I am currently developing a website for a client. It consists of users being able to upload pictures to be shown in a gallery on the site.
The problem we have is that when a user uploads an image it would obviously need to be verified to make sure it is safe for the website (no pornographic or explicit pictures). However my client would not like to manually have to accept every image that is being uploaded as this would be time consuming and the users' images would not instantly be online.
I am writing my code in PHP. If needs be I could change to ASP.net or C#. Is there any way that this can be done?
2019 Update
A lot has changed since this original answer way back in 2013, the main thing being machine learning. There are now a number of libraries and API's available for programmatically detecting adult content:
Google Cloud Vision API, which uses the same models Google uses for safe search.
NSFWJS uses TensorFlow.js claims to achieve ~90% accuracy and is open source under MIT license.
Yahoo has a solution called Open NSFW under the BSD 2 clause license.
2013 Answer
There is a JavaScript library called nude.js which is for this, although I have never used it. Here is a demo of it in use.
There is also PORNsweeper.
Another option is to "outsource" the moderation work using something like Amazon Mechanical Turk, which is a crowdsourced platform which "enables computer programs to co-ordinate the use of human intelligence to perform tasks which computers are unable to do". So you would basically pay a small amount per moderation item and have an outsourced actual human to moderate the content for you.
The only other solution I can think of is to make the images user moderated, where users can flag inappropriate posts/images for moderation, and if nobody wants to manually moderate them they can simply be removed after a certain number of flags.
Here are a few other interesting links on the topic:
http://thomas.deselaers.de/publications/papers/deselaers_icpr08_porn.pdf
http://www.naun.org/multimedia/NAUN/computers/20-462.pdf
What is the best way to programmatically detect porn images?
The example below does not give you 100% accurate results but it should help you a least a bit and works out of the box.
<?php
$url = 'http://server.com/image.png';
$data = json_decode(file_get_contents('http://api.rest7.com/v1/detect_nudity.php?url=' . $url));
if (#$data->success !== 1)
{
die('Failed');
}
echo 'Contains nudity? ' . $data->nudity . '<br>';
echo 'Nudity percentage: ' . $data->nudity_percentage . '<br>';
If you are looking for an API-based solution, you may want to check out Sightengine.com
It's an automated solution to detect things like adult content, violence, celebrities etc in images and videos.
Here is an example in PHP, using the SDK:
<?php
$client = new SightengineClient('YourApplicationID', 'YourAPIKey');
$output = $client>check('nudity')>image('https://sightengine.com/assets/img/examples/example2.jpg');
The output will then return the classification:
{
"status": "success",
"request": {
"id": "req_VjyxevVQYXQZ1HMbnwtn",
"timestamp": 1471762434.0244,
"operations": 1
},
"nudity": {
"raw": 0.000757,
"partial": 0.000763,
"safe": 0.999243
},
"media": {
"id": "med_KWmB2GQZ29N4MVpVdq5K",
"uri": "https://sightengine.com/assets/img/examples/example2.jpg"
}
}
Have a look at the documentation for more details: https://sightengine.com/docs/#nudity-detection
(disclaimer: I work there)
There is a free API that detects adult content (porn, nudity, NSFW).
https://market.mashape.com/purelabs/sensitive-image-detection
We've using it on our production environment and I would say it works pretty good so far. There are some false detections though, it seems they prefer to mark the image as unsafe if they are unsure.
It all depends on the level of accuracy you are looking for, simple skin tone detection (like nude.js) will prob get you 60-80% accuracy on a generous sample set, for anything more accurate than that, let's say 90-95%, you are going to need some specialized computer vision system with an evolving model that is revised over time. For the latter you might want to check out http://clarifai.com or https://scanii.com (which I work on)
Microsoft Azure has a very cool API called Computer Vision, which you can use for free (either through the UI or programmatically) and has tons of documentation, including for PHP.
It has some amazingly accurate (and sometimes humorous) results.
Outside of detecting adult and "racy" material, it will read text, guess your age, identify primary colours, etc etc.
You can try it out at azure.microsoft.com.
