Image Classification with C# - c#

I am scanning ID cards and there are 10 types of cards that are being scanned. Assume for example 10 driver licenses from 10 different states. Can somebody guide me on what would be the easiest approach to classify them using C#?

There are some online/offline ready to use classifiers take a look:
Accord Framework
Azure Vision API
Google Vision API

I presume that in the states you have a driver number and a passport number while not a c# answer and more generic I would suggest you use OCR and look for the passport number and or driver number
You could follow something like this article on code project which would allow you to scan the documents.
https://www.codeproject.com/Articles/160868/A-C-Project-in-Optical-Character-Recognition-OCR-U
However I am not sure how you would tell the different states I would to be honest give this over to the user to select the state that they are from during the entry process.

Related

Kinect v2 SDK 2.0 How to Save Multiple Skeleton Subjects to File

My question is pretty straightforward.
I can save all streams of Kinect v2 (and Kinect v1) synchronized. If I also have skeleton for one person, skeleton information is also saved.
My issue now is that I want to save the same synchronized information (color, depth, infrared, bodyindex and skeleton), but for the maximum of 6 people.
I think this can be accomplished by one of two ways:
Solution 1) - create one skeleton file for each of the 6 people, using the ID as reference for the filename, for instance.
Solution 2) - saved all this information in one single file, as I do for the remaining streams, using again an ID before each new person.
Besides, anyone has any clue on how to "lock" each person ID using Kinect SDK 2.0?
I think it's better to create Single File for each person.Then you can alter the contents very easily.If you are adding all the details in a single file,it will make the code complex.
Personally, I would save the data under a single INI or XML file using the persons ID to create the section they are referenced by. This will help reduce the complexity of your code if you use an online library. This will allow for greater extensibility and offer you the ability to edit two profiles at once without having to open multiple files.
As for 'locking' the user to an ID, that isn't something the Kinect itself is capable of. In order to do that you would have to create an algorithm that assigns an ID based on information about the user. To create an ID with staying power you need to make your program reliably be able to assign a unique signifier based on something like facial recognition, body size, name and/or distinguishing characteristics. The ID would have to be system independent, meaning that the same ID would be ascribed to that person regardless of if the computer running the program has seen them before. This would allow you to not only keep track of someone who leaves the screen, but between systems. This, however, is very difficult to coordinate and there is very little middle ground in making a system able to know that the person walking back into frame is the same. The Kinect DOES do this, but it uses xbox accounts as its unique identifier, something that the SDK does not allow you to utilize.
(TL;DR You would have to make your own version of xbox accounts and your own identifying system for those accounts using the SDK)

How to Reverse-GeoCode an array of Lat/Longs

I am looking for the ability in C# .Net to find the address from an array of Latitudes and Longitudes. My array would have something like the following (39.96481959995778, -83.00803899765015),(39.96575701532093, -83.00681591033936). From the coordinates i would get back all the address within that area. i appreciate any help with this.
This is called as Reverse-GeoCoding. You need to use a third party webservice (free or paid) that returns the user addresses on the basis of Lat/Long. Google has one like this See this on how to use google for this purpose.GEO CODING but there are other such services as well. You find one that is right for you. If you are using it in a commercial environment i guess you will have to purchase a license for that.

How to obtain a serial number of scanner with TWAIN?

I would like to obtain the serial number of a scanner in C# using twain_32.dll.
I've found out it has to be done with dscap method with the icap_serialnumber capability.
Can anyone give me an example how to do this?
You have confirmed that your scanner driver supports this capability? I find it in the TWAIN spec as CAP_SERIALNUMBER (0x1024). And it is optional - you cannot assume that a scanner supports it.
If you get TWRC_FAILURE when you try to GET that capability, check the condition code. Your library or component should provide a way to get the condition code after the GET. A value of TWCC_CAPUNSUPPORTED would mean that the scanner driver does not support that capability. Other condition codes are described in the TWAIN specification, although sometimes a little imagination is needed to guess what the driver is trying to say...
The TWAIN Working Group forum is maybe a little better place for this kind of question.

C# - Xbox Live Stat Grabber

I'm working on an xbl stat grabber. I have a problem I dont understand how to get the "gamer card"
Heres an example : http://www.youtube.com/watch?v=6HA-uz_v6A0&feature=related
I already have the avatar but I don't get how you can grab the stats and recent games...
You need access to the Xbox Live API, I think you have to apply to Microsoft to get on their 'Community Developer' programme, although it's a bit hazy on the site as to whether they are accepting applications or not.
One kind fellow (who I think is a Microsoft employee) saw that this was a terrible oversight from his employers decided to offer as web service that plugged into the Xbox Live network so you can pull statistics down, you can find info about it and a website here: -
http://duncanmackenzie.net/Blog/put-up-a-rest-api-for-xbox-gamertag-data
It's very comprehensive and should give you all the data you need (Gamerscore, current status, last game played etc)
EDIT: Extra stuff that might help
I'm not too familiar with C# but the process of using the service would be to do the following in your application: -
Construct your URL with a/your gamertag as the argument
Use some URL/Networking API (C#/.NET must have something like this somewhere) to load the URL and retrieve the contents. This should return you a big string containing a bunch of XML
Parse the XML into your application using some sort of XML parsing API (again, I'd imagine C#/.NET has these things built into the framework)
From the looks of the program, the gamercard info looks as if it is just an embedding based upon the gamer tag. You can find info on embedding your Xbox Live gamercard here.
The video author said the Halo stat information is coming courtesy of a site called HaloCharts.com. I don't know if he is embedding the information, perhaps reading an RSS feed, or if he is extracting data from the HTML.

What is a good api for mapping gps coordinates in c#?

I have a project that has a list of gps coordinates. I would like to find a way to make a simple map of those coordinates (possibly just one at a time). The map should have basic street info.
This part of our project is pretty simple so I don't think it needs to be an exceptionally feature rich product. This also means it shouldn't be really expensive.
What is a good product to achieve this?
edit: This is a desktop app where internet connectivity will probably not be available.
Google Maps is great for this.
If this is a desktop app with internet access you could still host an IE control and show it there.
EDIT: If this is a desktop app without internet access you'll have to buy something like Microsoft Streets & Trips. I don't know if it has reusable controls. You probably have to buy something more expensive to get that. Applications of this nature often fall under the category "GIS". Try searching Google for that.
Sharpmap is open source project written in C# and released under LGPL. To quote first line from page:
SharpMap is an easy-to-use mapping library for use in web and desktop applications.
I'd go with this solution
Map Rendering: SharpMap
Geometry operations: NetTopologySuite
Map data store: shapefiles in your file system or PostGis over PostgreSQL
Map data itself: the easiest way may be extracting from OpenStreetMaps data. Here, for example you can download shapefiles for your desired location
Everyting is open source (more or less, check the licenses) and works fine on windows.
Hope it helps
ESRI has an API. They have javascript, silverlight,wpf, and flash. they may have more. ESRI is pretty much the standard in mapping.

Categories