There were a couple of things I noticed about text detection using Mobile Vision: Our plan of attack was to extract every single line of text in the poster, and then figure out what each of those lines meant. It can be entire blocks of text, lines, words, and so on. The library is capable of providing us text in whichever format we desire. Text detection, which is what we wanted.Speaking of which, you might want to read this excellent introduction to Glide. I had to resort to 3rd party websites to figure out certain use-cases. It also handles annoyances like centering your images properly into your ImageView.ĭocumentation for Glide could have been better. There is a library called Glide which handles the complexities associated with pulling multiple images into your app.
JUST CALENDAR APP ANDROID
The Android documentation (precisely this page) pointed me to solutions for both these problems. You have to fiddle around with a Bitmap object and make non-trivial mathematical calculations. Centering images within the cards was harder than I thought.The high-resolution images take up a lot of memory, causing the scrolls to jitter.That’s where I ran into my first major set of problems: However, I wanted to display all the images taken by the app in vertically scrolling cards. The prototype worked well, and we decided to proceed with the main app.Ĭapturing the image and saving it on the phone was easier than I thought. For this, we built a small toy-app to detect text from images we hard-coded into the app. We didn’t want to discover at the last moment if Mobile Vision wasn’t up to the task. Next up, we wanted to be sure that Mobile Vision detected text to our satisfaction. Mobile Vision was capable of detecting text, free, and likely worked well with Android.
JUST CALENDAR APP FREE
Cloud Vision was capable of detecting text, but it’s not free (despite being inexpensive).But we did not know how well it worked with text. Amazon Rekognition was supposed to be pretty good at detecting objects within the image.
It didn’t take long for us to zero in on Google Mobile Vision: In particular, the three services we considered were: Alex had some familiarity with OpenCV, but we did not have enough time to come up with our own image recognition models.īased on what I read on the internet, I was aware of certain off-the-shelf libraries and services for image recognition. I had no knowledge whatsoever about computer vision. Though in retrospect step two was harder, our project could’ve been shelved right away if we had failed to detect text from the image. We have zero intentions of making money from this app. This was supposed to be a learning experience, after all. As a consequence, we made some compromises during the design phase. Our focus was to ship a working app as early as possible, and then iron out its shortcomings. App DevelopmentĬreating calendar events from their posters comes down to three things: So my friend Alexander “Alex” Kaberlein and I decided to build this app.
I searched, but I couldn’t find an app that converts images of posters into calendar events. Whenever I saw a poster for some event, such as a concert or conference, I took its picture to keep track of what exactly was on the poster.
0 kommentar(er)
