Wondering, how do I recognize if an image contains a specific object and this object is completely visible (not partially).
Cognitive Services Computer Vision API provides set of tags and description of the image I send, however, there is no information if object is completely or partially represented.
My goal is to have a service that I can upload a picture of, say, car, and get information is it a full car visible or just part of it.
Unfortunately the Computer Vision API is currently unable to perform such a function.
The tags returned do have a 'score' which represents the confidence that this item is in the image. You may find there's some correlation between the confidence and how much of the item is in the image, but you'd need to run some experiments to see how well it matches up. If the object is obscured too much, it may not even detect it all.
Feel free to drop a suggestion on our User Voice, if you think this would be a useful feature.
Related
I am currently using Microsoft Academic's datadump for a project and unable to identify the total number of theses & dissertations(T&D) present. Based on their website, 38% of data is categorised to OTHERS type (one among them is T&D). But their 60+GB CSV dump doesn't explicitly indicate the T&D records. Can someone help me with the statistics for T&D or how find the same?
I tried their API too and unable to find using their API too.
The Microsoft Academic Graph does not explicitly segment publication sub-types by thesis or dissertations, which means that neither the API or website will either.
If this is something you'd like to see added, please let them know by using the "Feedback" link in the lower-right corner on the Microsoft Academic website.
I want to use dataset at https://ingmec.ual.es/datasets/lidar3d-pf-benchmark/ in my project. The available map is .simplemap. What I understand is it stores both map and the robot poses as well. I want to get the point cloud representation of this map (which later I can convert into octomap) as well as vehicles ground truth pose in the map.
I have been able to get the CPose3DPDF from which I obtained CPose3d which I believe is the desired vehicle's ground truth pose. Please correct me if I am wrong. Now I have two problems. First the length of trajectory is just 97 which makes me suspicious about my code to obtain it. Second is about the CSensoryFrame which I obtain along with CPose3DPDF. When I get CObservation by doing CSensorFrame->getObservationByIndex and write to a file, it gives me idea that it stores velodyne readings. But I am unable to recover point cloud from it. Could anyone please guide me to a tool which can convert a .simplemap into a point cloud or an octomap representation and obtain vehicle's pose out of it as well. Many thanks in advance.
For the records: this one was answered here:
Your assumptions were all correct.
I realized the full UAL campus map was not included into the downloads. It's now available to download inside 2018-02-26-ual-campus-map.zip, at the bottom of this dataset page.
You can also regenerate the pointcloud, octomap from the .simplemap using the app application-observations2map.
Example .ini files can be found under MRPT/share/mrpt/config_files/*
You can also visually inspect .simplemap files with the robot-map-gui app.
I have 20,000 messages (combination of email and live chat) between my customer and my support staff. I also have a knowledge base for my product.
Often times, the questions customers ask are quite simple and my support staff simply point them to the right knowledge base article.
What I would like to do, in order to save my support staff time, is to show my staff a list of articles that may likely be relevant based on the initial user's support request. This way they can just copy and paste the link to the help article instead of loading up the knowledge base and searching for the article manually.
I'm wondering what solutions I should investigate.
My current line of thinking is to run analysis on existing data and use a text classification approach:
For each message, see if there is a response with a link to a how-to article
If Yes, extract key phrases (microsoft cognitive services)
TF-IDF?
Treat each how-to as a 'classification' that belongs to sets of key phrases
Use some supervised machine learning, support vector machines maybe to predict which 'classification, aka how-to article' belongs to key phrase determined from a new support ticket.
Feed new responses back into the set to make the system smarter.
Not sure if I'm over complicating things. Any advice on how this is done would be appreciated.
PS: naive approach of just dumping 'key phrases' into search query of our knowledge base yielded poor results since the content of the help article is often different than how a person phrases their question in an email or live chat.
A simple classifier along the lines of a "spam" classifier might work, except that each FAQ would be a feature as opposed to a single feature classifier of spam, not-spam.
Most spam-classifiers start-off with a dictionary of words/phrases. You already have a start on this with your naive approach. However, unlike your approach a spam classifier does much more than a text search. Essentially, in a spam classifier, each word in the customer's email is given a weight and the sum of weights indicates if the message is spam or not-spam. Now, extend this to as many features as FAQs. That is, features like: FAQ1 or not-FAQ1, FAQ2 or not-FAQ2, etc.
Since your support people can easily identify which of the FAQs an e-mail requires then using a supervised learning algorithm would be appropriate. To reduce the impact of any miss-classification errors, then consider the application presenting a support person with the customer's email followed by the computer generated response and all the support person would have to-do is approve the response or modify it. Modifying a response should result in a new entry in the training set.
Support Vector Machines are one method to implement machine learning. However, you are probably suggesting this solution way too early in the process of first identifying the problem and then getting a simple method to work, as well as possible, before using more sophisticated methods. After all, if a multi-feature spam classifier works why invest more time and money in something else that also works?
Finally, depending on your system this is something I would like to work-on.
I was wondering how does Nike website make the change you can see when selecting a color or a sole. At first I thought they were only using images and when the user picked a color you just replaced that part, but when I selected a different sole I noticed it didn't changed like an image it looked a bit more as if it was being rendered. Does anybody happens to know how this is made? Or where can I get further info about making this effect :)?
It's hard to know for sure, but my guess would be that they're using a rendering service similar to that provided by Adobe's Scene7.
It's a product that is used to colorize/customize a base product image based on user choices.
If you're interested in using the service, I'd suggest signing up for their weekly webinar. I attended one a while back and was very impressed with their offering. They showed the Converse site (which had functionality almost identical functionality to the Nike site) as a demo.
A lot of these tools are built out in Flash using a variety of techniques:
1) You can use Flash's BitmapData object to directly shift the hues of the pixels in your item. This is probably the simplest technique but often limits you to simple color transformations.
2) You can pre-render transparent PNG's (or photos, I guess) containing the various textures you would want to show on your object (for instance patterns or textures) and have them dynamically added to your stage at runtime. This, I think, offers the highest fidelity but means you need all of your items rendered upfront.
3) You can create 3D collada files and load them via a library like Papervision3D. Then dynamically change the texture at runtime. This is the most memory intensive technique and tends to result in far worse fidelity, but for that you get a full 3D object that you can view in space.
I'm sure there are other techniques but those are the top 3 I can think of. I hope that helps!
I read here that when sending an image for print it can have multiple color profiles assigned to it, which will cause a difference in color between what is displayed on your monitor and what is printed on your printer.
I was wondering if there were any tools and or libraries that can detect what "stacked" color profiles have been assigned to the image.
That isn't very well written and it would seem as though you've misunderstood it completely. With the possible exception of device link profiles (which almost nobody uses) you're not very likely to ever encounter any document with more than one ICC profile embedded in it. There is absolutely no way to programmatically determine whether or not the profile that is there is the "correct" one unless its a picture of a color target with known values, and there certainly isn't any way to tell how many conversions an image has gone through.
Actually, I take that back; you will find PDFs with multiple profiles. Just not single images.