minor refactoring

* rename data-images
* add pep8speaks
* move figures
* docs preview
* update config

.pep8speaks.yml

@@ -0,0 +1,28 @@
+# File : .pep8speaks.yml
+
+scanner:
+    diff_only: True  # If False, the entire file touched by the Pull Request is scanned for errors. If True, only the diff is scanned.
+    linter: pycodestyle  # Other option is flake8
+
+pycodestyle:  # Same as scanner.linter value. Other option is flake8
+    max-line-length: 110  # Default is 79 in PEP 8
+    ignore:  # Errors and warnings to ignore
+        - W504  # line break after binary operator
+        - E402  # module level import not at top of file
+        - E731  # do not assign a lambda expression, use a def
+        - C406  # Unnecessary list literal - rewrite as a dict literal.
+        - E741  # ambiguous variable name
+
+no_blank_comment: True  # If True, no comment is made on PR without any errors.
+descending_issues_order: False  # If True, PEP 8 issues in message will be displayed in descending order of line numbers in the file
+
+message:  # Customize the comment made by the bot,
+    opened:  # Messages when a new PR is submitted
+        header: "Hello @{name}! Thanks for opening this PR. "
+                # The keyword {name} is converted into the author's username
+        footer: "Do see the [Hitchhiker's guide to code style](https://goo.gl/hqbW4r)"
+                # The messages can be written as they would over GitHub
+    updated:  # Messages when new commits are added to the PR
+        header: "Hello @{name}! Thanks for updating this PR. "
+        footer: ""  # Why to comment the link to the style guide everytime? :)
+    no_errors: "There are currently no PEP 8 issues detected in this Pull Request. Cheers! :beers: "

MANIFEST.in

@@ -34,28 +34,28 @@ recursive-include experiments_* *.py *.yml
 recursive-include handling_annotations *.py
 
 # Include the figures
-recursive-include docs/source/_figures *.gif *.jpg *.png
+recursive-include assets *.gif *.jpg *.png
 
 # Include the sample images
-include data_images/others/lena.png
-    data_images/synthetic/reference.jpg
-    data_images/synthetic/texture_rgb_3cls.jpg
-    data_images/others/sea_starfish-2.jpg
-    data_images/histology_CIMA/29-041-Izd2-w35-CD31-3-les1.jpg
-    data_images/histology_Flagship/Case001_Cytokeratin.jpg
-    data_images/drosophila_disc/image/img_6.jpg
-    data_images/drosophila_disc/annot/img_6.png
-    data_images/drosophila_ovary_slice/image/insitu7545.jpg
-    data_images/drosophila_ovary_slice/annot_struct/insitu7545.png
-    data_images/langerhans_islets/image/gtExoIsl_21.jpg
+include data-images/others/lena.png
+    data-images/synthetic/reference.jpg
+    data-images/synthetic/texture_rgb_3cls.jpg
+    data-images/others/sea_starfish-2.jpg
+    data-images/histology_CIMA/29-041-Izd2-w35-CD31-3-les1.jpg
+    data-images/histology_Flagship/Case001_Cytokeratin.jpg
+    data-images/drosophila_disc/image/img_6.jpg
+    data-images/drosophila_disc/annot/img_6.png
+    data-images/drosophila_ovary_slice/image/insitu7545.jpg
+    data-images/drosophila_ovary_slice/annot_struct/insitu7545.png
+    data-images/langerhans_islets/image/gtExoIsl_21.jpg
 
 prune .git
 prune .github
 prune libs
 prune venv
 prune build
 prune docs
-prune data_images
+prune data-images
 prune tests
 prune notebooks
 prune ij_macros