Sample output from a "racy" image:
FEATURE NAME: VALUE:
Description { "tags": [ "person", "man", "young", "woman", "holding",
"surfing", "board", "hair", "laying", "boy", "standing",
"water", "cutting", "white", "beach", "people", "bed" ],
"captions": [ { "text": "a man and a woman taking a selfie",
"confidence": 0.133149087 } ] }
Tags [ { "name": "person", "confidence": 0.9997446 },
{ "name": "man", "confidence": 0.9587285 },
{ "name": "wall", "confidence": 0.9546831 },
{ "name": "swimsuit", "confidence": 0.499717563 } ]
Image format "Jpeg"
Image dimensions 1328 x 2000
Clip art type 0
Line drawing type 0
Black and white false
Adult content true
Adult score 0.9845981
Racy true
Racy score 0.964191854
Categories [ { "name": "people_baby", "score": 0.4921875 } ]
Faces [ { "age": 37, "gender": "Female",
"faceRectangle": { "top": 317, "left": 1554,
"width": 232, "height": 232 } } ]
Dominant color background "Brown"
Dominant color foreground "Black"
Accent Color #0D8CBE
I'm using the wikimapia api for developing an Android application. I've used my first key for about two months but not, for any request I make I get:
{
"debug": {
"code": 1004,
"message": "Key limit has been reached"
}
}
I've created a new key, but now, for any request I make I get the same response: []
Does anybody know what the problem is?
It looks like something wrong on Wikimapi side. It returns me [] too.
There are few post about this issue on wikimapia forum
http://wikimapia.org/forum/viewtopic.php?f=4&t=14933&p=288045&hilit=empty#p288045
I'm beginning to use CloudCode but I can't find my application after authentication.
Once I enter my email account and pass I get the following:
Email:
Pass:
1: results
Select an App:
From this step nothing works (Ex. parse deploy) and I get the error msg "Unknown application _default"
I'm using the latest parse-windows.2.0.11.exe, PowerShell on Win8.1
Should CloudCode be activate on the project in order to use it? if so, how is this done?
===UPDATE===
It turns out the global.json was created wrong (bug?)
{
"applications": {
"results": {
"applicationId": {
"appName": "AppName1",
"applicationId": "zzz",
"masterKey": "zzz"
},
"masterKey": {
"appName": "AppName2",
"applicationId": "xxx",
"masterKey": "xxx"
}
}
}
}
I've manually fixed it using this thread link
Hope this will help others..
=== END UPDATE===
Please advise.
Thanks,
Liran
My experience is with Android over Linux, but from what I see the base is the same - in Linux you create a folder for your CloudCode that you reference for deployments, so when you deploy you do that from inside that folder, read carefully through This Parse Tutorial - seems pretty similar.
Even by using sample project provided in Corona SDk , I get a notification with error 400. I guess my json data is correct. Following is the code for Json message.
local jsonMessage =
[[
"registration_ids": ["]] .. tostring(googleRegistrationId) .. [["],
"data":
{
"alert": "Hello World!",
"sound": "default"
}
}
]]
This is the message on my device.
Based on the 400 error code, the problem must be your JSON :
400
Only applies for JSON requests. Indicates that the request could not
be parsed as JSON, or it contained invalid fields (for instance,
passing a string where a number was expected). The exact failure
reason is described in the response and the problem should be
addressed before the request can be retried.
With all the square brackets and html tag, it's really hard to understand from your question how your JSON actually looks like.
Anyway, here's how it should look like :
{
"registration_ids": ["some reg id"],
"data":
{
"alert": "Hello World!",
"sound": "default"
}
}
I solved this error by changing the format of my json and checking the format on this link http://jsonlint.com/# . This was a great help and also I replace alert icon by custom icon by using this:
http://developer.android.com/guide/practices/ui_guidelines/icon_design_status_bar.html
{
"German":[
"Hello",
"guten Morgen",
"gute Nacht"
],
"English":[
"Hello",
"good morning",
"good Night"
],
"French":[
"bonjour",
"bonne nuit",
"bonjour"
]
}
In Android ,I have to parse this above output. I am unable to do. can any one tell me ,does it wrong jSON output or it is correct ?
http://www.androidhive.info/2012/01/android-json-parsing-tutorial/
Its problem with your URL - saqib_abbasi.0fees.net/Response.php
Try after removing the underscore from your host name.
See the following links
https://stackoverflow.com/a/11206362/1329126
http://en.wikipedia.org/wiki/Hostname#Restrictions_on_valid_host_names
It's a valid json. So you didn't do something right.
Make a JSONObject from the whole string, then you can get the arrays with getJSONArray("German") for example.