I know how to use already made haarcascades for face,eyes detection etc. But I wanted to create a haarcascade to recognize a ceiling fan(both when it is turned ON or OFF). Can anyone give me some good suggestions on how can I make such a haarcascade?Thanks in advance!
I followed this video and made Haarcascades for bikes and heavy vehicle detection and it was helpful
SentDex Making our own HaarCascades
Related
Im really new to machine Learning.I have a project to identify a given sound.(Ex: cutting wood)In the audio clip there will be several sound. What i need to do is recognise that particular sound from it. I red some articles about machine learning. But i still have lack of knowledge where to start this project and also I'm running out of time.
Any help will be really appreciated. Can anyone please tell me how to do this?
Can i directly perform template(algorithms) matching for a sound?
It's a long journey ahead of you and Stack Overflow isn't a good place for asking such a generic question. Consult help section for more.
To get you started, here are some web sites:
Awesome Bioacoustic
Comparative Audio Analysis With Wavenet, MFCCs, UMAP, t-SNE and PCA
Here are two small repos of mine related to audio classification:
Gender classification from audio
Kiwi / not-a-kiwi bird calls detector
They might give you an idea where to start your project. Check the libraries I am using - likely they will be of help to you.
I am trying to create an amazon webstore and the interface is just appalling.
I have seen a few companies that have made really decent stores but have no idea how they have accomplished this using the interface amazon give you as they make it near on impossible to customise a single thing.
Could someone please shed a light on what it is I need to do to create a fully customised design for my store?
Thanks in advance.
I have had luck in creating a custom layout... functionality is where I'm stuck. It seems we are FORCED to use their widgets, etc... though you can change the look of them quite easily.
I made my way by using Google Chrome's inspect element tool (F12). I was able to find the CSS that drives the different widgets for width, height, etc. Also, I was able to write my own CSS for, say, the search widget.
Your question is about 1.5 months old... so I assume you may have learned your way by now.
If you have any questions, I'd be happy to assist with what I know.
I have an alphabet which has not been tackled before, so when scanned, there's no way to detect the letters for recognition with OCR. I'm trying to program OCR for it, but don't have much experience in this. I'd appreciate some hints as to where to get started, and how such a system is normally implemented.
Take a look at this page--it describes the training process for an open source OCR engine.
The free Stanford Online Machine Learning class has a great set of lessons on Photo OCR in Part XVIII.
This blog post has a brief description of the example taught in the class.
There are some excellent resources at google books. Likewise, if you search for Optical Character Recognition on Amazon, there are some pretty up-to-date books that look to be fairly thick and intellectually challenging :D heh
btw - I'm well aware this post has some age, but you never know when some other person might stumble across this and find just what they need. And if this even has the chance of helping out, then so be it. OCR is such a strange subject, that there's not too much out there that can really really answer the deep-machine ended questions. Especially if you're going to attempt to write your own library. :P
I am looking for some advice on categorizing a library of sound effects. I have a large set of random sound effects, (think whistles, pops, growls, creaks, gunshots etc). I would like to be able to take a growl for example, and find the next growl that sounds the closest to the original.
Given a sound, what sound from my set sounds the closest to it.
I have done a fair amount of googling and have found two avenues that I am still researching. One is using echonest, although their "best match" support looks not promising for public users. The other option is diving into FFT and building my own matching algorithm. This is a fine option and would be a great learning experience but I wanted to get some opinions from others who might know a little more about sound processing; especially short clips .5sec - 3sec range, not full length music.
Thanks!
I have worked in movie postproduction for years and as far as I know, there is no way to do that automatically. Every file has meta information in its file header which describes what the sound is like. You are then actually not searching for the file names but in the meta string.
I don't think that it is trivial to sort effects programmatically as two effects that sound similar might be totally different if you look at the waveform.
You would need to extract significant information about a sound that you can then compare.
I am also not a DSP expert, maybe there are methods to do this
If you're interested in trying to build your own system to do this, I can suggest a few keywords that might help to refine your Google searches. In the academic research community, the task you're describing is often called "content-based audio searching". I know there's been a lot of work done on it, and though most pertains to music, sound effects have definitely been the focus of a number of studies.
You might want to start with the work of Pedro Cano.
Also, I recently heard about a company that's doing similar work. You might want to check out products from Imagine Research.
Those are just a couple of ideas off the top of my head. I'm not %100 sure they'll be helpful. If they are, please let me know!
How do you determine which onsets are beats? I am using Spectral Flux for Note Onset Detection and a Running Mean for peak-picking/thresholding.
I am just working with the guitar instrument so the presence of percussions may not help with this. Any ideas?
Thanks!
EDIT: Wow...just realized this question is 3 years old...sorry to resurrect an old post.
My Master's thesis was in beat detection and the main advantage of my method over all other published methods of beat detection was in resolution, both in the time domain and frequency (beat) domain. You can find my thesis here. What it basically boils down to (after alot of filtering) is a comb-filter convolution. My code is an adaptation of this project, which contains Matlab files for you to see how it works.
My code (both in C++ and the Matlab port) is not publicly available due to possible copywrite issues with my university, but if you email me at dberm22[at]gmail[dot]com, I'd be more than willing to ahem::discuss my work with you.
Try using a beat tracking algorithm. Beat tracking is a distinct problem from onset detection.
I think there's a good algorithm in the Queen Mary plugin set for Sonic Visualizer. The plugins are open source, so you can have a look at the code to figure out how they work.
Or do a search on google scholar for "beat tracking". There are a number of effective approaches. Dan Ellis' is a good one to start with. It's intuitive, and there's code available in Matlab and Java.