end_layout
\begin_layout Subsubsection
Efficacy
\end_layout
\begin_layout Standard
Computing a spatial descriptor can increase performance when highlighting
the difference to a colour histogram.
While a colour histogram will describe how many of each colour is present
in an image, spatial colour techniques of the type described above will
indicate the colours found in each area of the image.
Considering an image of a cow in a field, the colour histogram will identify
and count the brown pixels of the cow and the green pixels of the field,
spatial colour techniques will identify an area of brown in the middle
of an image surrounded by an area of green.
\end_layout
\begin_layout Subsection
Spatial Texture
\end_layout
@ -434,7 +457,7 @@ noprefix "false"
\end_inset
), which approximates the gradient of the intensity of an image.
), which approximates the gradient of the greyscale intensity of an image.
\begin_inset Float figure
wide false
sideways false
@ -582,10 +605,150 @@ Where
refers to the number of edge histogram bins.
\end_layout
\begin_layout Section
Distance Measures
\end_layout
\begin_layout Subsection
L1 Norm
\end_layout
\begin_layout Section
Test Methods
\end_layout
\begin_layout Subsection
Dataset
\end_layout
\begin_layout Standard
For the purposes of these experiments the Microsoft MSRC
\begin_inset CommandInset citation
LatexCommand cite
key "microsoft_msrc"
literal "false"
\end_inset
version 2 dataset was used.
The set is made up of 591 images across 20 categories, the classifications
for which can be seen in appendix
\begin_inset CommandInset ref
LatexCommand ref
reference "sec:MSRC-Dataset-Classifications"
plural "false"
caps "false"
noprefix "false"
\end_inset
.
\end_layout
\begin_layout Subsection
Precision and Recall
\end_layout
\begin_layout Standard
When comapring the effectiveness of different descriptors the main measurements
are those of precision and recall.
\end_layout
\begin_layout Standard
Once the visual search system has ranked a dataset on similarity to a query
image, the precision and recall can be calculated up to
\begin_inset Formula $n$
\end_inset
images through the ranked list.
\end_layout
\begin_layout Standard
At each
\begin_inset Formula $n$
\end_inset
the precision is defined as the number of images up to
\begin_inset Formula $n$
\end_inset
that are classed as relevant.
Higher precision values indicate better system accuracy and an ideal system
response as
\begin_inset Formula $n$
\end_inset
increases would be a precision of 1 until all relevant documents have been
returned at which point it would reduce to a minimum value of the fraction
of relevant documents in the dataset.
This would indicate that the system is able to select a relevant image
every time one is available.
\end_layout
\begin_layout Standard
The recall is defined at
\begin_inset Formula $n$
\end_inset
as how many of the available relevant results have been returned up to
\begin_inset Formula $n$
\end_inset
.
Higher recall values at
\begin_inset Formula $n$
\end_inset
indicate that the system can recall relevant documents faster with less
false positives and begins at 0 before increasing to a maximum of 1 as
\begin_inset Formula $n$
\end_inset
increases when all have been returned.
\end_layout
\begin_layout Standard
While both measurements appear to reflect similar concepts there is a difference.
Precision is a measure of how accurately a system can decide whether a
document is relevant while recall can be thought of as a measure of a systems
repeated accuracy and measures how long it takes to retrieve all relevant
documents.
\end_layout
\begin_layout Standard
A system with high recall but low precision will indicate that the system
is effectively able to retrieve all relevant documents eventually however
there will be false positives within the results.
Results of this quality would be advantageous when it is important to obtain
all relevant results however not when the relevance of each and every one
is valued.
\end_layout
\begin_layout Standard
A system with high precision but low recall would indicate that the system
is able to very confident in its selection of relevant documents but may
indicate an increase in false negatives.
\end_layout
\begin_layout Subsection
Precision Recall Curve
\end_layout
\begin_layout Standard
A way to visualise the response of a system is to calculate both precision
and recall at each
\begin_inset Formula $n$
\end_inset
and plot both as what is known as a precision-recall curve or PR curve.
\end_layout
\begin_layout Subsection
Methods
\end_layout
\begin_layout Section
Results
\end_layout
@ -616,6 +779,451 @@ options "plain"
\end_inset
\end_layout
\begin_layout Section
MSRC Dataset Classifications
\begin_inset CommandInset label
LatexCommand label
name "sec:MSRC-Dataset-Classifications"
\end_inset
\end_layout
\begin_layout Standard
\align center
\begin_inset Tabular
<lyxtabular version="3" rows="21" columns="2">
<features tabularvalignment="middle">
<column alignment="center" valignment="top">
<column alignment="center" valignment="top">
<row>
<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Category Index
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Category Classification
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
1
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Farm Animal
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
2
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Tree
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
3
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Building
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
4
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Plane
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
5
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Cow
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
6
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Face
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
7
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Car
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
8
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Bike
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
9
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Sheep
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
10
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Flower
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
11
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Sign
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
12
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Bird
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
13
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Book Shelf
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
14
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Bench
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
15
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Cat
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
16
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Dog
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
17
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Road
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
18
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Water Features
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
19
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Human Figures
\end_layout
\end_inset
</cell>
</row>
<row>
<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
20
\end_layout
\end_inset
</cell>
<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
\begin_inset Text
\begin_layout Plain Layout
Coast
\end_layout
\end_inset
</cell>
</row>
</lyxtabular>
\end_inset
\end_layout
\end_body

Binary file not shown.

View File

@ -1,2 +1 @@
@misc{microsoft_msrc, title={Image Understanding }, url={https://www.microsoft.com/en-us/research/project/image-understanding/}, journal={Microsoft}, publisher={Microsoft}, year={2000}, month={Jan}}