average_hash 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +15 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/.travis.yml +10 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +45 -0
- data/Rakefile +6 -0
- data/average_hash.gemspec +25 -0
- data/lib/average_hash.rb +8 -0
- data/lib/average_hash/hashing_strategy.rb +54 -0
- data/lib/average_hash/image.rb +27 -0
- data/lib/average_hash/version.rb +3 -0
- data/spec/average_hash_spec.rb +57 -0
- data/spec/fixtures/sample_1.jpg +0 -0
- data/spec/fixtures/sample_2.jpg +0 -0
- data/spec/spec_helper.rb +7 -0
- metadata +120 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
ZmNkN2ViMWQzMjgyMmE2MTVlNGU1MzMyODU5YWI4M2VkMWZmZDg0NA==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
YjdlODY4NDdmMjMzN2EwN2ZiY2QxOGZjY2E1MjE0MDAwZjRiNTkyMA==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
MTg4NzQyMjJiZDEyNmNjZDJjNjk5N2ZkYzhiMzg3MmFiYWQ1ZmY3NzBhNWIx
|
10
|
+
MjhjNzJjMTVhY2VjZDJiZTBmYTY3ZjQ4NmJiMzhhMGY1Mzc0NTdhNjU3Mjhh
|
11
|
+
MzBjMTgwYTczYjUyMzU5OTk4MGJlNWNjYTBiZmQwOTIzN2NhMDY=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
ZmI4MTFiODBkZTcxMzJjMDk5ODEyNmZhNzZiODY5NmEyNDQwYjM5Y2UwYzI2
|
14
|
+
ZjQxMDQ3OTk3ZTRiMGMwMDEzNGVlMjBmODNjOTMyMmJjNWI4OGY5NmUwYTQw
|
15
|
+
OTQ4ZTA1OTk2OTA2ODRhZTE3OTVkNDc0NTRkYWEyODg5NDg5ZDY=
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 ToruIwashita
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
# AverageHash
|
2
|
+
|
3
|
+
Simple similarity calculation method of image. It is inspired by [Phashion](https://github.com/westonplatter/phashion).
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'average_hash'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle install
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install average_hash
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
Determine the similarity of image
|
22
|
+
|
23
|
+
require 'average_hash'
|
24
|
+
image_1 = AverageHash::Image.new(file_path_1)
|
25
|
+
image_2 = AverageHash::Image.new(file_path_2)
|
26
|
+
image_1.duplicate?(image_2)
|
27
|
+
=> true
|
28
|
+
|
29
|
+
If you want to set the threshold of hamming distance, you can do the following. (dafault threshold is 5)
|
30
|
+
|
31
|
+
image_1.duplicate?(image_2, threshold: 3)
|
32
|
+
=> false
|
33
|
+
|
34
|
+
Get the hamming distance between two images
|
35
|
+
|
36
|
+
image_1.distance_from(image_2)
|
37
|
+
=> 4
|
38
|
+
|
39
|
+
## Contributing
|
40
|
+
|
41
|
+
1. Fork it
|
42
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
43
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
44
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
45
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'average_hash/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "average_hash"
|
8
|
+
spec.version = AverageHash::VERSION
|
9
|
+
spec.authors = ["ToruIwashita"]
|
10
|
+
spec.email = ["toru.iwashita@gmail.com"]
|
11
|
+
spec.description = %q{Simple similarity calculation method of image}
|
12
|
+
spec.summary = %q{Simple similarity calculation method of image}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_development_dependency "rspec"
|
24
|
+
spec.add_development_dependency "rmagick"
|
25
|
+
end
|
data/lib/average_hash.rb
ADDED
