Develop Reference

Handwriting signature detection

I'm trying to find if a scanned pdf form contains a signature (like making sure a check is signed).
The problem domain:
I will be receiving document packages (multi page pdf's with multiple forms). I have already put together document package classifiers that will check the package for all documents and scale the images to a common size. After that I know where the signatures should be and can scan the area of the document specifically. What I'm looking for is the best approach to making sure there is a signature present. I've considered just checking for a base threshold of dark pixels but that seems so clumsy. The trouble with signatures is that they are not really writing, more of a personal mark.
The only thing I can come up with is a machine learning method to look for loopyness? But I'm not all the familiar with machine learning and don't even know where to start with something like that. Anyone with some suggestions for practical approaches would very appreciated.
I'm coding this in Java if that's helpful at all

What you asked was very broad so there isn't a lot of information that we can give you. However, I can point you to some helpful links:
http://java-ml.sourceforge.net/ --This is a library that you can download that has lots of useful algorithms and other code to include in your program
https://www.youtube.com/playlist?list=PLiaHhY2iBX9hdHaRr6b7XevZtgZRa1PoU --this is a series that explains neural networks (something you might want to look into for your machine learning)
So a big tip I have for your algorithm is to instead of looking for how long exactly all of the loops and things are, look at all of their relative distances
"Relative distances from what?" you say. Well this is where the next tip comes in handy: instead of keeping track of the lines, keep track of the tips of the loops and the order of these points. If you then take the distance between all of them (relatively of course which means to set one of the lengths to zero). Along to keeping track of the distances, you should also keep track of the angles. You would calculate the angle ABC by taking the distance between (A,B), (B,C), and (A,C) (A,B, and C being coordinates on the xy plane) which creates a triangle between the points which allows you to use trigonometry to calculate the angle.
(I am assuming that for all of these you are also trying to detect who's signature it is of course because it actually doesn't really complicate things much at all) When trying to match up the signature detected to the stored signatures to see if they are the "same," don't make it to where the distances and angles have to be exact. Give a margin of error (like use a % range above and below). Here is a tip: Make the margin of error rather large. That way if it is written poorly, it will still be detected. This raises the chances of more than one signature being picked up. Luckily, there is a simply solution to this. Just have it run the algorithm again on the signatures that were found but with the margin of error smaller (you of course don't do this manually, the program does it). Continue decreasing the margin of error until you get only one signature remaining.
I am hoping you have ideas already for detecting where the actual signature is but check for the difference in darkness of the pixels of course. Make sure it is pretty continuous. Also take note of the fact that signatures are commonly signed in both black or blue or sometimes red and other fancy colors.

Vehicle Routing with Traffic Jam

I was building a prototype of vehicle routing application using google maps and optaplanner. I change the distance based scoring to duration based scoring, where the duration value was calculated using distance / avg speed of vehicle.
Now I want to add traffic jam variable into my application. The traffic jam variable was implemented as additional duration value from the current location to another location (I using a map of location and double just like distance variable in RoadLocation class). When I tried it to run it, the result was always same with the previous one. Here is the result from the first run :
I draw some red line to represent the traffic jam, and then try to re-run the solving phase. Here is the second result:
The result was the same with the previous one. My questions is, what the best method to apply the traffic jam variable into vehicle routing problem? Does anyone has any experience adding this variable? Any comment and suggestion will be appreciated.
Thanks and regards.

