Dev

Project.toml

@@ -1,7 +1,7 @@
 name = "FaceDetection"
 uuid = "00808967-75e2-4046-a522-2ca211e35506"
 authors = ["Jake W. Ireland <jakewilliami@icloud.com> and contributors"]
-version = "0.2.0"
+version = "1.0.0"
 
 [deps]
 ColorTypes = "3da002f7-5984-5a60-b8a6-cbb66c0b333f"

examples/read.jl

@@ -12,7 +12,7 @@ Adapted from https://github.com/Simon-Hohberg/Viola-Jones/
 
 println("\033[1;34m===>\033[0;38m\033[1;38m\tLoading required libraries (it will take a moment to precompile if it is your first time doing this)...\033[0;38m")
 
-include(joinpath(dirname(dirname(@__FILE__)), "src", "FaceDetection.jl"))
+include(joinpath(dirname(@__DIR__), "src", "FaceDetection.jl"))
 
 using .FaceDetection
 const FD = FaceDetection
@@ -33,14 +33,16 @@ function main(;
 
 	max_feature_width, max_feature_height, min_feature_height, min_feature_width, min_size_img = determine_feature_size(pos_testing_path, neg_testing_path; scale = scale, scale_to = scale_to)
 	img_size = scale ? scale_to : min_size_img
-	data_file = joinpath(dirname(@__FILE__), "data", "haar-like_features_c$(num_classifiers)_$(img_size)")
+	img_width, img_height = min_size_img
+	data_file = joinpath(@__DIR__, "data", "feature_votes_$(img_size)")
 
 	if ! isfile(data_file)
-		error(throw("You do not have a data file.  Ensure you run \"write.jl\" to obtain your Haar-like features before running this script/"))
+		error(throw("You do not have a data file.  Ensure you run \"write.jl\" to obtain your feature votes before running this programme."))
 	end
 
 	# read classifiers from file
-	classifiers = deserialize(data_file)
+	votes, features = deserialize(data_file)
+	classifiers = FD.learn(pos_training_path, neg_training_path, features, votes, num_classifiers)
 
 	FD.notify_user("Testing selected classifiers...")
 	num_faces = length(filtered_ls(pos_testing_path))

examples/write.jl

@@ -12,7 +12,7 @@ Adapted from https://github.com/Simon-Hohberg/Viola-Jones/
 
 println("\033[1;34m===>\033[0;38m\033[1;38m\tLoading required libraries (it will take a moment to precompile if it is your first time doing this)...\033[0;38m")
 
-include(joinpath(dirname(dirname(@__FILE__)), "src", "FaceDetection.jl"))
+include(joinpath(dirname(@__DIR__), "src", "FaceDetection.jl"))
 
 using .FaceDetection
 const FD = FaceDetection
@@ -45,12 +45,13 @@ function main(;
 	end
 
 	# classifiers are haar like features
-	classifiers = FD.learn(pos_training_path, neg_training_path, num_classifiers, min_feature_height, max_feature_height, min_feature_width, max_feature_width; scale = scale, scale_to = scale_to)
+	votes = FD.get_feature_votes(pos_training_path, neg_training_path, num_classifiers, min_feature_height, max_feature_height, min_feature_width, max_feature_width; scale = scale, scale_to = scale_to)
+
 
 	# write classifiers to file
 	img_size = scale ? scale_to : min_size_img
-	data_file = joinpath(dirname(@__FILE__), "data", "haar-like_features_c$(num_classifiers)_$(img_size)")
-	serialize(data_file, classifiers)
+	data_file = joinpath(@__DIR__, "data", "feature_votes_$(img_size)")
+	serialize(data_file, votes)
 end
 
 @time main(smart_choose_feats=true, scale=true, scale_to=(20, 20))

src/AdaBoost.jl

@@ -16,34 +16,7 @@ using Base.Threads: @threads
 using Base.Iterators: partition
 using ProgressMeter: @showprogress, Progress, next!
 
-#=
-    learn(
-        positive_iis::AbstractArray,
-        negative_iis::AbstractArray,
-        num_classifiers::Int64=-1,
-        min_feature_width::Int64=1,
-        max_feature_width::Int64=-1,
-        min_feature_height::Int64=1,
-        max_feature_height::Int64=-1
-    ) ->::Array{HaarLikeObject,1}
-
-The boosting algorithm for learning a query online.  $T$ hypotheses are constructed, each using a single feature.
-The final hypothesis is a weighted linear combination of the $T$ hypotheses, where the weights are inversely proportional to the training errors.
-This function selects a set of classifiers. Iteratively takes the best classifiers based on a weighted error.
-
-# Arguments
-
-- `positive_iis::AbstractArray`: List of positive integral image examples
-- `negative_iis::AbstractArray`: List of negative integral image examples
-- `num_classifiers::Integer`: Number of classifiers to select. -1 will use all classifiers
-- `min_feature_width::Integer`: the minimum width of the feature
-- `max_feature_width::Integer`: the maximum width of the feature
-- `min_feature_height::Integer`: the minimum height of the feature
-- `max_feature_width::Integer`: the maximum height of the feature
-
-# Returns `classifiers::Array{HaarLikeObject, 1}`: List of selected features
-=#
-function learn(
+function get_feature_votes(
     positive_path::AbstractString,
     negative_path::AbstractString,
     num_classifiers::Integer=-1,
@@ -53,7 +26,7 @@ function learn(
     max_feature_height::Integer=-1;
     scale::Bool = false,
     scale_to::Tuple = (200, 200)
-)::Array{HaarLikeObject,1}
+    )
 