README.md

@@ -17,11 +17,11 @@
 
 ## Superpixel segmentation with GraphCut regularisation
 
-Image segmentation is widely used as an initial phase of many image processing tasks in computer vision and image analysis. Many recent segmentation methods use superpixels because they reduce the size of the segmentation problem by order of magnitude. Also,  features on superpixels are much more robust than features on pixels only. We use spatial regularisation on superpixels to make segmented regions more compact. The segmentation pipeline comprises (i) computation of superpixels; (ii) extraction of descriptors such as colour and texture; (iii) soft classification, using a standard classifier for supervised learning, or the Gaussian Mixture Model for unsupervised learning; (iv) final segmentation using Graph Cut. We use this segmentation pipeline on real-world applications in medical imaging (see [sample images](data_images/).
+Image segmentation is widely used as an initial phase of many image processing tasks in computer vision and image analysis. Many recent segmentation methods use superpixels because they reduce the size of the segmentation problem by order of magnitude. Also,  features on superpixels are much more robust than features on pixels only. We use spatial regularisation on superpixels to make segmented regions more compact. The segmentation pipeline comprises (i) computation of superpixels; (ii) extraction of descriptors such as colour and texture; (iii) soft classification, using a standard classifier for supervised learning, or the Gaussian Mixture Model for unsupervised learning; (iv) final segmentation using Graph Cut. We use this segmentation pipeline on real-world applications in medical imaging (see [sample images](data-images/).
  We also show that [unsupervised segmentation](notebooks/segment-2d_slic-fts-clust-gc.ipynb) is sufficient for some situations,
   and provides similar results to those obtained using [trained segmentation](notebooks/segment-2d_slic-fts-classif-gc.ipynb).
 
-![schema](docs/source/_figures/schema_slic-fts-clf-gc.jpg)
+![schema](assets/schema_slic-fts-clf-gc.jpg)
 
 **Sample ipython notebooks:**
 * [Supervised segmentation](notebooks/segment-2d_slic-fts-classif-gc.ipynb) requires training annotation
@@ -30,8 +30,8 @@ Image segmentation is widely used as an initial phase of many image processing t
 
 **Illustration**
 
-![input image](docs/source/_figures/insitu7545.jpg)
-![segmentation](docs/source/_figures/insitu7545_gc.png)
+![input image](assets/insitu7545.jpg)
+![segmentation](assets/insitu7545_gc.png)
 
 Reference: _Borovec J., Svihlik J., Kybic J., Habart D. (2017). **Supervised and unsupervised segmentation using superpixels, model estimation, and Graph Cut.** In: Journal of Electronic Imaging._
 
@@ -47,8 +47,8 @@ An image processing pipeline to detect and localize Drosophila egg chambers that
 
 **Illustration**
 
-![estimated centres](docs/source/_figures/insitu7545_center_clusters.jpg)
-![ellipse fitting](docs/source/_figures/insitu7545_ellipse_fit.png)
+![estimated centres](assets/insitu7545_center_clusters.jpg)
+![ellipse fitting](assets/insitu7545_ellipse_fit.png)
 
 Reference: _Borovec J., Kybic J., Nava R. (2017) **Detection and Localization of Drosophila Egg Chambers in Microscopy Images.** In: Machine Learning in Medical Imaging._
 
@@ -63,8 +63,8 @@ Region growing is a classical image segmentation method based on hierarchical re
 
 **Illustration**
 
-![growing RG](docs/source/_figures/insitu7545_RG2SP_animation.gif)
-![ellipse fitting](docs/source/_figures/insitu7545_RG2SP-gc-mm.png)
+![growing RG](assets/insitu7545_RG2SP_animation.gif)
+![ellipse fitting](assets/insitu7545_RG2SP-gc-mm.png)
 
 Reference: _Borovec J., Kybic J., Sugimoto, A. (2017). **Region growing using superpixels with learned shape prior.** In: Journal of Electronic Imaging._
 
@@ -134,26 +134,26 @@ We introduce some useful tools for work with image annotation and segmentation.
 * **Quantization:** in case you have some smooth colour labelling in your images you can remove them with following quantisation script.
     ```bash
     python handling_annotations/run_image_color_quantization.py \
-        -imgs "./data_images/drosophila_ovary_slice/segm_rgb/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/segm_rgb/*.png" \
         -m position -thr 0.01 --nb_workers 2
     ```
 * **Paint labels:** concerting image labels into colour space and other way around.
     ```bash
     python handling_annotations/run_image_convert_label_color.py \
-        -imgs "./data_images/drosophila_ovary_slice/segm/*.png" \
-        -out ./data_images/drosophila_ovary_slice/segm_rgb
+        -imgs "./data-images/drosophila_ovary_slice/segm/*.png" \
+        -out ./data-images/drosophila_ovary_slice/segm_rgb
     ```
 * **Visualisation:** having input image and its segmentation we can use simple visualisation which overlap the segmentation over input image. 
     ```bash
     python handling_annotations/run_overlap_images_segms.py \
-        -imgs "./data_images/drosophila_ovary_slice/image/*.jpg" \
-        -segs ./data_images/drosophila_ovary_slice/segm \
+        -imgs "./data-images/drosophila_ovary_slice/image/*.jpg" \
+        -segs ./data-images/drosophila_ovary_slice/segm \
         -out ./results/overlap_ovary_segment
     ```
 * **In-painting** selected labels in segmentation.
     ```bash
     python handling_annotations/run_segm_annot_inpaint.py \
-        -imgs "./data_images/drosophila_ovary_slice/segm/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/segm/*.png" \
         --label 4
     ```
 * **Replace labels:** change labels in input segmentation into another set of labels in 1:1 schema.
@@ -167,50 +167,50 @@ We introduce some useful tools for work with image annotation and segmentation.
 ### Semantic (un/semi)supervised segmentation
 
