diff options
| -rw-r--r-- | Dockerfile | 5 | ||||
| -rw-r--r-- | Gemfile | 3 | ||||
| -rw-r--r-- | Gemfile.lock | 29 | ||||
| -rw-r--r-- | README.md | 4 | ||||
| -rwxr-xr-x | nypl_recrop.rb | 66 | ||||
| -rwxr-xr-x | run-sterogranimator-hi-res.sh | 3 | ||||
| -rwxr-xr-x | template_match_multiscale.py | 108 |
7 files changed, 216 insertions, 2 deletions
@@ -1,7 +1,9 @@ FROM teeps/cuda7.5-art-vid MAINTAINER Ryan Baumann <ryan.baumann@gmail.com> -RUN apt-get install -y bc +RUN apt-get install -y bc python-opencv +RUN apt-add-repository ppa:brightbox/ruby-ng && apt-get update && apt-get install -y ruby2.2 ruby2.2-dev +RUN gem install bundler ADD . /root/torch-warp @@ -9,4 +11,5 @@ RUN cp -v *-static /root/torch-warp/ WORKDIR /root/torch-warp +RUN bundle install RUN cd consistencyChecker && make @@ -0,0 +1,3 @@ +source 'https://rubygems.org' +gem 'rest-client' +gem 'dimensions' diff --git a/Gemfile.lock b/Gemfile.lock new file mode 100644 index 0000000..2edfb89 --- /dev/null +++ b/Gemfile.lock @@ -0,0 +1,29 @@ +GEM + remote: https://rubygems.org/ + specs: + dimensions (1.3.0) + domain_name (0.5.20160615) + unf (>= 0.0.5, < 1.0.0) + http-cookie (1.0.2) + domain_name (~> 0.5) + mime-types (3.1) + mime-types-data (~> 3.2015) + mime-types-data (3.2016.0521) + netrc (0.11.0) + rest-client (2.0.0) + http-cookie (>= 1.0.2, < 2.0) + mime-types (>= 1.16, < 4.0) + netrc (~> 0.8) + unf (0.1.4) + unf_ext + unf_ext (0.0.7.2) + +PLATFORMS + ruby + +DEPENDENCIES + dimensions + rest-client + +BUNDLED WITH + 1.12.5 @@ -17,7 +17,9 @@ This process is inspired by Patrick Feaster's post on [Animating Historical Phot For input, you need two PNG images of the same dimensions named e.g. `filename_0.png` and `filename_1.png`. You can then run `./run-torchwarp.sh filename` to run all the steps and output the morphing animation as `morphed_filename.gif`. -You can also use `./run-stereogranimator.sh ID` with an image ID from [NYPL's Stereogranimator](http://stereo.nypl.org/) to download an animated GIF and run it through the morphing process. +You can also use `./run-stereogranimator.sh ID` with an image ID from [NYPL's Stereogranimator](http://stereo.nypl.org/) to download an animated GIF at low resolution and run it through the morphing process. + +If you sign up for [the NYPL Digital Collections API](http://api.repo.nypl.org/), you can use your API token to download high-resolution original images. The `nypl_recrop.rb` script reads the token from the `NYPL_API_TOKEN` environment variable, and takes a Stereogranimator image ID as an argument, downloading the original TIFF image and using `template_matching_multiscale.rb` to calculate the crop and split the image into two views at full resolution. The `run-stereogranimator-hi-res.sh` script uses this process instead of `wget` with low-resolution GIFs. You can also pass the `NYPL_API_TOKEN` environment variable [in your `docker run` command](https://docs.docker.com/engine/reference/run/#/env-environment-variables). ## Docker Usage diff --git a/nypl_recrop.rb b/nypl_recrop.rb new file mode 100755 index 0000000..4ca1843 --- /dev/null +++ b/nypl_recrop.rb @@ -0,0 +1,66 @@ +#!/usr/bin/env ruby + +require 'json' +require 'rest-client' +require 'dimensions' + +NYPL_API_TOKEN = ENV["NYPL_API_TOKEN"] +NYPL_AUTH = "Token token=\"#{NYPL_API_TOKEN}\"" +NYPL_ENDPOINT = "http://api.repo.nypl.org/api/v1/items" + +stereo_metadata = JSON.parse(RestClient.get("http://stereo.nypl.org/view/#{ARGV[0]}.json")) + +unless stereo_metadata['external_id'] == 0 + abort('Image must be from NYPL collections.') +end + +digital_id = stereo_metadata['digitalid'].upcase +image_id = JSON.parse(RestClient.get("#{NYPL_ENDPOINT}/local_image_id/#{digital_id}", :Authorization => NYPL_AUTH)) +image_uuid = image_id['nyplAPI']['response']['uuid'] +image_captures = JSON.parse(RestClient.get("#{NYPL_ENDPOINT}/#{image_uuid}", :Authorization => NYPL_AUTH)) + +matching_captures = image_captures['nyplAPI']['response']['capture'].select{|c| c['imageID'].upcase == digital_id} + +if matching_captures && matching_captures.length > 0 + # capture_uuid = matching_captures[0]['uuid'] + # capture_details = JSON.parse(RestClient.get("#{NYPL_ENDPOINT}/item_details/#{capture_uuid}", :Authorization => NYPL_AUTH)) + highres_url = matching_captures[0]['highResLink'] + lowres_url = stereo_metadata['url'] + + # download images + $stderr.puts "Downloading images..." + `wget -nc -O #{ARGV[0]}.jpg '#{lowres_url}'` + `wget -nc -O #{ARGV[0]}.tif '#{highres_url}'` + + # calculate the crop for the original image using multiscale template matching + $stderr.puts "Calculating crop..." + crop_params = `./template_match_multiscale.py --template #{ARGV[0]}.jpg --image #{ARGV[0]}.tif`.chomp + + # apply the crop + `convert #{ARGV[0]}.tif -crop #{crop_params} +repage #{ARGV[0]}_cropped.tif` + + # calculate dimensions + lowres_dims = Dimensions.dimensions("#{ARGV[0]}.jpg") + highres_dims = Dimensions.dimensions("#{ARGV[0]}_cropped.tif") + + # calculate scaling + x_scale = highres_dims[0].to_f / lowres_dims[0].to_f + y_scale = highres_dims[1].to_f / lowres_dims[1].to_f + + # calculate scaled dimensions + cropped_width = stereo_metadata['width'] * x_scale + cropped_height = stereo_metadata['height'] * y_scale + x1 = stereo_metadata['x1'] * x_scale + x2 = stereo_metadata['x2'] * x_scale + y1 = stereo_metadata['y1'] * y_scale + y2 = stereo_metadata['y2'] * y_scale + + # use the scaled dimensions to split the cropped original into the component images + $stderr.puts "Cropping image..." + `convert #{ARGV[0]}_cropped.tif -crop #{cropped_width}x#{cropped_height}+#{x1}+#{y1} +repage #{ARGV[0]}_0.png` + + `convert #{ARGV[0]}_cropped.tif -crop #{cropped_width}x#{cropped_height}+#{x2}+#{y2} +repage #{ARGV[0]}_1.png` +else + puts image_captures.to_json + abort("No matching captures for #{digital_id}") +end diff --git a/run-sterogranimator-hi-res.sh b/run-sterogranimator-hi-res.sh new file mode 100755 index 0000000..9e18d71 --- /dev/null +++ b/run-sterogranimator-hi-res.sh @@ -0,0 +1,3 @@ +#!/bin/bash + +bundle exec ./nypl_recrop.rb $1 && ./run-torchwarp.sh $1 diff --git a/template_match_multiscale.py b/template_match_multiscale.py new file mode 100755 index 0000000..4c104af --- /dev/null +++ b/template_match_multiscale.py @@ -0,0 +1,108 @@ +#!/usr/bin/env python +# USAGE +# python template_match_multiscale.py --template template.png --image image.tif +# Adapted from: http://www.pyimagesearch.com/2015/01/26/multi-scale-template-matching-using-python-opencv/ + +# import the necessary packages +import numpy as np +import argparse +import glob +import cv2 + +def resize(image, width = None, height = None, inter = cv2.INTER_AREA): + # initialize the dimensions of the image to be resized and + # grab the image size + dim = None + (h, w) = image.shape[:2] + + # if both the width and height are None, then return the + # original image + if width is None and height is None: + return image + + # check to see if the width is None + if width is None: + # calculate the ratio of the height and construct the + # dimensions + r = height / float(h) + dim = (int(w * r), height) + + # otherwise, the height is None + else: + # calculate the ratio of the width and construct the + # dimensions + r = width / float(w) + dim = (width, int(h * r)) + + # resize the image + resized = cv2.resize(image, dim, interpolation = inter) + + # return the resized image + return resized + +# construct the argument parser and parse the arguments +ap = argparse.ArgumentParser() +ap.add_argument("-t", "--template", required=True, help="Path to template image") +ap.add_argument("-i", "--image", required=True, + help="Path to image where template will be matched") +ap.add_argument("-v", "--visualize", + help="Flag indicating whether or not to visualize each iteration") +args = vars(ap.parse_args()) + +# load the image image, convert it to grayscale, and detect edges +template = cv2.imread(args["template"]) +template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY) +template = cv2.Canny(template, 50, 200) +(tH, tW) = template.shape[:2] +cv2.imshow("Template", template) + +imagePath = args["image"] +# load the image, convert it to grayscale, and initialize the +# bookkeeping variable to keep track of the matched region +gray = cv2.imread(imagePath, 0) +found = None + +# loop over the scales of the image +for scale in np.linspace(0.2, 1.0, 20)[::-1]: + # resize the image according to the scale, and keep track + # of the ratio of the resizing + resized = resize(gray, width = int(gray.shape[1] * scale)) + r = gray.shape[1] / float(resized.shape[1]) + + # if the resized image is smaller than the template, then break + # from the loop + if resized.shape[0] < tH or resized.shape[1] < tW: + break + + # detect edges in the resized, grayscale image and apply template + # matching to find the template in the image + edged = cv2.Canny(resized, 50, 200) + result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF) + (_, maxVal, _, maxLoc) = cv2.minMaxLoc(result) + + # check to see if the iteration should be visualized + if args.get("visualize", False): + # draw a bounding box around the detected region + clone = np.dstack([edged, edged, edged]) + cv2.rectangle(clone, (maxLoc[0], maxLoc[1]), + (maxLoc[0] + tW, maxLoc[1] + tH), (0, 0, 255), 2) + cv2.imshow("Visualize", clone) + cv2.waitKey(0) + + # if we have found a new maximum correlation value, then ipdate + # the bookkeeping variable + if found is None or maxVal > found[0]: + found = (maxVal, maxLoc, r) + +# unpack the bookkeeping varaible and compute the (x, y) coordinates +# of the bounding box based on the resized ratio +(_, maxLoc, r) = found +(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r)) +(endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r)) + +print "%dx%d+%d+%d" % ((endX - startX), (endY - startY), startX, startY) + +# draw a bounding box around the detected result and display the image +# cv2.rectangle(gray, (startX, startY), (endX, endY), (0, 0, 255), 2) +# cv2.imshow("Image", gray) +# cv2.waitKey(0) |