     # get number of positive and negative images (and create a global variable of the total number of images——global for the @everywhere scope)
     positive_files = filtered_ls(positive_path)
@@ -73,18 +46,9 @@ function learn(
     max_feature_height = isequal(max_feature_height, -1) ? img_height : max_feature_height
     max_feature_width = isequal(max_feature_width, -1) ? img_height : max_feature_width
 
-    # Initialise weights $w_{1,i} = \frac{1}{2m}, \frac{1}{2l}$, for $y_i=0,1$ for negative and positive examples respectively
-    pos_weights = ones(num_pos) / (2 * num_pos)
-    neg_weights = ones(num_neg) / (2 * num_neg)
-
-    # Concatenate positive and negative weights into one `weights` array
-    weights = vcat(pos_weights, neg_weights)
-    labels = vcat(ones(Int8, num_pos), ones(Int8, num_neg) * -one(Int8))
-
     # Create features for all sizes and locations
     features = create_features(img_height, img_width, min_feature_width, max_feature_width, min_feature_height, max_feature_height)
     num_features = length(features)
-    feature_indices = Array(1:num_features)
     num_classifiers = isequal(num_classifiers, -1) ? num_features : num_classifiers
 
     # create an empty array with dimensions (num_imgs, numFeautures)
@@ -106,6 +70,61 @@ function learn(
     end
     print("\n") # for a new line after the progress bar
 
+    return votes, features
+end
+
+#=
+    learn(
+        positive_iis::AbstractArray,
+        negative_iis::AbstractArray,
+        num_classifiers::Int64=-1,
+        min_feature_width::Int64=1,
+        max_feature_width::Int64=-1,
+        min_feature_height::Int64=1,
+        max_feature_height::Int64=-1
+    ) ->::Array{HaarLikeObject,1}
+
+The boosting algorithm for learning a query online.  $T$ hypotheses are constructed, each using a single feature.
+The final hypothesis is a weighted linear combination of the $T$ hypotheses, where the weights are inversely proportional to the training errors.
+This function selects a set of classifiers. Iteratively takes the best classifiers based on a weighted error.
+
+# Arguments
+
+- `positive_iis::AbstractArray`: List of positive integral image examples
+- `negative_iis::AbstractArray`: List of negative integral image examples
+- `num_classifiers::Integer`: Number of classifiers to select. -1 will use all classifiers
+- `min_feature_width::Integer`: the minimum width of the feature
+- `max_feature_width::Integer`: the maximum width of the feature
+- `min_feature_height::Integer`: the minimum height of the feature
+- `max_feature_width::Integer`: the maximum height of the feature
+
+# Returns `classifiers::Array{HaarLikeObject, 1}`: List of selected features
+=#
+function learn(
+    positive_path::AbstractString,
+    negative_path::AbstractString,
+    features::AbstractArray,
+    votes::AbstractArray,
+    num_classifiers::Integer=-1
+    )
+
+    # get number of positive and negative images (and create a global variable of the total number of images——global for the @everywhere scope)
+    num_pos = length(filtered_ls(positive_path))
+    num_neg = length(filtered_ls(negative_path))
+    num_imgs = num_pos + num_neg
+
+    # Initialise weights $w_{1,i} = \frac{1}{2m}, \frac{1}{2l}$, for $y_i=0,1$ for negative and positive examples respectively
+    pos_weights = ones(num_pos) / (2 * num_pos)
+    neg_weights = ones(num_neg) / (2 * num_neg)
+
+    # Concatenate positive and negative weights into one `weights` array
+    weights = vcat(pos_weights, neg_weights)
+    labels = vcat(ones(Int8, num_pos), ones(Int8, num_neg) * -one(Int8))
+
+    num_features = length(features)
+    feature_indices = Array(1:num_features)
+    num_classifiers = isequal(num_classifiers, -1) ? num_features : num_classifiers
+
     notify_user("Selecting classifiers...")
     # select classifiers
     classifiers = []
@@ -145,6 +164,33 @@ function learn(
     print("\n") # for a new line after the progress bar
 
     return classifiers
+
+end
+function learn(
+    positive_path::AbstractString,
+    negative_path::AbstractString,
+    num_classifiers::Integer=-1,
+    min_feature_width::Integer=1,
+    max_feature_width::Integer=-1,
+    min_feature_height::Integer=1,
+    max_feature_height::Integer=-1;
+    scale::Bool = false,
+    scale_to::Tuple = (200, 200)
+)::Array{HaarLikeObject,1}
+
+    votes, features = get_feature_votes(
+        positive_path,
+        negative_path,
+        num_classifiers,
+        min_feature_width,
+        max_feature_width,
+        min_feature_height,
+        max_feature_height,
+        scale = scale,
+        scale_to = scale_to
+    )
+
+    return learn(positive_path, negative_path, features, votes, num_classifiers)
 end
 
 #=