@@ -0,0 +1,54 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
require 'RMagick'
|
4
|
+
|
5
|
+
module AverageHash
|
6
|
+
class HashingStrategy
|
7
|
+
RESIZNING_SIZE = 8
|
8
|
+
PIXEL_ACQUISITION_SIZE = 1
|
9
|
+
|
10
|
+
INDEX_OF_R = 0
|
11
|
+
INDEX_OF_G = 1
|
12
|
+
INDEX_OF_B = 2
|
13
|
+
|
14
|
+
NTSC_COEFFICIENT_OF_R = 0.30
|
15
|
+
NTSC_COEFFICIENT_OF_G = 0.59
|
16
|
+
NTSC_COEFFICIENT_OF_B = 0.11
|
17
|
+
|
18
|
+
def initialize(file_path)
|
19
|
+
@image = Magick::Image.read(file_path).first.resize(RESIZNING_SIZE, RESIZNING_SIZE)
|
20
|
+
end
|
21
|
+
|
22
|
+
def generate_hash
|
23
|
+
(image_pixel_count.times).map { |i| gray_scaled_pixel(i) > average_pixel ? '1' : '0' }.join
|
24
|
+
end
|
25
|
+
|
26
|
+
private
|
27
|
+
|
28
|
+
def image_columns
|
29
|
+
@image.columns
|
30
|
+
end
|
31
|
+
|
32
|
+
def image_rows
|
33
|
+
@image.rows
|
34
|
+
end
|
35
|
+
|
36
|
+
def image_pixel_count
|
37
|
+
image_columns * image_rows
|
38
|
+
end
|
39
|
+
|
40
|
+
def average_pixel
|
41
|
+
gray_scaled_pixels = (image_pixel_count.times).map { |i| gray_scaled_pixel(i) }
|
42
|
+
gray_scaled_pixels.reduce(0, :+) / image_pixel_count
|
43
|
+
end
|
44
|
+
|
45
|
+
def gray_scaled_pixel(num)
|
46
|
+
px = pixel_at((num % RESIZNING_SIZE), (num / RESIZNING_SIZE))
|
47
|
+
px[INDEX_OF_R] * NTSC_COEFFICIENT_OF_R + px[INDEX_OF_G] * NTSC_COEFFICIENT_OF_G + px[INDEX_OF_B] * NTSC_COEFFICIENT_OF_B
|
48
|
+
end
|
49
|
+
|
50
|
+
def pixel_at(offset_of_x, offset_of_y)
|
51
|
+
@image.export_pixels(offset_of_x, offset_of_y, PIXEL_ACQUISITION_SIZE, PIXEL_ACQUISITION_SIZE)
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
module AverageHash
|
4
|
+
class Image
|
5
|
+
DEFAULT_DUPE_THRESHOLD = 5
|
6
|
+
|
7
|
+
attr_reader :file_path
|
8
|
+
|
9
|
+
def initialize(file_path)
|
10
|
+
@file_path = file_path
|
11
|
+
end
|
12
|
+
|
13
|
+
def fingerprint
|
14
|
+
@average_hash ||= HashingStrategy.new(@file_path).generate_hash
|
15
|
+
@average_hash.to_i(2)
|
16
|
+
end
|
17
|
+
|
18
|
+
def distance_from(other)
|
19
|
+
(fingerprint ^ other.fingerprint).to_s(2).count('1')
|
20
|
+
end
|
21
|
+
|
22
|
+
def duplicate?(other, opts = {})
|
23
|
+
threshold = opts[:threshold] || DEFAULT_DUPE_THRESHOLD
|
24
|
+
distance_from(other) <= threshold
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,57 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe AverageHash::Image do
|
4
|
+
context 'fingerprint use sample_1.jpg' do
|
5
|
+
it do
|
6
|
+
image_1 = AverageHash::Image.new(fixture_file_path('sample_1.jpg'))
|
7
|
+
expect(image_1.fingerprint).to eq 13158600607563222924
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
context 'fingerprint use sample_2.jpg' do
|
12
|
+
it do
|
13
|
+
image_2 = AverageHash::Image.new(fixture_file_path('sample_2.jpg'))
|
14
|
+
expect(image_2.fingerprint).to eq 7870530257777914161
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
context 'use two jpg images' do
|
19
|
+
before do
|
20
|
+
@image_1 = AverageHash::Image.new(fixture_file_path('sample_1.jpg'))
|
21
|
+
@image_2 = AverageHash::Image.new(fixture_file_path('sample_2.jpg'))
|
22
|
+
end
|
23
|
+
|
24
|
+
context '"sample_1" distance_from "sample_2"' do
|
25
|
+