 We utilise (un)supervised segmentation according to given training examples or some expectations.
-![vusial debug](docs/source/_figures/visual_img_43_debug.jpg)
+![vusial debug](assets/visual_img_43_debug.jpg)
 
 * Evaluate superpixels (with given SLIC parameters) quality against given segmentation. It helps to find out the best SLIC configuration.
     ```bash
     python experiments_segmentation/run_eval_superpixels.py \
-        -imgs "./data_images/drosophila_ovary_slice/image/*.jpg" \
-        -segm "./data_images/drosophila_ovary_slice/annot_eggs/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/image/*.jpg" \
+        -segm "./data-images/drosophila_ovary_slice/annot_eggs/*.png" \
         --img_type 2d_split \
         --slic_size 20 --slic_regul 0.25 --slico
     ```
 * Perform **Un-Supervised** segmentation in images given in CSV
     ```bash
     python experiments_segmentation/run_segm_slic_model_graphcut.py \
-       -l ./data_images/langerhans_islets/list_lang-isl_imgs-annot.csv -i "" \
+       -l ./data-images/langerhans_islets/list_lang-isl_imgs-annot.csv -i "" \
        -cfg experiments_segmentation/sample_config.yml \
        -o ./results -n langIsl --nb_classes 3 --visual --nb_workers 2
     ```
     OR specified on particular path:
     ```bash
     python experiments_segmentation/run_segm_slic_model_graphcut.py \
-       -l "" -i "./data_images/langerhans_islets/image/*.jpg" \
+       -l "" -i "./data-images/langerhans_islets/image/*.jpg" \
        -cfg ./experiments_segmentation/sample_config.yml \
        -o ./results -n langIsl --nb_classes 3 --visual --nb_workers 2
     ```
-    ![unsupervised](docs/source/_figures/imag-disk-20_gmm.jpg)
+    ![unsupervised](assets/imag-disk-20_gmm.jpg)
 * Perform **Supervised** segmentation with afterwards evaluation.
     ```bash
     python experiments_segmentation/run_segm_slic_classif_graphcut.py \
-        -l ./data_images/drosophila_ovary_slice/list_imgs-annot-struct.csv \
-        -i "./data_images/drosophila_ovary_slice/image/*.jpg" \
+        -l ./data-images/drosophila_ovary_slice/list_imgs-annot-struct.csv \
+        -i "./data-images/drosophila_ovary_slice/image/*.jpg" \
         --path_config ./experiments_segmentation/sample_config.yml \
         -o ./results -n Ovary --img_type 2d_split --visual --nb_workers 2
     ```
-    ![supervised](docs/source/_figures/imag-disk-20_train.jpg)
+    ![supervised](assets/imag-disk-20_train.jpg)
 * Perform **Semi-Supervised** is using the the supervised pipeline with not fully annotated images.
 * For both experiment you can evaluate segmentation results.
     ```bash
     python experiments_segmentation/run_compute-stat_annot-segm.py \
-        -a "./data_images/drosophila_ovary_slice/annot_struct/*.png" \
+        -a "./data-images/drosophila_ovary_slice/annot_struct/*.png" \
         -s "./results/experiment_segm-supervise_ovary/*.png" \
-        -i "./data_images/drosophila_ovary_slice/image/*.jpg" \
+        -i "./data-images/drosophila_ovary_slice/image/*.jpg" \
         -o ./results/evaluation --visual
     ```
-    ![vusial](docs/source/_figures/segm-visual_D03_sy04_100x.jpg)
+    ![vusial](assets/segm-visual_D03_sy04_100x.jpg)
 
