CoverMaker (ImageJ) | |
---|---|
Author | Pavel Tomancak, Johannes Schindelin |
Maintainer | Pavel Tomancak |
Source | on GitHub |
Initial release | 27/05/2012 |
Latest version | 29/06/2012 |
Development status | active |
Category | Category:Plugins |
- Membrane Pro Cover Image Maker 1 0 72
- Membrane Pro Cover Image Maker 1 0 75
- Membrane Pro Cover Image Maker 1 0 78
- Membrane Pro Cover Image Maker 1 0 74
- 5Prepare CoverMaker Database
Cover Photo Maker Post is an app specifically for designing social media posts. With one click, you can select sizing that's perfectly scaled for a Facebook cover photo, so you don't have to hassle with resizing an image. This Cover photo maker for Facebook is super fast and super easy, making it ideal for those with little design experience. Unscrew membrane housing cap from the membrane housing and remove the RO membrane. The membrane has often been there for 1-3 years and may be difficult to pull out. This may require needle-nose pliers to remove. If you would like to clean the membrane housing, disconnect the two tubes on the opposite end of the cap.
Introduction
Error creating thumbnail: Unable to save thumbnail to destination
Nature cover for the paper on the developmental hourglass [1].
This project explores the algorithms for reconstructing scientific images as a combination of other scientific images drawing from a large database of scientific imagery. The resulting image can be visually stunning given that a large database with good balance of colors is available. One such database consisting of about 66,000 images of gene expression patterns in Drosophila embryogenesis is provided here as a starting point. The results of the plugin can be used as material for cover art such as for example the Nature cover on the right.Membrane Pro Cover Image Maker 1 0 72
There are many online or offline solutions available for reconstructing images in this way, some of them undoubtedly more sophisticated than the CoverMaker. The CoverMaker is open source, integrated into Fiji and so can serve as platform for exploring the associated image analysis questions. Everyone is welcome to improve the code and the algorithms, contribute more image databases and show off the results of their experiments.
Please note that the Nature cover was NOT made with the CoverMaker plugin, but it inspired its subsequent development. Below we show the template image depicting the famous Ernst Haeckel embryo drawings and the resulting output image generated using the CoverMaker. For more examples jump to the Gallery section.
Drawing of Haeckel embryos. For afficionados this is in fact Romanes' 1892 copy of the Ernst Haeckel drawing. If you consider Haeckel a fraud, think again and start by reading the excellent Robert J. Richards book 'The Tragic Sense of Life'. | CoverMaker rendition of Haeckel embryos The image was generated using a database of 66,579 images of gene expression pattern during Drosophila embryogenesis visualized by histochemical RNA in situ hybridization.[2][3] |
Gallery
Here are some example CoverMaker images. Feel free to send your experiments particularly if you make it on the cover ;-).
- Backcover of Bioessays featuring famous drawing of early Drosophila embryogenesis by Victoria Foe
- Cover of Methods journal focused on Drosophila, edited by Nobert Perrimon
- Cover of Bioimage Informatics 2012 conference brochure
- Cover of July 2012 Issue of Nature Methods containing focus on Bioimage Informatics
- high-resolution version of Nature Methods cover
- Open clipart microscope
- Runt expression pattern at cellular blastoderm stage of Drosophila embryogenesis
- Cover suggestion for Focus on Bioimage Informatics - logos
- Stage 10 Drosophila egg chamber
- Dorsal ectoderm expression at blastoderm satge
- ImageJ2 logo
- Haeckel embryos
- Fiji logo
How does it work
Versions 1 1 11 – user friendly subversion client. The principle is very simple. One divides the template image into tiles that have the same pixel dimensions as the down-sampled database images (for instance 12 by 9 pixels as is the case in the provided image database). The program then systematically goes through the small tiles of the template image placing the database images that show best pixel wise color matching. We do this by summing the squared pixel-wise and color-wise differences between the template and all the database images and selecting the database image with the lowest sum (i.e. difference). There are other possible metrics, but this one works well for the embryo database.
The template image gets cropped to the dimensions that are compatible with the tile size (i.e. for 12x9 tiles the dimensions have to be divisible by 12 and 9 respectively). Every database image is used only once and so, as the build-up progresses, the database can get 'exhausted' for a particular color and shape. To minimize this effect we place the tiles randomly into the image.