it { expect(@image_1.distance_from(@image_2)).to eq 36 }
|
26
|
+
end
|
27
|
+
|
28
|
+
context '"sample_1" duplicate? "sample_2"' do
|
29
|
+
it { expect(@image_1.duplicate?(@image_2)).to be_falsey }
|
30
|
+
end
|
31
|
+
|
32
|
+
context '"sample_1" duplicate? "sample_2" with threshold 35' do
|
33
|
+
it { expect(@image_1.duplicate?(@image_2, threshold: 35)).to be_falsey }
|
34
|
+
end
|
35
|
+
|
36
|
+
context '"sample_1" duplicate? "sample_2" with threshold 36' do
|
37
|
+
it { expect(@image_1.duplicate?(@image_2, threshold: 36)).to be_truthy }
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
context 'use duplicate jpg image, "sample_1" duplicate? "sample_1"' do
|
42
|
+
it do
|
43
|
+
image_1_1 = AverageHash::Image.new(fixture_file_path('sample_1.jpg'))
|
44
|
+
image_1_2 = AverageHash::Image.new(fixture_file_path('sample_1.jpg'))
|
45
|
+
expect(image_1_1.duplicate?(image_1_2)).to be_truthy
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
|
50
|
+
describe AverageHash::HashingStrategy do
|
51
|
+
context 'generate_hash with argument "smaple_1.jpg"' do
|
52
|
+
it do
|
53
|
+
hashing_strategy = AverageHash::HashingStrategy.new(fixture_file_path('sample_1.jpg'))
|
54
|
+
expect(hashing_strategy.generate_hash).to eq '1011011010011100101111011000100100001011000010111000111110001100'
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
Binary file
|
Binary file
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: average_hash
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- ToruIwashita
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-11-07 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ! '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ! '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rmagick
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ! '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Simple similarity calculation method of image
|
70
|
+
email:
|
71
|
+
- toru.iwashita@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- .gitignore
|
77
|
+
- .rspec
|
78
|
+
- .travis.yml
|
79
|
+
- Gemfile
|
80
|
+
- LICENSE.txt
|
81
|
+
- README.md
|
82
|
+
- Rakefile
|
83
|
+
- average_hash.gemspec
|
84
|
+
- lib/average_hash.rb
|
85
|
+
- lib/average_hash/hashing_strategy.rb
|
86
|
+
- lib/average_hash/image.rb
|
87
|
+
- lib/average_hash/version.rb
|
88
|
+
- spec/average_hash_spec.rb
|
89
|
+
- spec/fixtures/sample_1.jpg
|
90
|
+
- spec/fixtures/sample_2.jpg
|
91
|
+
- spec/spec_helper.rb
|
92
|
+
homepage: ''
|
93
|
+
licenses:
|
94
|
+
- MIT
|
95
|
+
metadata: {}
|
96
|
+
post_install_message:
|
97
|
+
rdoc_options: []
|
98
|
+
require_paths:
|
99
|
+
- lib
|
100
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
101
|
+
requirements:
|
102
|
+
- - ! '>='
|
103
|
+
- !ruby/object:Gem::Version
|
104
|
+
version: '0'
|
105
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
110
|
+
requirements: []
|
111
|
+
rubyforge_project:
|
112
|
+
rubygems_version: 2.0.0
|
113
|
+
signing_key:
|
114
|
+
specification_version: 4
|
115
|
+
summary: Simple similarity calculation method of image
|
116
|
+
test_files:
|
117
|
+
- spec/average_hash_spec.rb
|
118
|
+
- spec/fixtures/sample_1.jpg
|
119
|
+
- spec/fixtures/sample_2.jpg
|
120
|
+
- spec/spec_helper.rb
|