This paragraph is just an introduction. If you wanna skip it, do it. ;-)
I have implemented a similar approach with traffic jams, but it was not a real-time system. The solution runs every X minutes, which is absolutely fine.
That gave me the benefit for pre-calculating the ways and routes for the complete road network, before the actual optaPlanner calculation starts.
This saves time for the real calculation of optaPlanner.
The network consists of vertexes and arcs. For each arc you'll have a weight.
Here starts the real deal for you.
Let's assume that you implement a Dijkstra or A-Star algorithm for the precalculation step for all places and how to get there. These way finding algorithm is seleting the arc with the lowest "travelling" costs. For each arc/road, which would be blocked, we assume a distance of DOUBLE.MAX_VALUE. This value can be interpreted as "not driveable" or drastically said: This connection between two vertexes even doesn't exist for the current solution finding process. So the way finding algorithm will simply skip this road. For every driveable road, we calculate the real costs, e.g. distance or take an approximation out of experience.
The optaplanner process itself just uses the precalculated way finding mechanism, e.g. compares the calculated distances for getting from place A to place B.
For setting the distance variable to DOUBLE.MAX_VALUE you can decide between user based information, information of other providers like google or admin based rules. As my experience goes along with user based content vs. admin based actions, I can recommend both ways.
Let's discuss the user based action: The user can have the same set of GUI actions as the admin for flagging a way as "jammed". For the next optaPlanner iteration the flag is going to be involved. If you have GPS data of your users you can get the approximate velocity. For each intervall of the GPS measurement you can calculate that velocity. If the velocity is on a road (not a crossing), and below a defined minimum velocity (let's say 1mph or 2 kmh), then you can ask the user if it's a traffic jam or not via popup OR block that road automatically without asking the user. If you chose the popup dialog then a lot of different users have to vote "yes" within a defined time slot, e.g. half an hour, then the road get's blocked. You can resolve the traffic jam, when a lot of users drive the road again and send the GPS coordinates of that road.
The main advantage of the automatic approach is, that you'll have a system based approach with a low error rate.
If you take the manual approach via admin, then you have to take care of implementing a GUI for displaying the roads and enabling/disabling the blocked attribute for a road.

Video and audio analysis in Java

I would like to do some audio and video analysis in Java.
In a bit more detail, I would like to identify the points in audio/video that have either been monotonous for quite some time or have drastically changed compared to some previous state.
If you want to look at it in a mathematical way, I can try to explain it like this:
Example:
You have an audio file. You should extract the waveform of that
audio file. You could try to approximate that waveform with some
simpler function, that can be expressed as a closed formula. Let's
call that function f(t).
Now, to find out how your function behaves (is it increasing or decreasing) at some point or interval, I guess I could use the first derivative,f'(t). If I'd like even more information, I assume second derivative, f''(t) would also come in handy.
So, if we assume we can do that then I guess I'd have 1 piece of information about the audio.
However, if I'm not mistaken, audio files can also have spectrograms, so I'm unsure how they fall into all of this.
So, the real question goes here: Is there a way to do this in Java (efficiently)? I've been doing some digging and I've found MusicG, however, the last update date is July 2012, which leads me to believe this may be abandoned.
The second part refers to video files, but without their audio component.
This is where I'll have more questions, so I'm just gonna go and shoot them.
How do you identify points of change in "pace" in videos?
Here's an example:
Imagine the video shows car driver's point of view while he's driving
on a long, straight road. Since the surroundings are mostly the same,
the pace could be described as "not changing much". At one point, the
road begins to curve but the driver, due to him falling asleep" is not
following the road that precisely, so the surroundings start to change
somewhat, and so does the pace. At the apex of that curve there is a
tree, which grows bigger and bigger as the car is approaching it.
Here, the POV (and the pace) is changing quite a lot, since the tree
is getting bigger and bigger. In the end, the car crashes into a tree,
all hell breaks loose, the car starts to roll uncontrollably, which
indicates a really intense pace.
I'm assuming one way could be to do an image segmentation and somehow determine which portions of the frames are changing, and how big are those portions to try to determine pace, but I'd like additional input.
If anyone has had prior experience doing any sort of related work in Java, what approaches did you explore and/or use? One thing that immediately comes to my mind is JavaCV, but as I said, with my limited experience, I'm unsure what to actually try.

Beat Matching Algorithm

I've recently begun trying to create a mobile app (iOS/Android) that will automatically beat match (http://en.wikipedia.org/wiki/Beatmatching) two songs.
I know that this exists out there, and there have been others who have had some success, but I'm running into issues related to the accuracy of the players.
Specifically, I run into "sync" issues where the "beats" don't line up. The various methods used to date are:
Calculate the BPM in advance, identify a "beat" (using something like sonicapi.com), and trying to line up appropriately, and begin a mix in with its playback rate adjusted (tempo adjustment)
Utilizing a bunch of meta data to trigger specific starts and stops
What does NOT work:
Leveraging echonest's API (it beat matches on the server, we want to do it on the client)
Something like pydub (does not do it in realtime)
Who uses this algorithm today:
iwebdj
Traktor
Does anyone have any suggestions on how to solve this problem? I've seen lots of people do it, but doing it in real time on a mobile device seems to be an issue.