 The previous two (un)segmentation accept [configuration file](experiments_segmentation/sample_config.yml) (YAML) by parameter `-cfg` with some extra parameters which was not passed in arguments, for instance:
 ```yaml
@@ -240,16 +240,16 @@ In general, the input is a formatted list (CSV file) of input images and annotat
 1. With zone annotation, we train a classifier for centre candidate prediction. The annotation can be a CSV file with annotated centres as points, and the zone of positive examples is set uniformly as the circular neighbourhood around these points. Another way (preferable) is to use an annotated image with marked zones for positive, negative and neutral examples.
     ```bash
     python experiments_ovary_centres/run_center_candidate_training.py -list none \
-        -segs "./data_images/drosophila_ovary_slice/segm/*.png" \
-        -imgs "./data_images/drosophila_ovary_slice/image/*.jpg" \
-        -centers "./data_images/drosophila_ovary_slice/center_levels/*.png" \
+        -segs "./data-images/drosophila_ovary_slice/segm/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/image/*.jpg" \
+        -centers "./data-images/drosophila_ovary_slice/center_levels/*.png" \
         -out ./results -n ovary
     ```
 1. Having trained classifier we perform center prediction composed from two steps: i) center candidate clustering and ii) candidate clustering.
     ```bash
     python experiments_ovary_centres/run_center_prediction.py -list none \
-        -segs "./data_images/drosophila_ovary_slice/segm/*.png" \
-        -imgs "./data_images/drosophila_ovary_slice/image/*.jpg" \
+        -segs "./data-images/drosophila_ovary_slice/segm/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/image/*.jpg" \
         -centers ./results/detect-centers-train_ovary/classifier_RandForest.pkl \
         -out ./results -n ovary
     ```
@@ -260,8 +260,8 @@ In general, the input is a formatted list (CSV file) of input images and annotat
 1. This is just cut out clustering in case you want to use different parameters.
     ```bash
     python experiments_ovary_centres/run_center_clustering.py \
-        -segs "./data_images/drosophila_ovary_slice/segm/*.png" \
-        -imgs "./data_images/drosophila_ovary_slice/image/*.jpg" \
+        -segs "./data-images/drosophila_ovary_slice/segm/*.png" \
+        -imgs "./data-images/drosophila_ovary_slice/image/*.jpg" \
         -centers "./results/detect-centers-train_ovary/candidates/*.csv" \
         -out ./results
     ```
@@ -286,7 +286,7 @@ In general, the input is a formatted list (CSV file) of input images and annotat
         -out ~/Medical-drosophila/RESULTS/atlas_datasets/ovary_images/stage_3
     ```
 
-![ellipse fitting](docs/source/_figures/insitu7544_ellipses.jpg)
+![ellipse fitting](assets/insitu7544_ellipses.jpg)
 
 ### Region growing with a shape prior
 
@@ -303,12 +303,12 @@ pip install --user git+https://github.com/Borda/morph-snakes.git
     ```bash
     python experiments_ovary_detect/run_RG2Sp_estim_shape-models.py  \
         -annot "~/Medical-drosophila/egg_segmentation/mask_2d_slice_complete_ind_egg/*.png" \
-        -out ./data_images -nb 15
+        -out ./data-images -nb 15
     ```
 1. Run several segmentation techniques on each image.
     ```bash
     python experiments_ovary_detect/run_ovary_egg-segmentation.py  \
-        -list ./data_images/drosophila_ovary_slice/list_imgs-segm-center-points.csv \
+        -list ./data-images/drosophila_ovary_slice/list_imgs-segm-center-points.csv \
         -out ./results -n ovary_image --nb_workers 1 \
         -m ellipse_moments \
            ellipse_ransac_mmt \
@@ -328,15 +328,15 @@ pip install --user git+https://github.com/Borda/morph-snakes.git
 1. In the end, cut individual segmented objects comes as minimal bounding box.
     ```bash
     python experiments_ovary_detect/run_cut_segmented_objects.py \
-        -annot "./data_images/drosophila_ovary_slice/annot_eggs/*.png" \
-        -img "./data_images/drosophila_ovary_slice/segm/*.png" \
