-
Notifications
You must be signed in to change notification settings - Fork 0
/
cvpr_visualsearch.m
217 lines (177 loc) · 5.91 KB
/
cvpr_visualsearch.m
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
%% EEE3032 - Computer Vision and Pattern Recognition (ee3.cvpr)
%%
%% cvpr_visualsearch.m
%% Skeleton code provided as part of the coursework assessment
%%
%% This code will load in all descriptors pre-computed (by the
%% function cvpr_computedescriptors) from the images in the MSRCv2 dataset.
%%
%% It will pick a descriptor at random and compare all other descriptors to
%% it - by calling cvpr_compare. In doing so it will rank the images by
%% similarity to the randomly picked descriptor. Note that initially the
%% function cvpr_compare returns a random number - you need to code it
%% so that it returns the Euclidean distance or some other distance metric
%% between the two descriptors it is passed.
%%
%% (c) John Collomosse 2010 ([email protected])
%% Centre for Vision Speech and Signal Processing (CVSSP)
%% University of Surrey, United Kingdom
close all;
clear all;
%% Edit the following line to the folder you unzipped the MSRCv2 dataset to
DATASET_FOLDER = 'dataset';
%% Folder that holds the results...
DESCRIPTOR_FOLDER = 'descriptors';
%% and within that folder, another folder to hold the descriptors
%% we are interested in working with
DESCRIPTOR_SUBFOLDER='avgRGB';
% DESCRIPTOR_SUBFOLDER='globalRGBhisto';
% 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)
ALLFEAT=[];
ALLFILES=cell(1,0);
ALLCATs=[];
ctr=1;
allfiles=dir (fullfile([DATASET_FOLDER,'/Images/*.bmp']));
for filenum=1:length(allfiles)
fname=allfiles(filenum).name;
%identify photo category for PR calculation
split_string = split(fname, '_');
ALLCATs(filenum) = str2double(split_string(1));
imgfname_full=([DATASET_FOLDER,'/Images/',fname]);
img=double(imread(imgfname_full))./255;
thesefeat=[];
featfile=[DESCRIPTOR_FOLDER,'/',DESCRIPTOR_SUBFOLDER,'/',fname(1:end-4),'.mat'];%replace .bmp with .mat
load(featfile,'F');
ALLFILES{ctr}=imgfname_full;
ALLFEAT=[ALLFEAT ; F];
ctr=ctr+1;
end
% get counts for each category for PR calculation
CAT_HIST = histogram(ALLCATs).Values;
CAT_TOTAL = length(CAT_HIST);
run_total = 50;
AP_values = zeros([1, run_total]);
for run=1:run_total
%% 2) Pick an image at random to be the query
NIMG=size(ALLFEAT,1); % number of images in collection
queryimg=floor(rand()*NIMG); % index of a random image
if queryimg == 0
queryimg = 1;
end
%% 3) Compute the distance of image to the query
dst=[];
for i=1:NIMG
candidate=ALLFEAT(i,:);
query=ALLFEAT(queryimg,:);
category=ALLCATs(i);
%% COMPARE FUNCTION
thedst=compareEuclidean(query,candidate);
dst=[dst ; [thedst i category]];
end
dst=sortrows(dst,1); % sort the results
%% 4) Calculate PR
precision_values=zeros([1, NIMG]);
recall_values=zeros([1, NIMG]);
correct_at_n=zeros([1, NIMG]);
query_row = dst(1,:);
query_category = query_row(1,3);
fprintf('category was %s\n', CATEGORIES(query_category))
%calculate PR for each n
for i=1:NIMG
rows = dst(1:i, :);
correct_results = 0;
incorrect_results = 0;
if i > 1
for n=1:i - 1
row = rows(n, :);
category = row(3);
if category == query_category
correct_results = correct_results + 1;
else
incorrect_results = incorrect_results + 1;
end
end
end
% LAST ROW
row = rows(i, :);
category = row(3);
if category == query_category
correct_results = correct_results + 1;
correct_at_n(i) = 1;
else
incorrect_results = incorrect_results + 1;
end
precision = correct_results / i;
recall = correct_results / CAT_HIST(1,query_category);
precision_values(i) = precision;
recall_values(i) = recall;
end
%% 5) calculate AP
average_precision = sum(precision_values .* correct_at_n) / CAT_HIST(1,run);
AP_values(run) = average_precision;
%% 6) plot PR curve
figure(1)
plot(recall_values, precision_values);
hold on;
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
%% 8 Calculate MAP
% figure(4)
% histogram(AP_values);
% title('Average Precision Distribution');
% ylabel('Count');
% xlabel('Average Precision');
% xlim([0, 1]);
MAP = mean(AP_values)
AP_sd = std(AP_values)
% figure(2)
% plot(1:run_total, AP_values);
% title('Average Precision Per Run');
% xlabel('Run');
% ylabel('Average Precision');