The tricky part is to prepare the database. We provide a pre-computed database based on the embryo in situ data containing 12x9 pixels tiles. You can generate your own databases using the Prepare CoverMaker Database script that scours a file system and down-samples all available RGB jpegs to the desired tile dimensions.
Finally, for printing poster size images, the plugin will generate in the second step of its operation (after the output image has been formed at the original resolution of the template image) an arbitrarily large output image at desired dpi resolution using the database of original images available here or generated by you using the Prepare CoverMaker Database script.
CoverMaker Tutorial
We will start by opening an image that will serve as template. For the time being it needs to be an RGB image. It can have any dimensions, however consider that larger images will require many more tiles to fill up, it will take long and the effect will be less visible. Fiji logo shown on the right is a good start. Alternatively one of the Fiji sample images such as the clown.jpg gives good results quickly. Note: I would recommend having only one image opened before proceeding further. | Template image |
Now we launch the CoverMaker python script by going to Plugins -> Examples -> CoverMaker -> Cover Maker. (Or typing 'l' and searching with keyword 'cover'). A basic dialog box will appear prompting us to select the image database by clicking on Browse and locating in the file system the tif file containing down-sampled images. The tif file is called 12_9.tif indicating that the images have been scaled to the 12x9 pixel dimension. This is the default tile size. If you use a different database with different aspect ratio please change the default tile width and height in the dialog box. Next click ok and the reconstruction will start. As a first step the template image will be cropped to the size that is multiple of the tile width and height (not shown, see Future work for comment on the cropping issue. Below we monitor the progress of building the cover | The initial CoverMaker dialog box |
Starting | Progress 1 | Progress 2 | Almost there | Finished Cover |
After the reconstruction finishes a second dialog box pops up. Here we have an option to Cancel the program, the finished low resolution image will remain opened and can be saved using normal Fiji procedures. If we like the result of the experiment, we can save it at high resolution using the original images. We can decide on the final resolution of the output image in dpi, specify the width or height in pixels or inches. The fields are linked and should update while we are editing the different parameters. Next we need to click on Browse and locate the zip file containing the originals. Finally we click on ok and the building of the final high resolution output image will commence as shown below. Note that now the image grows sequentially since we already know where to place the images from the initial run and the randomization is no longer necessary. | The second CoverMaker dialog box for saving high resolution output |
Starting | Progress 1 | Progress 2 | Almost there | Finished Cover |
When we zoom in on the final output image that was generated in this case at 300dpi and compare with the initial reconstructed image we will see the database images with much greater detail. The image can be made almost arbitrarily large and printed as a large poster. Note: the downsampler we use does not do a good job upsampling, thus when the originals are too small for a given dpi size combination artifacts in the output image will occur (grid of lines). This exception is currently not handled properly.
Close up on the Initial low resolution image | Close up on the final high resolution image |
Prepare CoverMaker Database
In many ways preparing the image databases is a trickier business than actually performing the reconstruction. The aim of the Prepare_CoverMaker_Database.py script (Plugins -> Examples -> Cover Maker -> Prepare Cover Maker Database) is to explore your local filesystem for RGB images that could be used to build a database. As many things can go wrong in the process, it should be considered experimental.
Input/Search/Output
Before we start searching for images we must decide on the dominant aspect ratio present in our image set. Obviously, since the tiles have all the same dimensions, different aspect ratios of input images would cause deformation during down-sampling to that common tile dimension. Fortunately, since CoverMaker is targeting scientific imaging, in most cases a large image database will have a uniform or one dominant aspect ratio.
Input and output parameters dialog
The user must also specify the aspect ratio and base directory under which the images are to be found.
The output parameters are the minimum and maximum tile width and height of the downsampled tiles. These should be compatible with the aspect ratio (for convenience the width and height are linked in the Dialog box). Users can specify a range of tile dimensions (by specifying minimum and maximum widths and heights) and the script will generate scalings between those bound in increments of one pixel. Note that the range should not be very broad (typically between 10 and 20 pixels). When the minimum and maximum are the same only single tile size will be generated.