+        -annot "./data-images/drosophila_ovary_slice/annot_eggs/*.png" \
+        -img "./data-images/drosophila_ovary_slice/segm/*.png" \
         -out ./results/cut_images --padding 50
     ```
 1. Finally, performing visualisation of segmentation results together with expert annotation.
     ```bash
     python experiments_ovary_detect/run_export_user-annot-segm.py
     ```
-    ![user-annnot](docs/source/_figures/insitu7545_user-annot-segm.jpg)
+    ![user-annnot](assets/insitu7545_user-annot-segm.jpg)
 
 ---
 

circle.yml

@@ -122,6 +122,11 @@ jobs:
       - *install_pips
       # DOCUMENTATION
       - *make_docs
+      # PREVIEW
+      - store_artifacts:
+          # allows us to preview the generated html pages
+          path: docs/build/html/
+          destination: html
 
 workflows:
   version: 2

data-images/drosophila_disc/list_imaginal-disks.csv

@@ -0,0 +1,11 @@
+,path_image,path_annot
+1,data-images/drosophila_disc/image/img_5.jpg,data-images/drosophila_disc/annot/img_5.png
+2,data-images/drosophila_disc/image/img_6.jpg,data-images/drosophila_disc/annot/img_6.png
+3,data-images/drosophila_disc/image/img_12.jpg,data-images/drosophila_disc/annot/img_12.png
+4,data-images/drosophila_disc/image/img_14.jpg,data-images/drosophila_disc/annot/img_14.png
+5,data-images/drosophila_disc/image/img_15.jpg,data-images/drosophila_disc/annot/img_15.png
+6,data-images/drosophila_disc/image/img_19.jpg,data-images/drosophila_disc/annot/img_19.png
+7,data-images/drosophila_disc/image/img_20.jpg,data-images/drosophila_disc/annot/img_20.png
+8,data-images/drosophila_disc/image/img_24.jpg,data-images/drosophila_disc/annot/img_24.png
+9,data-images/drosophila_disc/image/img_26.jpg,data-images/drosophila_disc/annot/img_26.png
+10,data-images/drosophila_disc/image/img_43.jpg,data-images/drosophila_disc/annot/img_43.png

data-images/drosophila_disc/list_imaginal-disks_short.csv

@@ -0,0 +1,3 @@
+,path_image,path_annot
+1,data-images/drosophila_disc/image/img_6.jpg,data-images/drosophila_disc/annot/img_6.png
+2,data-images/drosophila_disc/image/img_43.jpg,data-images/drosophila_disc/annot/img_43.png

data-images/drosophila_ovary_slice/list_imgs-annot-struct.csv

@@ -0,0 +1,11 @@
+,path_image,path_annot
+1,data-images/drosophila_ovary_slice/image/insitu4174.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu4174.png
+2,data-images/drosophila_ovary_slice/image/insitu4358.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu4358.png
+3,data-images/drosophila_ovary_slice/image/insitu7331.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu7331.png
+4,data-images/drosophila_ovary_slice/image/insitu7544.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu7544.png
+5,data-images/drosophila_ovary_slice/image/insitu7545.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu7545.png
+6,data-images/drosophila_ovary_slice/image/insitu4174.tif,data-images/drosophila_ovary_slice/annot_struct/insitu4174.png
+7,data-images/drosophila_ovary_slice/image/insitu4358.tif,data-images/drosophila_ovary_slice/annot_struct/insitu4358.png
+8,data-images/drosophila_ovary_slice/image/insitu7331.tif,data-images/drosophila_ovary_slice/annot_struct/insitu7331.png
+9,data-images/drosophila_ovary_slice/image/insitu7544.tif,data-images/drosophila_ovary_slice/annot_struct/insitu7544.png
+10,data-images/drosophila_ovary_slice/image/insitu7545.tif,data-images/drosophila_ovary_slice/annot_struct/insitu7545.png

data_images/drosophila_ovary_slice/list_imgs-annot-struct_short.csv → data-images/drosophila_ovary_slice/list_imgs-annot-struct_short.csv

@@ -1,3 +1,3 @@
 ,path_image,path_annot
-1,data_images/drosophila_ovary_slice/image/insitu4174.jpg,data_images/drosophila_ovary_slice/annot_struct/insitu4174.png
-2,data_images/drosophila_ovary_slice/image/insitu7545.tif,data_images/drosophila_ovary_slice/annot_struct/insitu7545.png
+1,data-images/drosophila_ovary_slice/image/insitu4174.jpg,data-images/drosophila_ovary_slice/annot_struct/insitu4174.png
+2,data-images/drosophila_ovary_slice/image/insitu7545.tif,data-images/drosophila_ovary_slice/annot_struct/insitu7545.png