There are lots of methods for solving this problem, some of which work better than others. Matthew Davies has published several papers on the matter, among many others. Glancing at this article seems to break down some of the steps necessary for doing this. I built a beat tracker in Matlab (unfortunately...) with a fellow student and our goal was to create an outro/intro between 2 songs so that the tempo was seamless between them. We wanted to do this for songs that varied in BPM by a small amount (+-7 or so BPM between the two). Our method went sort of like this:
Find two songs in our database that had overlapping 'key center'. So lets say 2 songs, both in Am.
Find this particular overlap of key centers between the two. Say 30 seconds into song 1 and 60 seconds into song 2
Now create a beat map, using an onset-detection algorithm with peak picking; Also, this was helpful for us.
Pick the first 'beat' for each track, and overlap the two tracks at that point. Now, since they are slightly different BPM from each other, the beats won't really line up with each other.
From this, we created a sort of map that gave us the sample offsets between beats of song A and beats of song B. From this, we wanted to be able to time-stretch the fade-in region of song B so that each one of its onsets (beats in this case) lined up at the correct sample index as the onsets from song A, over ITS fade-out region. So for example, if onset 2 from song B was shown as 5,000 samples ahead of onset 2 from song A, we simply stretched that 5,000 sample region so that onset 2 matched exactly between both songs.
This seems like it would sound weird, but it actually sounded pretty good. Although this was done entirely offline in Matlab, I am also looking for a way to do this in real-time in a mobile app. Not entirely sure about libraries you can use for this in Android world, but I imagine that it would be most efficient in C++.
A couple of libraries I have come across would be good for prototyping something, or at least studying the source code to get a better understanding of how you could do this in a mobile app:
Essentia (great community, open-source)
Aubio (also seems to be maintained pretty well, open-source)
Additional things to read up on for doing this kind of stuff in iOS land:
vDSP Programming guide
This article may also help
I came across this project that is doing some beat detection. Although it seems pretty out-dated unfortunately, it may offer some additional insights.
Unfortunately it isn't as simple as just 'pressing play' at the same time to align beats, unless you are assuming very specific aspects about them (exact tempos, etc.).
If you reallllly have some time on your hands, you should check out Tristan Jehan's (founder of Echonest) thesis; it is jam packed with algorithms and methods for beat detection, etc.

Android Algorithm for find all Geopoints within a given distance

In my naive beginning Android mind I thought the way to do this would be to loop through each of the objects checking if proximity falls within X range and if so, include the object. This is being done with Google Maps and GeoPoints.
That said, I know this is probably the slowest way possibly. I did a search for Android Proxmity algorithm's and did not get much really. What I am looking for is best options with regard to this the more efficiently.
Are there any libraries I have not been able to find?
If not, should I load these Location objects into SQL then go from there or keep them in a JSONArray?
Once I establish my best datastructure, what is he best method to find all Locations located with X miles of user?
I am not asking for cut and paste code, rather the best method to this efficiently. Then, I can stumble through the code :)
My first gut feeling is to group the Locations by regions but I'm not exactly sure how to do this.
I could potentially have tens of thousands of datapoints.
Any help in simply heading in the right direction is greatly appreciated.
As a side note, I reach this juncture after discovering that a remote API I had been using was.. well.. just PLAIN WRONG and ommiting datapoints from my proximity search. I also realized that if just placed on the datapoints on the phone, then I could allow the user to run the App without internet connection, and only GPS and this would be a HUGE plus. So, with all setbacks come opportunnities!

The answer depends on the representation of the GeoPoints: If these are not sorted you need to scan all of them (this is done in linear time, sorting wrt. distance or clustering will be more expensive). Use Location.distanceTo(Location) or Location.distanceBetween(float, float, float, float, float[]) to calculate the distances.
If the GeoPoints were sorted wrt. distance to your position this task can be done much more efficiently, but since the supplier does not know your position, I assume that this cannot be done.
If the GeoPoints are clustered, i.e. if you have a set of clusters with some center and a radius select each cluster where the distance from your position to the cluster's center is within the limit plus the radius. For these clusters you need to check each GeoPoint contained in the cluster (some of them are possibly farther away from your position than the limit allows). Alternatively you might accept the error and include all points of the cluster (if the radius is relatively small I would recommend this).