Finally the user must specify the originals width and height to which the images should be scaled. If these dimensions are the same as the dominant image dimensions on the filesystem, no scaling will occur, however this will duplicate every image encountered during the search. The resulting zip archive could become too large. Note that the images need not be very large as they will be scaled down again when CoverMaker outputs the final image at reasonable resolution.
Progress log
The script will then recursively traverse the directory tree under this root looking for images with extensions jpeg, jpe and jpg. The extensions to be searched are currently hardcoded. During the search the script will write into ImageJ log the images it encountered and what is being done with them. Hopefully most images will have the matching aspect ratio specified above and will be scaled. Images with different aspect ratios will be skipped.
The output of the script are two types of files:
- tif stacks containing downsampled image tiles of the specified dimensions (the naming convention is width_height.tif, i.e. for 12x9 pixel tiles 12_9.tif). Separate tif file for each output tile size will be generated
- one zip archive of the original images scaled to the size specified in the parameters original width and original height (note that this file should NOT be unzipped)
Both output files are saved in the base directory. They can be directly used in the CoverMaker plugin.
Potential problems
Sometimes an image with jpeg like extension is not in fact an jpeg. The script currently checks if the image has three channels and skips the image if this is not the case. However, in my experience, a lot of unexpected things can happen when exploring large filesystems with diverse imagery. Finally, as the searching of a large filesystem can take some time, random errors, corrupted images or insufficient memory can cause the script to crash.
Catching these errors is the challenge for future improvements of the script.
Databases
Currently we provide a single database of images prepared for CoverMaker. The database contains 81,751 images of Drosophila melanogaster embryos stained by RNA in situ hybridization with probes for about 6000 genes. The images have been scaled to the size of 12x9 pixels resulting in a tif stack that can serve as input for the CoverMaker plugin. Additionally, in order to save the high resolution images you will need the matching zip archive of original images.
Database type | scaled tiles | originals (DO NOT unzip) |
Drosophila Embryo in situ | 12_9.tif (16.6MB) | originals.zip (1.45GB) |
Important note : Do not unzip the orinals.zip archive. The CoverMaker is able to extract the relevant images.
More scientific databases to come.. Feel free to send me yours.
Implementation and Acknowledgements
The plugin was written as a Jython script during the Madison ImageJ2/Fiji hackathon in January 2011. The heavy lifting is performed using in lined Java code snippet courtesy of Albert Cardona. All the large scale downsampling is done using Stephan Saalfeld proper downsampler. Johannes Schindelin has helped a lot with the Dialog Listeners and will maintain the plugin for posterity.
BTW, this plugin and its genesis is a great example of the power of Fiji and the hackathons. I came to the hackathon not knowing anything about python and with only basic knowledge of Java and the ImageJ code base. In ten days I had the plugin written, probably driving the Fiji geeks crazy with my constant basic (or downright stupid) questions. But the take home message for biologists is - it can be done!
Future work
There is clearly room for improvement. Here is what comes to my mind, but feel free to suggest more features or, even better, go ahead and implement them.
- implement, test and evaluate more color metrics
- research optimization strategies for the placement of the tiles
- avoid the need to crop the template by employing a proper out of bounds strategy
- implement different tile geometries (like for instance hexagons)
- port it all into Java and particularly ImgLib2 for better performance (hopefully)
References
- ↑A.T. Kalinka, K. Varga, D.T. Gerrard, S.W. Preibisch, D.L. Corcoran, J. Jarrels, U. Ohler, C.M. Bergman, P. Tomancak (2010), 'Gene expression divergence recapitulates the developmental hourglass model', Nature468 (7325): 811–844, DOI doi:10.1038/nature09634
- ↑P. Tomancak, A. Beaton, R. Weiszmann, E. Kwan, S. Shu, S.E. Lewis, S. Richards, M. Ashburner, V. Hartenstein, S.E. Celniker, G.M. Rubin (2002), 'Systematic determination of patterns of gene expression during Drosophila embryogenesis.', Genome Biology3 (12): 88–88
- ↑P. Tomancak, B.P. Berman, A. Beaton, R. Weiszmann, E. Kwan, V. Hartenstein, S.E. Celniker, G.M. Rubin (2007), 'Global analysis of patterns of gene expression during Drosophila embryogenesis.', Genome Biology8 (7): 145–145
Two tools in one. The online software that is both an excellent book mockup generator and ebook cover creator that thousands of authors and entrepreneurs are using to instantly create free ebook covers, 3d book mockups and book png files.
