I'm looking for a desktop search engine for finding images on my local hard drive with high visual similarity. I've only found paid for ones so far. It could be Linux or windows one, either would be helpful.
A Google desktop plug-in would be nice!
Super User is a question and answer site for computer enthusiasts and power users. It only takes a minute to sign up.Sign up to join this community
dupeGuru PE. Plus it's open-source. :)
dupeGuru Picture Edition (PE for short) is a tool to find duplicate pictures on your computer. dupeGuru PE is a big brother of dupeGuru. It works like dupeGuru, but is specialized for duplicate pictures matching. dupeGuru PE runs on Windows, Mac OS X and Linux.
dupeGuru PE is efficient. Not only can dupeGuru PE find exact matches, but it can also find duplicates among pictures of different kind (PNG, JPG, GIF etc..) and quality. On Mac OS X, dupeGuru PE can scan your iPhoto library.
dupeGuru PE is customizable. You can tweak its matching engine to find exactly the kind of duplicates you want to find. The Preference page of the help file lists all the scanning engine settings you can change.
dupeGuru PE is safe. Its engine has been especially designed with safety in mind. Its reference directory system as well as its grouping system prevent you from deleting pictures you didn't mean to delete.
Compare any picture format. dupeGuru PE supports JPG, PNG, TIFF, GIF and BMP formats. All these formats can be compared together. The Mac OS X version of dupeGuru PE also supports PSD and RAW (CR2 and NEF) formats.
Your iPhoto and Aperture libraries are supported.
Do whatever you want with your duplicates. Not only can you delete duplicates files dupeGuru finds, but you can also move or copy them elsewhere. There are also multiple ways to filter and sort your results to easily weed out false duplicates (for low threshold scans).
6 more apps that do the job:
Duplicate images often find their way into collections, even commercial stock collections. Now you can clean them of duplicates and near duplicates. Search a folder (including subfolders) for duplicate and near duplicate images. Match all images or restrict match to same size or same aspect ratio. Dup Detector creates a data file by opening and reading image pixel data for each image in your collection. It then finds duplicates by % match and displays matching pairs from a log file. You may delete a duplicate at any time.
Supports 9 image file formats (jpg, bmp, png, tif, pcx, tga, wmf, emf, psp).
This freeware version requires all images to be in one folder (or subfolders).
(MFC42.dll must exist on your system).
This application can search through your images collection and find duplicates not only by file name or size, but also by visual similarity.
It done by implementation of some public domain algorithm to do its work.
DoubleKiller searches single or multiple directories for duplicate files by comparing any combination of file name, size, modification date and content. Using user-defined masks like *.mp3 or *.dll you can limit the scan to files that interest you or protect important files from being scanned. Furthermore you can exclude files in a particular file size range or files with certain attributes, like hidden or system files.
When the scan is finished a list containing all duplicates found is displayed and you can manually or automatically select the files to be removed. The result list can be sorted and exported to a textfile readable by both humans and spreadsheet applications.
DoubleKiller is a stand-alone executable that does not need to be installed, just extracted and run, and does not alter the system in any way without the user's prior permission.
VisiPics does more than just look for identical files, it goes beyond checksums to look for similar pictures and does it all with a simple user interface. First, you select the root folder or folders to find and catalogue all of your pictures. It then applies five image comparison filters in order to measure how close pairs of images on the hard drive are.
Visipic is a program that is considerably faster than any other commercial product and has an interface that let you do other things while Visipics automatically finds your duplicated images. It will detect two different resolution files of the same picture as a duplicate, or the same picture saved in different formats, or duplicates where only minor cosmetic changes have taken place.
All detected duplicates are shown side by side with pertinent information such as file name, type and size being displayed. Its auto-select mode let you choose if you want to keep the higher resolution picture, space-saving filetype, smaller filesize or all of the above. If you are insecure over what you really want to delete you can manually select the images you don't want to keep and delete them yourself.
SimilarImages is a utility program to analyze and search large media collections (images/videos) for near duplicates, meaning media showing the same thing but e.g. in different file formats, compression levels, sizes. SimilarImages first analyzes a file, generating a color/location footprint of a normalized thumbnail image of a file, and then compares these footprints. Analyzation results will be cached and stored on disk, so that subsequent runs become faster.
The program ImageDupeless is intended for search/find of the similar images (duplicates) in the large collections. The supported graphic file formats are JPEG, GIF, BMP, PCX, PNG, TIFF, PGM, WMF, EMF, EPS, PSD, ICO. The comparison is based on the contents of images, not depending on their sizes, formats, resolutions, etc. There are advanced opportunities of cataloging the galleries available on CDs and of further off-line work with them. At that the comparison of new images with those of included into the gallery takes much less time, than complete rescanning the gallery, and is possible even if the CD itself with imaging data is absent. There are internal facilities for comparison, deletion (including groups of images), movement, and update of files, change of root directory binding for the gallery.
Tineye image search has a plugin.
For a local CBIR engine, there are a couple out there. From the makers of Tineye is Pixmatch!!
While it requires you to upload images and have it scan it, it is actually very accurate.
A local version would be Octogan. It's not that accurate.
While googling, this page did catch my eye. I'm having it index my picture collection currently. It looks promising.
It has two parts. Caliph is the indexer. Emir is the query engine. Nice play on names huh?
http://www.imgseek.net It's a gnome app (for linux) that search images using visual similarity among other things. I used it widely and is pretty accurate, and you can manage the threshold of the search. If you don't find any windows native alternative, you probably wanna try to port it using gnome for windows.
Mark Tyler wrote an image differencer as a test program for mtpixel ( spin off from mtpaint, which is @ sourceforge ). Mtpixel is now developed as part of mtcelledit (a light gtk2 spreadsheet app on Google code )
You may have better luck with one over the other.
Iirc it only does 2 images at a time, so you'd need to script the file finding.
Reasonable NoClone 2013 Duplicate Find Finder can find similar images regardless of size, cropped，modified.
Google has a new service here: http://www.google.com/imghp?hl=en&tab=wi
In Chrome (and some other browsers but not all) click the camera icon on the right hand end of the search field to open the dialog.