I need to build an image classification model in Azure ML- which initially takes an input from Phone (A check in app which takes information like ID and also we will capture the image of the person- Here ID is used to tag the image) which will be redirected to data storage. once it's done, we will upload the n number of images of person to the data storage, it should able to classify the image based on facial recognition and should categorize as separate image folder for different person( Just like Google Photos). In short, If there's a 100 unique people come for check in and during the event if we click random images of these 100 unique persons, when we load this data to blob - it should categorize the persons separately.
Can I go with approach-
1.Check in app-- Loads image with tag
2.Blob- store the image
3. custom vison- ML classifier
4.Loding n number of images to blob
5. comparing the image with check in app loaded image and categorizing as album just like google photos
6. Loading albums to app to make attendees to see the images
Please guide me with the solution and services need to be considered to make this possible in azure
Thanks in adavance
Within Azure you need to look into Cognitive Services, with more information located here: https://azure.microsoft.com/en-us/services/cognitive-services/
Azure Cognitive Services is substantially surfaced as a series of API endpoints. In your example, you can post images from the mobile device to the Azure endpoint, where you can train the services to recognize individuals and have it return a JSON package of the people in the picture, or have it place rectangles around those people in a picture, etc. Other Cognitive Services include those related to images, speech, video, etc.
The Face API maps to your scenario well: https://azure.microsoft.com/en-us/services/cognitive-services/face/
https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/#overview
Related
Sometimes the Web Detection API is not able to detect multiple objects in an image, hence I'm considering using Object Localiser. But Object Localiser essentially returns the bounding box co-ordinates (as shown in the documentation example). So how can I take the results from Object Localiser and send to Web Detection API so that I can get a list of individual web entities/products?
It's basically similar to the use case 'Vision Product Search' mentioned on the Cloud Vision landing page except would want to reference products indexed by Google instead of our own products.
I want to use Firebase Analytics in my website in order to get some statistics for the visitors of each page (I don't want to track user journey in the site). I wanted to define multiple data streams (one for each url) in my google analytics dashboard, but then it warned me with the following message:
In most cases, a single web stream will meet your measurement needs. Using multiple web streams to measure different pages or sites in a single user’s journey may lead to inconsistent results.
in my case-where I want to see the statistics of my site based on its pages (urls)-should I define multiple data streams?
As the message says, it is not necessary to split based on the path in the web site.
You can in the Google Analytics console instead filter based on that path. This gives you the best of both worlds, as you can show stats for a specific path, but also for the site in its entirety.
I ended up using separate data streams in a similar situation where we had a multilingual site with a domain-per-language. The analytics dashboard lets you separate the data by domain, but the tools are bulky and don't seem available everywhere.
In short, creating a separate stream for data that is always going to be viewed separately can be a real convenience, even if it's not "the right way".
The main caveat from the data-streams documentation seems to be that you can miscount data. For instance, a user switching from the English site to the French site will be counted as a visitor on each rather than as a single visit. As long as you're aware of the data implications, you should be okay.
Bing returns banner information including an image and birth date at the top of the search results when you enter a search such as 'Lady Gaga birth date'.
I would like to access this information using Microsoft Cognitive Services for an app using celebrity ages.
When I examine the httpResponseMessage return from the cognitive services call I can't find the image or birth date that appear on the top of the search results page in the body of the return.
Can you point me in the right direction to get this information from a cognitive services call. Similarly, I'd like to be able to access the summary information that appears on the top right of the search results. Any links to advanced documentation or samples on using the cognitive services Bing web search API would also be appreciated.
Thank you for you help.
Those blocks are all custom. It's less about cognitive services and more about tapping into data, translating and creating a presentation.
If you go to the Bing Web Search API site. There select "seattle seahawks" with Response Filter images. You can see that there is some text(name) and a contentUrl. You could write a parser for this to process into the pages.
Although the more logical choice would be actually calling the Bing website or Wikipedia directly. And parsing that result. As you already know it contains the information you want.
I'm testing this microsoft cognitive service and this is awsome!
By now I'm developing a simple WPF GUI to manage groups and person.
I can careate and retreive groups and its persons but I cant get the images I've already uploaded.
I'm using this https://dev.projectoxford.ai/docs/services/563879b61984550e40cbbe8d/operations/563879b61984550f30395240 function to get the face/image but the only response is the persistedFaceId.
Is there a way to retreive the person's images?
The Face API does not provide such a feature, unfortunately. Your application would need to maintain this information.
I found this site
http://www.shutterfly.com/documentation/api_OrderImage.sfly
but there are no examples of actually walking through the whole process. Does anyone have any good documentation on using this API to take a local photo and allow someone to order a print via shutterfly?
I went through these steps:
Sign up for an account
Sign up as a developer
Create an application (I called mine Test). Note the generated Application Id and Shared Secret
The Shutterfly API page has a list of references for various Domain-specific APIs:
Address Book
Album Data
Folder Data
Go To Shutterfly UE
Image Upload
Interactive Sign-in
Image Request
Order
Pricing
Seamless Sign-in
User Data
User Authentication
Each uses RESTful principles. The documentation looks pretty comprehensive to me, if you need some background, here's links for RESTful APIs and ROME you may find useful
There is also an API Explorer section on the same page that allows you to test the methods via a form on their site. For example this form for CRUD operations on the album data.
Based on your comment, for your requirements, you would:
Use the Album GET to list albums, then get the data for a specific album.
Use the Image Get request to retrieve the image data, so your friend can verify the image(s) they want to purchase.
Authenticate the user
Use the Pricing POST request to get the estimated pricing for the image.
User the Order POST to submit the order over https
Update: Found a page describing using a Greasemonkey script which adds Shutterfly print ordering capability to Flickr. This might provide the basis for a solution.
For Reference:
The original link above is a middle step of the Shutterfly Open API ordering procedure.
The whole process goes through a series of steps allowing you to control much more than just pushing photos into somebody's album in Shutterfly.
With this process, your application can actually carry out the entire procedure of:
specifying the images and the sizes and quantities, or other products
calculating shipping, taxes, and totals
paying, and
launching the processing
It also includes the ability to see when the packages will be delivered and arrive.
Thus if you have a solid application for mapping your images onto paper and products, you can pretty much control the entire process.
Once the order is submitted, it will appear on the user's account at Shutterfly who the order was associated with.
Kudos to Shutterfly for making such a powerful tool! It would be great if other printing facilities had similar tools.