Ebook Cover Creator
More people use our free ebook creator than any other on the internet! Use the same software as the pros! To gain maximum interest and impact when selling ebooks, products or even when offering a free report, it is important that your product look valuable. The truth is that 98% of ebook covers created by authors do not compete well in the market place.
We polled groups of experienced book buyers by showing them the front ebook covers of self-published books that the readers did not know were self-published. An overwhelming majority of these readers said that they would not purchase the covers that they were shown because of the quality and design being subpar.
So the question is can an ebook cover creator actually design a book cover that readers are willing to get excited about? And the answer is absolutely. Our ebook cover creates has rave reviews for making amazing ebook covers for books from all genres.
Why Use Our Free Ebook Cover Creator
Membrane Pro Cover Image Maker 1 0 75
Use our ebook cover creator to make an amazing book from scratch or use one of over a hundred professionally designed and pre-built templates to customize and make your own. If you don’t have a cover yet then you will have the option to create one using our simple software. Super easy and free to use, our free ebook cover creator is the key to a great product launch or successful giveaway. Our creator has these awesome features:
- Easy to use design interface
- 130+ pre-built templates perfect for 30+ genres
- Ability to save an editable design onto your computer so you can upload it and change it in the future
Book Mockup Generator
Membrane Pro Cover Image Maker 1 0 78
Our book mockup generator takes even less time than our ebook cover creator. Use it to create mockups that instantly look like a paperback book, hardback book, ebook, dvd cover and more. To create a mockup of an existing book just select the template you would like your book to look like and then upload your cropped front book cover. This takes just less than 30 seconds from start to finish.
- Large selection of mock-up formats
- Great for authors who already have a cover
- Perfect for showcasing a realistic image of your book on your website or social media
Making your image look like a tangible product goes a long way in convincing casual browsers to become customers.
Our easy to use software creates free book mockups in less than 30 seconds. Don’t believe me? No fuss, no Photoshop just beautifully rendered free book mockups. See for yourself right above this text.
Why Use Our Free Book Mockups
Some people love cracking open Photoshop and feeling like they put hard work into something, but other would rather focus on all the other things that need to be done, like:
marketing your book
marketing your book
Our free software easily and elegantly creates realistic mockups whatever you are trying to promote. We’ve spent thousands of dollars to create the fastest and most professional mockups we’ve ever seen. They are high resolution and ready to download within seconds of uploading your cover image. These are just some of the great mockup templates you can select using our mockup software:
- paperback book mockups
- hardback book mockups
- kindle mockups
- Ipad mockups
- mobile devices mockups
- dvd case mockups
- spiral bound mockups
Alternatives to Using Our Free Book Mockups
Unfortunately our free book mockups do not allow you the ability to add a spine image to any of your books, we purposefully chose angles and renderings that make the spine unnecessary, but if you would prefer to have a product shot that highlights your book’s spine image then we also have these great Photoshop mockups that you can use for free.
How To Use The Free Book Mockups
Unless the book spine is an issue for you I am certain you will love the free book mockups created with out software. To
Membrane Pro Cover Image Maker 1 0 74
- Step 1: Select the mockup template you would most like to see your book cover rendered as.
- Step 2: Upload a high resolution book cover cropped to the front only. Also make sure that your book cover uses a RGB color profile and is not saved as a CMYK color profile.
- Step 3: Submit your cover and download your high resolution mockup on the next page.
Need a Book png or a Book with a Transparent Background?
If you are an author, publisher or product creator the chances are that you are always running into the need for your book without a background. Our mockup generator creates high-resolution book png files that are perfect for your product pages, social media and advertising efforts. Grab one of our 10 book png files with your cover image right inside!
Writing a book and sharing it with the world can be scary, it seems that everywhere we look there is someone out to judge us or leave us a poor review. Use our ebook cover creator and mockup generator to make sure your book looks amazing!